Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: SEGMENTATION SYSTEM.
Rozprawy doktorskie na temat „SEGMENTATION SYSTEM”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „SEGMENTATION SYSTEM”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
1
Jomaa, Diala. "Fingerprint Segmentation". Thesis, Högskolan Dalarna, Datateknik, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:du-4264.
Pełny tekst źródłaStreszczenie:
In this thesis, a new algorithm has been proposed to segment the foreground of the fingerprint from the image under consideration. The algorithm uses three features, mean, variance and coherence. Based on these features, a rule system is built to help the algorithm to efficiently segment the image. In addition, the proposed algorithm combine split and merge with modified Otsu. Both enhancements techniques such as Gaussian filter and histogram equalization are applied to enhance and improve the quality of the image. Finally, a post processing technique is implemented to counter the undesirable effect in the segmented image. Fingerprint recognition system is one of the oldest recognition systems in biometrics techniques. Everyone have a unique and unchangeable fingerprint. Based on this uniqueness and distinctness, fingerprint identification has been used in many applications for a long period. A fingerprint image is a pattern which consists of two regions, foreground and background. The foreground contains all important information needed in the automatic fingerprint recognition systems. However, the background is a noisy region that contributes to the extraction of false minutiae in the system. To avoid the extraction of false minutiae, there are many steps which should be followed such as preprocessing and enhancement. One of these steps is the transformation of the fingerprint image from gray-scale image to black and white image. This transformation is called segmentation or binarization. The aim for fingerprint segmentation is to separate the foreground from the background. Due to the nature of fingerprint image, the segmentation becomes an important and challenging task. The proposed algorithm is applied on FVC2000 database. Manual examinations from human experts show that the proposed algorithm provides an efficient segmentation results. These improved results are demonstrating in diverse experiments.
2
Wong, Jennifer L. "A material segmentation and classification system". Thesis, Massachusetts Institute of Technology, 2013. http://hdl.handle.net/1721.1/85523.
Pełny tekst źródłaStreszczenie:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2013.Cataloged from PDF version of thesis.
Includes bibliographical references (page 75).
In this thesis, I developed a material segmentation and classification system that takes in images of an object and identifies the material composition of the object's surface. The 3D surface is first segmented into regions that likely contain the same material, using color as a heuristic measure. The material classification of each region is then based on the cosine lobe model. The cosine lobe model is our adopted reflectance model, which allows for a simple approximation of a material's reflectance properties, which then serves as the material's unique signature.
by Jennifer L. Wong.
M. Eng.
3
Östgren, Magnus. "FPGA acceleration of superpixel segmentation". Thesis, Mälardalens högskola, Inbyggda system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-48577.
Pełny tekst źródłaStreszczenie:
Superpixel segmentation is a preprocessing step for computer vision applications, where an image is split into segments referred to as superpixels. Then running the main algorithm on these superpixels reduces the number of data points processed in comparison to running the algorithm on pixels directly, while still keeping much of the same information. In this thesis, the possibility to run superpixel segmentation on an FPGA is researched. This has resulted in the development of a modified version of the algorithm SLIC, Simple Linear Iterative Clustering. An FPGA implementation of this algorithm has then been built in VHDL, it is designed as a pipeline, unrolling the iterations of SLIC. The designed algorithm shows a lot of potential and runs on real hardware, but more work is required to make the implementation more robust, and remove some visual artefacts.
4
Cho, Jinsoo. "Velocity-based cardiac segmentation and motion-tracking". Diss., Available online, Georgia Institute of Technology, 2004:, 2003. http://etd.gatech.edu/theses/available/etd-04082004-180106/unrestricted/cho%5Fjinsoo%5F200312%5Fphd.pdf.
Pełny tekst źródła
5
King, Stephen. "A machine vision system for texture segmentation". Thesis, Brunel University, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.310081.
Pełny tekst źródła
6
Kernell, Björn. "Improving Photogrammetry using Semantic Segmentation". Thesis, Linköpings universitet, Datorseende, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148491.
Pełny tekst źródłaStreszczenie:
3D reconstruction is the process of constructing a three-dimensional model from images. It contains multiple steps where each step can induce errors. When doing 3D reconstruction of outdoor scenes, there are some types of scene content that regularly cause problems and affect the resulting 3D model. Two of these are water, due to its fluctuating nature, and sky because of it containing no useful (3D) data. These areas cause different problems throughout the process and do generally not benefit it in any way. Therefore, masking them early in the reconstruction chain could be a useful step in an outdoor scene reconstruction pipeline. Manual masking of images is a time-consuming and boring task and it gets very tedious for big data sets which are often used in large scale 3D reconstructions. This master thesis explores if this can be done automatically using Convolutional Neural Networks for semantic segmentation, and to what degree the masking would benefit a 3D reconstruction pipeline.3D-rekonstruktion är teknologin bakom att skapa 3D-modeller utifrån bilder. Det är en process med många steg där varje steg kan medföra fel. Vid 3D-rekonstruktion av stora utomhusmiljöer finns det vissa typer av bildinnehåll som ofta ställer till problem. Två av dessa är vatten och himmel. Vatten är problematiskt då det kan fluktuera mycket från bild till bild samt att det kan innehålla reflektioner som ger olika utseenden från olika vinklar. Himmel å andra sidan ska aldrig ge upphov till 3D-information varför den lika gärna kan maskas bort. Manuell maskning av bilder är väldigt tidskrävande och dyrt. Detta examensarbete undersöker huruvida denna maskning kan göras automatiskt med Faltningsnät för Semantisk Segmentering och hur detta skulle kunna förbättra en 3D-rekonstruktionsprocess.
7
Fergusson, Robert Johnstone. "Human visual system based object extraction for video coding". Thesis, University of Strathclyde, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.366673.
Pełny tekst źródła
8
Chen, Cheng. "A General System for Supervised Biomedical Image Segmentation". Research Showcase @ CMU, 2013. http://repository.cmu.edu/dissertations/214.
Pełny tekst źródłaStreszczenie:
Image segmentation is important with applications to several problems in biology and medicine. While extensively researched, generally, current segmentation methods perform adequately in the applications for which they were designed, but often require extensive modifications or calibrations before used in a different application. We describe a system that, with few modifications, can be used in a variety of image segmentation problems. The system is based on a supervised learning strategy that utilizes intensity neighborhoods to assign each pixel in a test image its correct class based on training data. In summary, we have several innovations: (1) A general framework for such a system is proposed, where rotations and variations of intensity neighborhoods in scales are modeled, and a multi-scale classification framework is utilized to segment unknown images; (2) A fast algorithm for training data selection and pixel classification is presented, where a majority voting based criterion is proposed for selecting a small subset from raw training set. When combined with 1-nearest neighbor (1-NN) classifier, such an algorithm is able to provide descent classification accuracy within reasonable computational complexity. (3) A general deformable model for optimization of segmented regions is proposed, which takes the decision values from previous pixel classification process as input, and optimize the segmented regions in a partial differential equation (PDE) framework. We show that the performance of this system in several different biomedical applications, such as tissue segmentation tasks in magnetic resonance and histopathology microscopy images, as well as nuclei segmentation from fluorescence microscopy images, is similar or better than several algorithms specifically designed for each of these applications.
In addition, we describe another general segmentation system for biomedical applications where a strong prior on shape is available (e.g. cells, nuclei). The idea is based on template matching and supervised learning, and we show the examples of segmenting cells and nuclei from microscopy images. The method uses examples selected by a user for building a statistical model which captures the texture and shape variations of the nuclear structures from a given data set to be segmented. Segmentation of subsequent, unlabeled, images is then performed by finding the model instance that best matches (in the normalized cross correlation sense) local neighborhood in the input image. We demonstrate the application of our method to segmenting cells and nuclei from a variety of imaging modalities, and quantitatively compare our results to several other methods. Quantitative results using both simulated and real image data show that, while certain methods may work well for certain imaging modalities, our software is able to obtain high accuracy across several imaging modalities studied. Results also demonstrate that, relative to several existing methods, the template based method we propose presents increased robustness in the sense of better handling variations in illumination, variations in texture from different imaging modalities, providing more smooth and accurate segmentation borders, as well as handling better cluttered cells and nuclei.
9
Fatemi-Ghomi, Navid. "Performance measures for wavelet-based segmentation algorithms". Thesis, University of Surrey, 1997. http://epubs.surrey.ac.uk/794/.
Pełny tekst źródła
10
Brodie, James Cameron. "Investigation of ephrin regulation during hindbrain segmentation". Thesis, University College London (University of London), 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.249431.
Pełny tekst źródła
11
Gasslander, Maja. "Segmentation of Clouds in Satellite Images". Thesis, Linköpings universitet, Datorseende, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-128802.
Pełny tekst źródłaStreszczenie:
The usage of 3D modelling is increasing fast, both for civilian and military areas, such as navigation, targeting and urban planning. When creating a 3D model from satellite images, clouds canbe problematic. Thus, automatic detection ofclouds inthe imagesis ofgreat use. This master thesis was carried out at Vricon, who produces 3D models of the earth from satellite images.This thesis aimed to investigate if Support Vector Machines could classify pixels into cloud or non-cloud, with a combination of texture and color as features. To solve the stated goal, the task was divided into several subproblems, where the first part was to extract features from the images. Then the images were preprocessed before fed to the classifier. After that, the classifier was trained, and finally evaluated.The two methods that gave the best results in this thesis had approximately 95 % correctly classified pixels. This result is better than the existing cloud segmentation method at Vricon, for the tested terrain and cloud types.
12
Jaques, Karen F. "Segmentation and axonal guidance in the vertebrate embryo". Thesis, University of Cambridge, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.386159.
Pełny tekst źródła
13
Harders, Matthias. "Haptically assisted interactive 3D segmentation of the intestinal system /". [S.l.] : [s.n.], 2002. http://e-collection.ethbib.ethz.ch/show?type=diss&nr=14948.
Pełny tekst źródła
14
Lim, Tit Meng. "Segmentation in the nervous system of the chick embryo". Thesis, University of Cambridge, 1987. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.329053.
Pełny tekst źródła
15
Jeong, Dong-Seok. "Nonlinear image restoration using a segmentation-oriented expert system". Diss., Virginia Polytechnic Institute and State University, 1988. http://hdl.handle.net/10919/54333.
Pełny tekst źródła
16
HASE, Hiroyuki, Toyohide WATANABE i Jien KATO. "A Highway Surveillance System Using an HMM-Based Segmentation Method". Institute of Electronics, Information and Communication Engineers, 2002. http://hdl.handle.net/2237/14983.
Pełny tekst źródła
17
Malmberg, Filip. "Segmentation and Analysis of Volume Images, with Applications". Licentiate thesis, Uppsala : Centre for Image Analysis, Swedish University of Agricultural Sciences, 2008. http://epsilon.slu.se/10686781.pdf.
Pełny tekst źródła
18
Tosteberg, Patrik. "Semantic Segmentation of Point Clouds Using Deep Learning". Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-136793.
Pełny tekst źródłaStreszczenie:
In computer vision, it has in recent years become more popular to use point clouds to represent 3D data. To understand what a point cloud contains, methods like semantic segmentation can be used. Semantic segmentation is the problem of segmenting images or point clouds and understanding what the different segments are. An application for semantic segmentation of point clouds are e.g. autonomous driving, where the car needs information about objects in its surrounding. Our approach to the problem, is to project the point clouds into 2D virtual images using the Katz projection. Then we use pre-trained convolutional neural networks to semantically segment the images. To get the semantically segmented point clouds, we project back the scores from the segmentation into the point cloud. Our approach is evaluated on the semantic3D dataset. We find our method is comparable to state-of-the-art, without any fine-tuning on the Semantic3Ddataset.
19
Estgren, Martin. "Bone Fragment Segmentation Using Deep Interactive Object Selection". Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-157668.
Pełny tekst źródłaStreszczenie:
In recent years semantic segmentation models utilizing Convolutional Neural Networks (CNN) have seen significant success for multiple different segmentation problems. Models such as U-Net have produced promising results within the medical field for both regular 2D and volumetric imaging, rivalling some of the best classical segmentation methods. In this thesis we examined the possibility of using a convolutional neural network-based model to perform segmentation of discrete bone fragments in CT-volumes with segmentation-hints provided by a user. We additionally examined different classical segmentation methods used in a post-processing refinement stage and their effect on the segmentation quality. We compared the performance of our model to similar approaches and provided insight into how the interactive aspect of the model affected the quality of the result. We found that the combined approach of interactive segmentation and deep learning produced results on par with some of the best methods presented, provided there were adequate amount of annotated training data. We additionally found that the number of segmentation hints provided to the model by the user significantly affected the quality of the result, with convergence of the result around 8 provided hints.
20
Molin, Joel. "Foreground Segmentation of Moving Objects". Thesis, Linköping University, Department of Electrical Engineering, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-52544.
Pełny tekst źródłaStreszczenie:
Foreground segmentation is a common first step in tracking and surveillance applications. The purpose of foreground segmentation is to provide later stages of image processing with an indication of where interesting data can be found. This thesis is an investigation of how foreground segmentation can be performed in two contexts: as a pre-step to trajectory tracking and as a pre-step in indoor surveillance applications.
Three methods are selected and detailed: a single Gaussian method, a Gaussian mixture model method, and a codebook method. Experiments are then performed on typical input video using the methods. It is concluded that the Gaussian mixture model produces the output which yields the best trajectories when used as input to the trajectory tracker. An extension is proposed to the Gaussian mixture model which reduces shadow, improving the performance of foreground segmentation in the surveillance context.
21
Carlsson, Mattias. "Neural Networks for Semantic Segmentation in the Food Packaging Industry". Thesis, Linköpings universitet, Datorseende, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-145413.
Pełny tekst źródłaStreszczenie:
Industrial applications of computer vision often utilize traditional image processing techniques whereas state-of-the-art methods in most image processing challenges are almost exclusively based on convolutional neural networks (CNNs). Thus there is a large potential for improving the performance of many machine vision applications by incorporating CNNs. One such application is the classification of juice boxes with straws, where the baseline solution uses classical image processing techniques on depth images to reject or accept juice boxes. This thesis aim to investigate how CNNs perform on the task of semantic segmentation (pixel-wise classification) of said images and if the result can be used to increase classification performance. A drawback of CNNs is that they usually require large amounts of labelled data for training to be able to generalize and learn anything useful. As labelled data is hard to come by, two ways to get cheap data are investigated, one being synthetic data generation and the other being automatic labelling using the baseline solution. The implemented network performs well on semantic segmentation, even when trained on synthetic data only, though the performance increases with the ratio of real (automatically labelled) to synthetic images. The classification task is very sensitive to small errors in semantic segmentation and the results are therefore not as good as the baseline solution. It is suspected that the drop in performance between validation and test data is due to a domain shift between the data sets, e.g. variations in data collection and straw and box type, and fine-tuning to the target domain could definitely increase performance. When trained on synthetic data the domain shift is even larger and the performance on classification is next to useless. It is likely that the results could be improved by using more advanced data generation, e.g. a generative adversarial network (GAN), or more rigorous modelling of the data.
22
Schöndell, Andreas. "Evaluation of methods for segmentation of 3D range image data". Thesis, Linköpings universitet, Bildbehandling, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-64657.
Pełny tekst źródłaStreszczenie:
3D cameras delivering height data can be used for quality inspection of goods on a conveyor. It is then of interest to distinguish the important parts of the image from background and noise and further to divide these interesting parts into segments that have a strong correlation to objects on the conveyor belt. Segmentation can easily be done by thresholding in the simple case. However, in more complex situations, for example when objects touch or overlap, this does not work well. In this thesis, research and evaluation of a few different methods for segmentation of height image data are presented. The focus is to find an accurate method for segmentation of smooth irregularly shaped organic objects such as vegetables or shellfish. For evaluative purposes a database consisting of height images depicting a variety of such organic objects has been collected. We show in the thesis that a conventional gradient magnitude method is hard to beat in the general case. If, however, the objects to be segmented are heavily non-convex with a lot of crests and valleys within themselves one could be better off choosing a normalized least squares method.3D-kameror som levererar höjddata kan användas för kvalitetskontroll av varor på ett löpande band. Det är då av intresse att urskilja de viktiga delarna av bilden från bakgrund och brus samt även att dela upp dessa intressanta delar i segment med stark korrelans till objekten på bandet. Segmentering kan utföras genom tröskling i det enkla fallet. I mer komplexa situationer då objekt vidrör eller överlappar varandra blir det svårare. I detta examensarbete presenteras forskning och utvärdering av några olika metoder för segmentering av höjdbildsdata. Fokus ligger på att finna en noggrann metod för segmentering av mjuka släta oregelbundna objekt som grönsaker och skaldjur. I utvärderingssyfte har en databas bestående höjdbilder föreställande lite olika typer av sådana organiska objekt samlats in. Vi visar i uppstatsen att en konventionell gradientlängdsmetod är svår att slå i det generella fallet. Om objekten som ska segmenteras är kraftigt icke-konvexa å andra sidan, med en mängd krön och dalar inom varje objekt, kan man göra bättre i att välja en normaliserad minstakvadratfelsmetod.
23
Thomasson, Viola. "Liver Tumor Segmentation Using Level Sets and Region Growing". Thesis, Linköpings universitet, Datorseende, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-70363.
Pełny tekst źródłaStreszczenie:
Medical imaging is an important tool for diagnosis and treatment planning today. However as the demand for efficiency increases at the same time as the data volumes grow immensely, the need for computer assisted analysis, such as image segmentation, to help and guide the practitioner increases. Medical image segmentation could be used for various different tasks, the localization and delineation of pathologies such as cancer tumors is just one example. Numerous problems with noise and image artifacts in the generated images make the segmentation a difficult task, and the developer is forced to choose between speed and performance. In clinical practise, however, this is impossible as both speed and performance are crucial. One solution to this problem might be to involve the user more in the segmentation, using interactivite algorithms where the user might influence the segmentation for an improved result. This thesis has concentrated on finding a fast and interactive segmentation method for liver tumor segmentation. Various different methods were explored, and a few were chosen for implementation and further development. Two methods appeared to be the most promising, Bayesian Region Growing (BRG) and Level Set. An interactive Level Set algorithm emerged as the best alternative for the interactivity of the algorithm, and could be used in combination with both BRG and Level Set. A new data term based on a probability model instead of image edges was also explored for the Level Set-method, and proved to be more promising than the original one. The probability based Level Set and the BRG method both provided good quality results, but the fastest of the two was the BRG-method, which could segment a tumor present in 25 CT image slices in less than 10 seconds when implemented in Matlab and mex-C++ code on an ACPI x64-based PC with two 2.4 GHz Intel(R) Core(TM) 2CPU and 8 GB RAM memory. The interactive Level Set could be succesfully used as an interactive addition to the automatic method, but its usefulness was somewhat reduced by its slow processing time ( 1.5 s/slice) and the relative complexity of the needed user interactions.
24
Nar, Fatih. "Vessel Segmentation Using Shallow Water Equations". Phd thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613197/index.pdf.
Pełny tekst źródłaStreszczenie:
This thesis investigates the feasibility of using fluid flow as a deformable model for
segmenting vessels in 2D and 3D medical images. Exploiting fluid flow in vessel
segmentation is biologically plausible since vessels naturally provide the medium for
blood transportation. Fluid flow can be used as a basis for powerful vessel
segmentation because streaming fluid regions can merge and split providing
topological adaptivity. In addition, the fluid can also flow through small gaps formed
by imaging artifacts building connections between disconnected areas. In our study,
due to their simplicity, parallelism, and low computational cost compared to other
fluid simulation methods, linearized shallow water equations (LSWE) are used. The
method developed herein is validated using synthetic data sets, two clinical datasets,
and publicly available simulated datasets which contain Magnetic Resonance
Angiography (MRA) images, Magnetic Resonance Venography (MRV) images and
retinal angiography images. Depending on image size, one to two order of magnitude
speed ups are obtained with developed parallel implementation using Nvidia
Compute Unified Device Architecture (CUDA) compared to single-core and multicore
CPU implementation.
25
Anistratov, Pavel. "Computation of Autonomous Safety Maneuvers Using Segmentation and Optimization". Licentiate thesis, Linköpings universitet, Fordonssystem, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-162164.
Pełny tekst źródłaStreszczenie:
This thesis studies motion planning for future autonomous vehicles with main focus on passenger cars. By having automatic steering and braking together with information about the environment, such as other participants in the traffic or obstacles, it would be possible to perform autonomous maneuvers while taking limitations of the vehicle and road–tire interaction into account. Motion planning is performed to find such maneuvers that bring the vehicle from the current state to a desired future state, here by formulating the motion-planning problem as an optimal control problem. There are a number of challenges for such an approach to motion planning; some of them are how to formulate the criterion in the motion planning (objective function in the corresponding optimal control problem), and how to make the solution of motion-planning problems efficient to be useful in online applications. These challenges are addressed in this thesis. As a criterion for motion-planning problems of passenger vehicles on doublelane roads, it is investigated to use a lane-deviation penalty function to capture the observation that it is dangerous to drive in the opposing lane, but safe to drive in the original lane after the obstacle. The penalty function is augmented with certain additional terms to address also the recovery behavior of the vehicle. The resulting formulation is shown to provide efficient and steady maneuvers and gives a lower time in the opposing lane compared to other objective functions. Under varying parameters of the scenario formulation, the resulting maneuvers are changing in a way that exhibits structured characteristics. As an approach to improve efficiency of computations for the motion-planning problem, it is investigated to segment motion planning of the full maneuver into several smaller maneuvers. A way to extract segments is considered from a vehicle dynamics point of view, and it is based on extrema of the vehicle orientation and the yaw rate. The segmentation points determined using this approach are observed to allow efficient splitting of the optimal control problem for the full maneuver into subproblems. Having a method to segment maneuvers, this thesis further studies methods to allow parallel computation of these maneuvers. One investigated method is based on Lagrange relaxation and duality decomposition. Smaller subproblems are formulated, which are governed by solving a low-complexity coordination problem. Lagrangian relaxation is performed on a subset of the dynamic constraints at the segmentation points, while the remaining variables are predicted. The prediction is possible because of the observed structured characteristics resulting from the used lane-deviation penalty function. An alternative approach is based on adoption of the alternating augmented Lagrangian method. Augmentation of the Lagrangian allows to apply relaxation for all dynamic constraints at the segmentation points, and the alternating approach makes it possible to decompose the full problem into subproblems and coordinating their solutions by analytically solving an overall coordination problem. The presented decomposition methods allow computation of maneuvers with high correspondence and lower computational times compared to the results obtained for solving the full maneuver in one step.
26
Kok, Emre Hamit. "Developing An Integrated System For Semi-automated Segmentation Of Remotely Sensed Imagery". Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/12606107/index.pdf.
Pełny tekst źródłaStreszczenie:
Classification of the agricultural fields using remote sensing images is one of the most popular methods used for crop mapping. Most recent classification techniques are based on per-field approach that works as assigning a crop label for each field. Commonly, the spatial vector data is used for the boundaries of the fields for applying the classification within them. However, crop variation within the fields is a very common problem. In this case, the existing field boundaries may be insufficient for performing the field-based classification and therefore, image segmentation is needed to be employed to detect these homogeneous segments within the fields.
This study proposed a field-based approach to segment the crop fields in an image within the integrated environment of Geographic Information System (GIS) and Remote Sensing. In this method, each field is processed separately and the segments within each field are detected. First, an edge detection is applied to the images, and the detected edges are vectorized to generate the straight line segments. Next, these line segments are correlated with the existing field boundaries using the perceptual grouping techniques to form the closed regions in the image. The closed regions represent the segments each of which contain a distinct crop type. To implement the proposed methodology, a software was developed. The implementation was carried out using the 10 meter spatial resolution SPOT 5 and the 20 meter spatial resolution SPOT 4 satellite images covering a part of Karacabey Plain, Turkey. The evaluations of the obtained results are presented using different band combinations of the images.
27
Phuyal, Bishnu P. "Adaptive trajectory segmentation method and its application in in-car navigation system /". The Ohio State University, 2001. http://rave.ohiolink.edu/etdc/view?acc_num=osu1488205318508526.
Pełny tekst źródła
28
Lee, We Hung, i 李威亨. "An Improved Document Segmentation System". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/62583290250708391241.
Pełny tekst źródłaStreszczenie:
碩士中原大學
資訊工程研究所
82
Most of document segmentation systems still have shortcomings. Firstly, most of them could not possess both the advantages of efficiency and validity at the same time. Secondly, requirement of human intervention to provide comparative data hinders the motivation of office automation. Lastly, the skew produced by artificiality or the machine itself , even though several researches provide needed solutions , a choice between wasting time or reliability of detection method still has to be made. By taking the advantage of skew sensitivity and sample points'' sequence independency, based on the Hough transform for skew angle detection, we devise an efficient technique（Synoptic image）to decrease the large amount of sample points within the document image and reduce the expensive time complexity during Hough transform obviously. As for the block segmentation and recognition, we use the technique of connected component labeling process in combination with boundary shrinking process to find out the outside frames of white regions for table blocks. Then, feedback the mapping image to the Recursive X_Y Cut (RXYC) process to extract the content which we are just interested in. Besides, we particularly break up the RXYC into schemes of two passes. In pass one, we cut the document image into small and broken blocks, then merging process is involved in pass two. By doing so, we can also obtain an important information during pass one -- the average height of text blocks. We can use this information as an important guide in the block classification process, thereby increasing the validity of the segmentation and recognition.
29
Jiun-Liang, Lai, i 賴俊良. "Normalized Cut Based Texture Segmentation System". Thesis, 2001. http://ndltd.ncl.edu.tw/handle/03881273508111843299.
Pełny tekst źródłaStreszczenie:
碩士中華大學
電機工程學系碩士班
89
Image segmentation, which partitions images into homogeneous regions, is an important task in many computer vision applications. Typically, differences in gray levels and/or colors alone are not sufficient for segmenting images of interest. This problem may be solved to a certain degree by taking account of the texture information. One of the commonly used approaches to extracting texture features is the frequency approach. In this thesis, we used Gabor filters to extract texture features in various frequency bands. Based on these features, the Normalized cut measure of similarity between pixels are used to partition images such that the disassociation between different textures and the association within similar texture are to be maximized simultaneously. We also developed a texture segmentation system in which the Gabor filter based feature space is transformed into the Normalized cut based feature space by solving the associated generalized eigen-system efficiently. The performance improvement can be demonstrated by the experimental results on segmentation of some Brodatz textures.
30
Lin, Mei-Lin, i 林玫霖. "MRI Based Acoustic Neuroma Image Segmentation System". Thesis, 2011. http://ndltd.ncl.edu.tw/handle/82435459192491022005.
Pełny tekst źródłaStreszczenie:
碩士國立中興大學
資訊管理學系所
99
This research proposes a MRI based acoustic neuroma image segmentation system. Acoustic neuroma, also known as vestibular schwannoma, is one kind of intracranial tumor. Most commonly, acoustic neuroma arises in a wedge shaped area bounded by the petrous bone, the pons and the cerebellum. Acoustic neuroma results from abnormal hyperplasia of Schwann cells of the inferior vestibular nerve. Generally, acoustic neuroma is often a benign tumor; however, it still has potential probability to become a malignant tumor that usually grows faster and tends to spread to other organs which may seriously harm human bodies or even cause death. Acoustic neuroma MR images which are scanned by the doctor are used in this research to detect the location of tumors. The involvement of the user is needed in this research. A seed point is assigned by the user, and edge based segmentation methods such as gradient calculation, edge enhancement, and noise reduction are used to illustrate edge of the acoustic neuroma in MRI. Besides, a region growing method is used to get the intensity feature of the acoustic neuroma. The combination of edge based segmentation methods and the region growing method provides a good result in acoustic neuroma segmentation. The goal of this research is to solve great amount of waste in medical resource and time consuming in traditional acoustic neuroma detection. ACM and LSM are used to investigate the performance of the proposed method. In order to quantitate segmentation results, four commonly used segmentation error measures (ME, RAE, MHD, and RDE) are used in this research. The results show that the proposed method is better than other two methods with regards to segmentation accuracy.
31
Chen, Ping-Che, i 陳秉哲. "An Interactive System for Video Object Segmentation". Thesis, 2002. http://ndltd.ncl.edu.tw/handle/01836425769421399162.
Pełny tekst źródłaStreszczenie:
碩士國立臺灣大學
資訊工程學研究所
90
Video object segmentation is to extract an object from an image sequence. Single image segmentation is very hard; generally human intervention is re-quired for correct results. The motion information in an image sequence makes video object segmentation easier. However, there is still no algorithm that can automatically segment video objects precisely. Furthermore, it is in-efficient to perform single image segmentation for each image in the image sequence independently, for both supervised and unsupervised approaches. Therefore, it is important to utilize the temporal coherence between images in an image sequence. We proposed a video object segmentation system that combines both supervised single image segmentation and interactive video object tracking. The user uses a single image segmentation tool to extract the video object in one or more images, and use the interactive tracking tool to find the video object in the remaining images. The tracking tool is hierarchical, from higher detail level to lower detail level. The user can interactively correct the track-ing result between two tracking operations to ensure the correctness. The experimental results show that this system is simple to use and the user is able to obtain accurate results.
32
ZHANG, ZHI-WEI, i 張志偉. "An expert system for Chinese newspaper segmentation". Thesis, 1991. http://ndltd.ncl.edu.tw/handle/62582344275980366294.
Pełny tekst źródła
33
Yang, Shi-Ming, i 楊世銘. "An Image Segmentation System Based on Blackboard Architecture". Thesis, 2001. http://ndltd.ncl.edu.tw/handle/43357827014203266396.
Pełny tekst źródłaStreszczenie:
碩士國立成功大學
電機工程學系
89
The Segmentation process of a medical image is a complex work. We need to integrate image processing and medical knowledge to segment the regions of interest. Since a blackboard architecture can integrate multiple processes into a system as knowledge sources, we make use of the blackboard architecture to integrate image processing and expert knowledge to segment the regions of interest in a medical image automatically. As far as image processing is concerned, we use multi-resolution approach of image segmentation system or active contour model system to segment images. After the image segmentation, the image is partitioned into several regions. We interpret these features of regions into an abstract level. Finally, we use the expert knowledge and the features of regions to classify these regions. We also provide some user interface to enable users to modify the results. We focus our attention on the data representation, knowledge representation, and the mechanism of blackboard architecture aspects.
34
Fang, Dong-Sen, i 方東森. "Video Segmentation System Of Moving Object Using FPGA". Thesis, 2002. http://ndltd.ncl.edu.tw/handle/19535055062906259310.
Pełny tekst źródłaStreszczenie:
碩士國立臺北科技大學
自動化科技研究所
90
The application of moving object segmentation is an essential technique on whether image identification or MPEG_4 compression techniques in the future. Moving object segmentation is also an important preprocessing stage in image capture procedures. MPEG_4 is currently the most focused compression technique. Therefore, to develop a way to retrieve video object within dynamic images in MPEG_4 is the key topic. The results of current researches over this topic tend to consume much processing time, and are also hard for hardware implementation. Therefore it’s quite difficult to apply moving object segmentation in real time. We first propose an easily implemented hardware moving object segmentation algorithm focused on this goal. We also propose an effective MADND (Mean Absolute Different Noise Deletion) algorithm for noise reduction, and a full orientated object scan algorithm to identify object region. In moving object detection, we propose a TFDA (Triple Frames Different And ) algorithm which is capable of detecting precise object region without complex operation. In hardware framework, we use a FPGA from Xilinx Vertex_E600 to design, simulate and integrate system algorithm . The result is a fast moving object segmentation hardware system . After design and test stages, we conclude the features of our system: 1.Simple and easily implemented algorithms. 2.Efficient in segmentation, can apply different segmentation approaches according to different conditions. 3.Provide fast segmentation ability to fit in real time MPEG_4 transmitting framework. 4.Can be used as an IP in image processing SOC.
35
Cheng, Wei-Yun, i 鄭為允. "Neuron Segmentation and Tracing system for Brainbow Imagery". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/55075990745816425601.
Pełny tekst źródłaStreszczenie:
碩士國立清華大學
電機工程學系
100
Due to dozens of colorized neuron fibers spreading densely in a very intricate structure, it is difficult to trace them by using existing algorithms designed for monochrome single-neuron images and also time-consuming to label them manually. We propose a neuron segmentation system on Drosophila Brainbow image stack. The idea follows the steps of manually, that is, the system is designed to imitate the way biological experts identify different neurons. Besides, because the “color information” of Brainbow imagery is a composite signal coming from those captured by different band-pass filters, it is straightforward to consider each channel independently. On the other hand, according to the considerable morphological differences between cell bodies and neuron fibers, some three-dimensional morphological processing methods could also be applied. Based on the location and the fluorescence intensity of each cell body, we can trace and segment each neuron by considering the similarities among adjacent voxels. The proposed system can provide segmentation results semi-automatically, and thus it would be useful for biologists in identifying the neural-circuits.
36
Wang, Guang-Tzu, i 王光祖. "An Automatic Phalangeal Segmentation System with Carpal Information". Thesis, 2013. http://ndltd.ncl.edu.tw/handle/72803067902843751900.
Pełny tekst źródłaStreszczenie:
碩士國立清華大學
電機工程學系
101
Abstract The objective of this thesis is to develop an automatic and accurate phalangeal segmentation system, which can constitute a fully automatic phalanx bone age assessment system by adding feature extraction and analysis/classification stages in the future. Study shows that generally the result of segmentation can be further improved by a proposed preprocessing of adjusting the gray level distribution of the knuckle images, i.e., EMROI (epiphyseal/metaphyseal bone region of interest), before entering the bone edge detection/segmentation stage. The improvements are more profound in the cases of younger children however, for children with age over 8 and elder the effects of the proposed preprocessing become less effective and even deteriorate the segmentation results. Therefore this thesis proposes an age-dependent preprocessing scheme before entering the bone edge detection/segmentation stage. Observing that the density of carpal area increases with age, we propose a method utilizing such growth characteristics of carpal to quickly determine the prior knowledge of age for the hand radiogram under segmentation. A knuckle segmentation process is proposed. First, the input X-ray hand-image is processed and nine knuckle images of the index finger, middle finger, ring finger (i.e., 9 EMROI’s) are segmented. Then the prior knowledge of age is determined by using the carpal area density characteristics and the age-dependent preprocessing based on the prior knowledge of age is applied to the 9 EMROI’s. Finally, image segmentation is applied to detect the bone edges and/or contours in those knuckle images. Four image segmentation methods, namely GVF snake, round-average deduction method, adaptive two-means clustering algorithm and the level set evolution are adopted in our experiments. Six error measures: ME (misclassification error), RFAE (relative foreground area error), NU (non-uniformity), MHD (modified Hausdorff distances), EMM (edge mismatch), and Mean Errors are used to assess the effectiveness of the proposed phalanx image segmentation process. The experimental results show that the error measures for the cases of incorporating prior knowledge of age and proposed age-dependent preprocessing are generally better than those cases without using prior knowledge of age and proposed preprocessing. For example, the values of mean errors are improved from 28% to 33% for the four different segmentation methods, respectively.
37
Tzeng, Yi-Syuan, i 曾詣玹. "Auto accessory segmentation and interactive try on system". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/n92kwt.
Pełny tekst źródłaStreszczenie:
碩士國立中央大學
資訊工程學系
105
The convenience and diversity of online shopping makes many consumers willing to buy apparel or accessories on the web. In order to make products more attractive to users, many virtual try-on systems are developed for e-commerce applications. This paper proposes an interactive virtual try-on system combined with automatic accessory segmentation. Our system automatically retrieves the accessory from images and store them in the try-on system to provide users with subsequent selection. When a user selects the hat that he or she wants to try on, the accessory is placed on the proper position of the user in the image. In the stage of accessories segmentation, we perform background elimination and super-pixel segmentation. According to the color information on the accessory image, the feature vector generated by the color histogram is used to select super-pixels that belong to the accessories. In the stage of try-on system, we use Kinect, which provides skeleton information, to track the user’s face and gestures. When a user selects the accessory, the proposed system reads the corresponding accessory information and places the accessory in the appropriate location based on the results of the face tracking. In the experiment, the segmentation part of our system can reach an accuracy of more than 90%. The proposed try-on system can reach 30 fps real-time speed in a personal computer.
38
Godfrey, Andrea Lynn. "A product segmentation approach and its relationship to customer segmentation approaches and recommendation system approaches". Thesis, 2007. http://hdl.handle.net/2152/3054.
Pełny tekst źródła
39
Godfrey, Andrea Lynn 1973. "A product segmentation approach and its relationship to customer segmentation approaches and recommendation system approaches". 2007. http://hdl.handle.net/2152/13234.
Pełny tekst źródła
40
Chen, Chien-Hao, i 陳建豪. "The Development of Video Segmentation System Using the Multiresolution and Flooding Based RSST (MFRSST) Segmentation Method". Thesis, 2003. http://ndltd.ncl.edu.tw/handle/18773195468832706040.
Pełny tekst źródłaStreszczenie:
碩士中華大學
資訊工程學系碩士班
91
Abstract In the recent years, a lot of research activities are addressed on the video segmentation problems for developing the object-based video processing systems. Based on the extension of the image segmentation methods, the video segmentation systems may be constructed for obtaining the video objects and then developing the object-based video processing systems. The video objects are acquired by applying the image and video features, such as color, intensity, motion, texture, and shapes, to partition the regions with the same feature homogeneity. Hence, the quality and efficiency of the video segmentation system will determine the performance of the object-based video processing system. However, the conventional image segmentation methods have some problems that make the video segmentation process inaccurate, i.e., they can’t ensure the region connectivity, define the region boundaries accurately, and partition image with an arbitrary number. The method of the recursive shortest spanning tree (RSST) is proposed to improve the above problems and is widely adopted in many video segmentation systems. In the following, the fast RSST (FRSST) algorithm is proposed to reduce the computation complexity by removing the sorting process in the RSST method. However, the FRSST method is still too inefficient to meet the requirements for some new visual applications such as video segmentation, region-based video coding, and object-based video retrieval. In this thesis, the concepts of multiresolution decomposition and flooding process of watershed algorithm are applied to develop the multiresolution and flooding based RSST (MFRSST) image segmentation method that can speed up the image segmentation process and have the same partition quality as the RSST. In the MFRSST segmentation method, the N + M regions are partitioned by the two-step segmentation processes. Firstly, a lower resolution subband image is obtained by the multiresolution decomposition process and then the subband image is partitioned into N regions by using the flooding and FRSST methods. Secondly, the region boundary refinement process is applied to obtain additional M detailed regions. The region number can be specified by the user, but it is not suitable for video segmentation system. The segmentation number N + M is difficult to be determined automatically, hence, the number N+M is determined according to the statistical property of the image. In theory, the larger number is demanded for the complex image and the lower number is enough for the smooth image. On the basis of the MFRSST, we improve the COST211 video segmentation system by applying the optical flow motion detection method such that the rotation and zooming movements of objects can be detected. Because the optical flow method can calculate the motion vectors of rotation and zoom, the objects with the uniform rotation or zooming motion vectors can be segmented. In the new improved segmentation system, the YIQ color space is used for color segmentation and the motion information is used for motion segmentation. It is important to define the link values for the color and motion in segmentation system. The definition of the link values will affect the quality of segmentation.
41
CHEN, YIH-TAY, i 陳易泰. "PCB Dimension Measuring System Based on Color Image Segmentation". Thesis, 2000. http://ndltd.ncl.edu.tw/handle/29237934860771078185.
Pełny tekst źródłaStreszczenie:
碩士中華大學
機械與航太工程研究所
88
As the electric circuit getting more compact and complicated, and the trace width getting finer and finer, the printed circuit board inspection processes become more difficult and time-consuming. As a result, traditional inspection method using bare eye with the aid of microscope or magnifier can no longer satisfy the need for high speed and high accuracy. To cope with this situation, an automated optical inspection system is developed in this research. By integrating image processing, stage and light source control techniques, the developed system can automatically inspect fiducial mark, trace, and pad with variety of shapes and sizes in an off-line fashion. Generally speaking, the measuring of circle (fiducial mark, circular pad), rectangle (rectangular pad), and line width (trace) can be accomplished in three steps. Firstly, color segmentation techniques based on classification method are used to isolate the desired object from the selected area of color PCB image. In this research, four classifiers are investigated including minimal-distance classifier, Bayesian classifier, neural network, and fuzzy set theory. Secondly, edge detection technique is applied to collect all the edge points representing profile of the object. Finally, by adopting a suitable curve fitting technique, major dimensions of the pad can be obtained. As to the speed and accuracy, the experimental results show that the inspection method based on neural-network classifier possesses the highest measuring accuracy; however, the inspection method based on minimal-distance classifier can complete the measurement most quickly. It is worthwhile to notice that, no matter which segmentation method is used, the maximum error is less than 3% of the standard dimension for circular pad or 5% for rectangular pad. In addition to mentioned measurement function, the developed system can also be used to detect flaws, such as pinhole, protrusion, and spurious copper. The developed automated optical inspection system is presented. Some important techniques established in this research, including color segmentation, curve fitting, and defect detection, are discussed in detailed in this thesis.
42
Wang, Yi-Ting, i 王意婷. "Skin segmentation system automatically adapted to image illumination conditions". Thesis, 2008. http://ndltd.ncl.edu.tw/handle/94786729661413283965.
Pełny tekst źródłaStreszczenie:
碩士開南大學
資訊管理學系
97
Skin detection is a two-class classification problem; every pixel in an image is finally assigned to the skin class or non-skin class based on a decision scheme. Several classification methods can be used to solve this problem, for instance, explicit skin-color thresholding, Bayes classifiers, neural network classifiers and so on. Previous studies of skin detection with Bayes classifiers employed a fixed skin color model to treat each image regardless of the illumination condition in the image. However, presentation of skin color in images can be influenced by illumination conditions and thus makes the result of skin segmentation degrade. To solve this problem, a self-adapting method is proposed, which can conform to varying skin color caused by different lighting conditions or races. This method collects some representative skin samples from the input image and uses them to tune a trained skin color model. The adapted skin color model can match better the skin distribution in the input image and increases the skin segmentation accuracy. The proposed approach consists of a training stage and a skin detection stage. In the training stage, a skin image data set and a non-skin image data set are scanned independently to calculate a skin color model and a non-skin color model. In the skin detection stage, the trained skin color model is used to select the pixels most likely to be skin in an image. Then, the selected skin pixels are used to build a new skin color model and this new model is combined with the trained skin color model to detect all the skin pixels. The underlying idea of the proposed approach is that the trained skin model is tuned by imposing a local skin model to make the resulting skin model adapt to the current image. After testing over 18000 images, it shows that the new method performs better than the original method.
43
Hwuang, Jin-Fu, i 黃君富. "A Blackboard-based Segmentation System for Brain MRI Images". Thesis, 1996. http://ndltd.ncl.edu.tw/handle/23453114436419902982.
Pełny tekst źródłaStreszczenie:
碩士國立成功大學
電機工程研究所
84
Medical image interpretation is a complex task that req- uires the integration of knowledge acquired from different domains such as medicine, image processing and computer vision. This thesis describes a brain MRI-scan segmentation system based on traditional techniques of image processing and a blackboard architecture expert system. In image processing, we use automatic region growing to segment the brain parts of the head images. The seed points needed in the process of region growing are chosen accord- ing to common features of the brain parts in MRI images. Then these seeds are screened automatically by some limita- tions and follow some criteria to grow up to the regions we are interested in. After segmentation, the binary segmented image has several candidate regions for the brain. Each of them are then converted to computer-acceptable forms, and are judged by the knowledge sources in the blackboard system. In this thesis, we analyze problems of image processing, data representation and blackboard mechanism, and propose a practical solution for them. Besides, we also discuss its applicability in other situations.
44
Hwang, Yao-Chien, i 黃耀仟. "Design and Implementation of an Automatic Phalangeal Segmentation System". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/59339959797925113666.
Pełny tekst źródłaStreszczenie:
碩士國立清華大學
電機工程學系
98
The thesis aims at developing an algorithm and its Matlab program to identify phalangeal ROI and to accurately segment the phanlangeal bone from the soft tissue and background in a left-hand X-ray image, so that the segmentation result can be utilized in subsequent feature extraction, analysis, and classification modules in a fully automatic computer assisted bone age assessment system. When inputting the cropped left-hand X-ray image from DICOM, the developed program can automatically process the image, remove the background to obtain the hand mask, locate the five phalangeal ROI’s, and segment the phanlangeal bone from the soft tissue and background of the distal, middle, and proximal phalanx without further human intervention and parameter adjustments. Three major steps are employed in the developed program. First, the background portion of the left-hand X-ray image is removed by using the histogram mode with triangular algorithm to find a proper threshold to remove the background and to obtain the proper hand mask. Then using the centroid of the palm portion of the hand mask as a starting point with scan method, the locations of five fingers are determined and the corresponding phalangeal ROI’s are extracted. Finally, for each extracted distal, middle, and proximal ROI, the phalanx is segmented from tissue and other unnecessary background region by using a trapezoid algorithm, round-average deduction algorithms, and Matlab filling tool. 40 left hand X-ray images and 200 left hand images from more than 700 different subjects with ages covering 0 to 19 for both genders are processed and segmented by the proposed algorithm. The results statistics showed that, it only takes less than 10 seconds by the proposed Matlab program from reading-in a left-hand image to producing the segmented result, and most of the images can produce successfully extracted middle, distal, and proximal phalanx ROI’s, which are the three most important phalanx regions in clinical bone age research. Meanwhile, for comparison purpose, adaptive two-means segmentation algorithm is also implemented and the segmentation results of the proposed round-average deduction method and adaptive two-means on extracting phalanx bone region are evaluated by using five error measures: ME, RFAE, EMM, MHD, and NU. The experimental result statistics showed that, the proposed round-average deduction method performs better than adaptive two-means method on ME、RFAE、EMM and NU, but is worse on MHD. However, the round-average deduction method executes much faster than adaptive two-means.
45
Lin, Yi-Ling, i 林倚鈴. "Video Handwritten Chinese Character Recognition System Using Stroke Segmentation". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/47803280429289060109.
Pełny tekst źródłaStreszczenie:
碩士大同大學
資訊工程學系(所)
98
In recent years, traditional text input devices are changed gradually to handwriting. Though handwriting board and touchpad are easy to use, they are inconvenient to carry. This paper proposes a video handwritten Chinese character recognition system using stroke segmentation and on-line model. Firstly, the location of fingertip is extracted and the fingertip trajectory is recorded for recognition. The trajectory is straight line approximated by finding the turning points of strokes. Owing to the loss of depth information, it is unknown the user is going to write or move the fingertip. Therefore ,character writing habits are utilized to develop rules for pen-up and pen-down strokes classification. The main idea is to find impossible strokes which represent pen-up strokes for moving fingertip. The first case of pen-up stroke is from right to left or bottom to up. The second case is that the pen-up stroke would not exist between two parallel strokes. The third case is that the next pen-down stroke would not be of the opposite direction with the current one. The forth case is pen-up stroke between left and right character components. And the last case is pen-up stroke between upper on lower character component. These rules are used to segment the character into pen-down and pen-up strokes. In addition to stroke direction, stroke types, stroke length ratio, and angle between two consecutive strokes are also used to build the character online model as a four tuple continuous sequence of string. For characters written with multiple ways, we could build more than one online model for these characters. Minimum edit distance by dynamic programming is deployed to match the input character on-line string with stored online character models for recognition. In experiments, we build about 1000 Chinese character on-line models. The recognition system is tested with five persons writing each of the 1000 Chinese characters three times. There are totally 548726 images with camera of capturing speed 30 frames per second. The accuracy of fingertip tracking is 98.88% with processing speed 12.6 times per second. The accuracy of pen-up and pen-down stroke segmentation is 91.56% and the accuracy of character recognition is 93.61%. These results demonstrate that the proposed method could be used to input characters by fingertip efficiently.
46
Lu, Ko-Yen, i 呂科諺. "Anchorperson Detection for TV News Segmentation System viaVisual Features". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/88735793065027978044.
Pełny tekst źródłaStreszczenie:
碩士國立中興大學
電機工程學系所
94
In this thesis, we designed a scheme for TV news segmentation via video content analysis techniques and explored the efficient visual features. The scheme can be divided into three parts, such as anchorperson shot change detection based on skin color, probable anchorperson segment detection and anchorperson detection. An anchorperson shot surely contains face region, and this feature is informative and important for anchorperson shot change detection. In order to reduce computational complexity for face detection, we only use skin color information as the major tool for searching face region. Otherwise, the anchorperson shot time should be shorter than that of a report shot time. As a result, we make use of the properties above also called time constraint method to discover the probable anchorperson segments. However, the probable anchorperson segment might involve the report segment, it will effect the detect precision. Here, we exploit the region histogram based on non-skin color method to exclude report segments. According to simulation results, our proposed method can efficiently decompose TV news into anchorperson shots and report segments. The proposed method can easily apply to software and hardware based personal video recorder for efficiently accessing the large amount of TV news video in the near future.
47
Tsao, Sheng-Che, i 曹盛哲. "Neural Networks Techniques for Image Segmentation and Control System". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/35639006883699256795.
Pełny tekst źródłaStreszczenie:
碩士國立交通大學
控制工程系
82
This thesis is divided into two parts. Part I of this thesis studies the biologically derived image processing techniques－ the FBF network. We take advantage of biological vision system to solve a lot of tradeoff existing in traditional image segmentation algorithms. We discuss the most important element of FBF network－the shunting competitive neural networks. A biological perception model which is called FACADE theory is discussed. The main point of part I is to discuss the structure and properties of the FBF network.The FBF network uses multimask formulation and hierarchical structure to detach a desired figure from background. A vector analysis for the oriented masks of FBF networks is provided. Finally,we provide some examples to explain the effect of parameter variation. Part II of this thesis concentrates on the application of Gaussian neural networks on nonlinear control system. A Gaussian networks design procedure, which determines the networks parameters via frequency analysis is reviewed. We discuss the performance of the Gaussian network controller and compare it with a similar neural network controller－the CMAC. Finally, we demonstrate that the training time and memory needed for achieving certain accuracy would increase tremendously as input and output dimension increase.
48
Yang, Yu Hao, i 郭永隆. "A Multiscale Based System for Texture Classification and Segmentation". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/99266865333948642674.
Pełny tekst źródłaStreszczenie:
碩士國立成功大學
資訊及電子工程研究所
82
Texture analysis extracts more attention in digital image processing and pattern recognition, and is widely applied to the processing and interpretation of medical and remotely sensed data where texture information is sometimes the only way to characterize a digital image. A new multiscale method for texture analysis based on Gaussian wavelet decomposition has been proposed. We utilize the number of local extreme in each scale, which is different for different textures, as our texture feature (wavelet feature) and prove that this feature is invariant to gray level deviation in color space. First, we address the problem of texture classification. Wavelet features derived from 16 texture patterns are extracted and utilized as model features to train the decision surface in error back propagation neural network(EBPT). Experiments for texture classification with these 16 patterns have shown an accuracy rate for 96.5%. The data set consists of two hundred and fifty-six textural subimages equally distributed among sixteen classes of texture.
49
Guo, Yong Long, i 郭永隆. "A multiscale based system for texture classsification and segmentation". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/15271201850359202973.
Pełny tekst źródła
50
Sahba, Farhang. "Reinforced Segmentation of Images Containing One Object of Interest". Thesis, 2007. http://hdl.handle.net/10012/3420.
Pełny tekst źródłaStreszczenie:
In many image-processing applications, one object of interest must
be segmented. The techniques used for segmentation vary depending
on the particular situation and the specifications of the problem
at hand. In methods that rely on a learning process, the lack of a
sufficient number of training samples is usually an obstacle,
especially when the samples need to be manually prepared by an
expert. The performance of some other methods may suffer from
frequent user interactions to determine the critical segmentation
parameters. Also, none of the existing approaches use online
(permanent) feedback, from the user, in order to evaluate the
generated results. Considering the above factors, a new
multi-stage image segmentation system, based on Reinforcement
Learning (RL) is introduced as the main contribution of this
research. In this system, the RL agent takes specific actions,
such as changing the tasks parameters, to modify the quality of
the segmented image. The approach starts with a limited number of
training samples and improves its performance in the course of
time. In this system, the expert knowledge is continuously
incorporated to increase the segmentation capabilities of the
method. Learning occurs based on interactions with an offline
simulation environment, and later online through interactions with
the user. The offline mode is performed using a limited number of
manually segmented samples, to provide the segmentation agent with
basic information about the application domain. After this mode,
the agent can choose the appropriate parameter values for
different processing tasks, based on its accumulated knowledge.
The online mode, consequently, guarantees that the system is
continuously training and can increase its accuracy, the more the
user works with it. During this mode, the agent captures the user
preferences and learns how it must change the segmentation
parameters, so that the best result is achieved. By using these
two learning modes, the RL agent allows us to optimally recognize
the decisive parameters for the entire segmentation process.