Rozprawy doktorskie na temat „FUZZY EDGE DETECTION”

Este trabalho desenvolveu um novo método para a detecção de contornos em imagens digitais que apresentam objetos de interesse muito próximos e que contêm complexidades associadas ao fundo da imagem como variação abrupta de intensidade e oscilação de iluminação. O método desenvolvido utiliza lógicafuzzy e desvio padrão da declividade (Desvio padrão da declividade fuzzy - FuzDec) para o processamento de imagens e detecção de contorno. A detecção de contornos é uma tarefa importante para estimar características de escoamento bifásico através da segmentação da imagem das bolhas para obtenção de parâmetros como a fração de vazio e diâmetro de bolhas. FuzDec foi aplicado em imagens de instabilidades de circulação natural adquiridas experimentalmente. A aquisição das imagens foi feita utilizando o Circuito de Circulação Natural (CCN) do Instituto de Pesquisas Energéticas e Nucleares (IPEN). Este circuito é completamente constituído de tubos de vidro, o que permite a visualização e imageamento do escoamento monofásico e bifásico nos ciclos de circulação natural sob baixa pressão.Os resultados mostraram que o detector proposto conseguiu melhorar a identificação do contorno eficientemente em comparação aos detectores de contorno clássicos, sem a necessidade de fazer uso de algoritmos de suavização e sem intervenção humana.
This work has developed a new method for digital image contour detection which can be successfully applied to images presenting objects of interest with high proximity and presenting complexities related with background abrupt intensity fluctuations. The developed method makes use of fuzzy logic and declivity standard deviation (Fuzzy Declivity Standard Deviation FuzDec) to image processing and contour detection. Contour detection is an important task to estimate two-phase flow features through bubble segmentation in order to obtain parameters as void fraction and bubble diameter. FuzDec was applied to natural circulation instability images which were experimentally acquired. Image acquisition was done at the Natural Circulation Circuit (CCN) of the Instituto de Pesquisas Energéticas e Nucleares (IPEN) in Brazil. This facility is all made up with glass tubes allowing easy visualization and imaging of one-phase and two-phase flow patterns during natural circulation cycles under low pressures. Results confirm that the proposed detector can improve contour identification when compared to classical contour detector algorithms, without using smoothing algorithms or human intervention.

Submitted by Claudinei Pracidelli (cpracide@ipen.br) on 2016-11-11T13:03:47Z No. of bitstreams: 0
Made available in DSpace on 2016-11-11T13:03:47Z (GMT). No. of bitstreams: 0
Este trabalho desenvolveu um novo método para a detecção de contornos em imagens digitais que apresentam objetos de interesse muito próximos e que contêm complexidades associadas ao fundo da imagem como variação abrupta de intensidade e oscilação de iluminação. O método desenvolvido utiliza lógicafuzzy e desvio padrão da declividade (Desvio padrão da declividade fuzzy - FuzDec) para o processamento de imagens e detecção de contorno. A detecção de contornos é uma tarefa importante para estimar características de escoamento bifásico através da segmentação da imagem das bolhas para obtenção de parâmetros como a fração de vazio e diâmetro de bolhas. FuzDec foi aplicado em imagens de instabilidades de circulação natural adquiridas experimentalmente. A aquisição das imagens foi feita utilizando o Circuito de Circulação Natural (CCN) do Instituto de Pesquisas Energéticas e Nucleares (IPEN). Este circuito é completamente constituído de tubos de vidro, o que permite a visualização e imageamento do escoamento monofásico e bifásico nos ciclos de circulação natural sob baixa pressão.Os resultados mostraram que o detector proposto conseguiu melhorar a identificação do contorno eficientemente em comparação aos detectores de contorno clássicos, sem a necessidade de fazer uso de algoritmos de suavização e sem intervenção humana.
t
IPEN/T
Instituto de Pesquisas Energeticas e Nucleares - IPEN-CNEN/SP

Images are one of the best sources for research & communication. Proper analysis of image data is essential for various fields like satellite images & remote sensing, Biometrics, Criminology, military surveillance, astrology & many more. Requirements of the users vary according to the nature of application in use.Image processing plays a critical role in the analysis of data and is an integral part for various applications. Image denoising is one of the challenging branches of image processing. Impulse noise is among the prevalent noises that degrade the image quality and its subsequent noise suppression plays a pivotal role in the enhancement of images. The presence of impulse noise cannot be averted during the digitization, acquisition, and transmission of images. Many state of art filters are available in the literature to deal with impulse noise encountered in images. Filters having dual modes of detection and restoration exhibit superior performance in removing noise and thereby keeping the original information of the images intact. In real world sometimes the user is uncertain about his requirements therefore the characteristics of the employed filter for impulse noise removal should be adaptable to the indecisive features of an image.The denoising filter should be robust enough to handle the varying amounts of noise density and should be intuitive in nature. This thesis work tries to cater to all the essential features required for an efficient filter. Incorporation of fuzzy logic makes the filter more versatile.Investigations performed in this thesis show that the proposed work excels in the quantitative as well as qualitative manner. Four schemes introduced in this thesis are : (i) High-density impulse noise detection using FCM algorithm (HDIND) viii (ii) Edge preserving fuzzy filter for the suppression of impulse noise in images (EFFSIN) (iii) Heuristic analysis of neighboring pixels for impulse noise detection (SPHN) (iv) Impulse noise removal in color image sequences using Fuzzy logic (INFL) The initial three schemes namely HDIND, EFFSIN, and SPHN focus on the grayscale images and INFL is proposed for color image sequences. All the schemes incorporate an efficient detection criterion and after proper classification of noisy and noise-free pixels, performs the restoration procedure. The use of fuzzy logic in the methods has enhanced the decision making aspect of the algorithms to classify the noisy pixels present in an image. The simulation results are done in isolation for all the schemes deduce that HDIND and EFFSIN are robust in nature and their performance does not deteriorates with a rise in noise density. The edge-preserving nature of EFFSIN preserves the original image data and false alarm rates are reduced. SPHN provides good PSNR and MSE results. INFL is a Spatio-temporal filter that gives excellent performance. SSIM, PSNR, MSE, False alarm and Miss detection rates are used as quality measures to analyze the proposed mechanisms.

O objetivo deste trabalho é apresentar uma nova abordagem, baseada no conceito de números fuzzy, para detecção de bordas em imagens digitais chamado FUNED (Fuzzy Number Edge Detector). A técnica de detecção de bordas implementada pelo FUNED considera uma vizinhança local dos pixels da imagem, definida pelo usuário e, baseado no conceito de números fuzzy, é verificado se um pixel pertence ou não aquela região da imagem, com base na intensidade dos tons de cinza que compõem a região. O pixel que não pertence à região é então classificado como um possível pixel de borda. Através de uma função de pertinência, a técnica proposta fornece uma matriz de pertinência em tons de cinza e, pela escolha de um limiar, as bordas da imagem são segmentadas. Para a modelagem do problema, os tons de cinza são considerados como números fuzzy e, para cada pixel gi,j da imagem, calcula-se a sua pertinência em relação a uma determinada região, considerando os vizinhos que possuem níveis de cinza próximos de gi,j. Ao considerar os valores de cinza como números fuzzy, incorpora-se a variabilidade inerente dos valores de cinza de imagens, proporcionando assim uma abordagem mais adequada ao tratamento de imagens digitais, em comparação ao tratamento clássico, baseado em uma formulação analítica. Para avaliação do desempenho da técnica, foram usadas imagens sintéticas e imagens reais em tons de cinza, obtidas na literatura, e realizados testes qualitativos e quantitativos. Para a realização dos testes quantitativos, foi desenvolvida uma nova metodologia de avaliação de detectores de bordas baseada na análise ROC. O processo de avaliação desenvolvido considera diferentes medidas, que são tomadas comparando-se as bordas obtidas com as bordas ideais. Os resultados da avaliação de desempenho mostraram que o FUNED é eficaz computacionalmente quando comparado aos detectores de Canny e de Sobel e, também a outras abordagens fuzzy. A técnica permite ao usuário o ajuste dos seguintes parâmetros: o tamanho da vizinhança local, o suporte de um número fuzzy e o limiar. O ajuste desses parâmetros proporciona diversas possibilidades de visualização das bordas de uma imagem, permitindo a escolha de detalhes da imagem. A implementação computacional do FUNED é intuitiva e com bom desempenho tanto para obtenção de bordas como em tempo de processamento, sendo adequada para aplicações em tempo real com implementação em hardware.
The purpose of this work is to introduce a new approach, based on fuzzy numbers, for edge detection in gray level images. The proposed approach is called FUNED (Fuzzy Number Edge Detector). The edge detection technique, implemented by FUNED, considers a local neighborhood of image pixels, defined by the user and, based on fuzzy numbers concept, it is verified whether a pixel belongs to that image region, according to the gray level intensity in the region. The pixel that does not belong to the region is then classified as a possible edge pixel. Therefore, through a membership function, the proposed technique provides a membership matrix in gray levels and, through the choice of a threshold, the image edges are segmented. For the modeling of the problem, the gray levels are considered fuzzy numbers and, for each pixel gi,j of the image, it is computed its membership regarding to a specific region, considering the neighbors presenting gray levels near gi,j. When considering gray-values as fuzzy numbers, the inherent variability of the image gray values are incorporated, thus promoting a more powerful approach for the treatment of digital images as compares with the classic treatment based on analytical formulation. For the assessment of the performance of the technique, it was used gray-level synthetics and real images, obtained from the literature, and qualitative and quantitative tests were carried out. To achieve the quantitative tests, it was developed a new methodology for evaluating edge detectors based on ROC analysis. The evaluation process developed considers various measures, that are taken by comparing the edges obtained with the ideal edges. The results of the assessment showed that the FUNED is more computationally efficient when compared to the results obtained by Canny and Sobel detectors and, also to other fuzzy approaches. The technique allows the user to adjust several parameters. The adjustment of these parameters provide several image edge visualization possibilities, which allow the choice of details in the image. The computational implementation of FUNED is intuitive and with good performance both for obtaining edges as in processing time, being suitable for real time applications with hardware implementation.

Les uninormes són uns operadors d'agregació que, per la seva definició, es poden considerar com a conjuncions o disjuncions, i que han estat aplicades a camps molt diversos. En aquest treball s'estudien algunes equacions funcionals que tenen com a incògnites les uninormes, o operadors definits a partir d'elles. Una d'elles és la distributivitat, que és resolta per les classes d'uninormes conegudes, solucionant, en particular, un problema obert en la teoria de l'anàlisi no-estàndard. També s'estudien les implicacions residuals i fortes definides a partir d'uninormes, trobant solució a la distributivitat d'aquestes implicacions sobre uninormes. Com a aplicació d'aquests estudis, es revisa i s'amplia la morfologia matemàtica borrosa basada en uninormes, que proporciona un marc inicial favorable per a un nou enfocament en l'anàlisi d'imatges, que haurà de ser estudiat en més profunditat.
Las uninormas son unos operadores de agregación que, por su definición se pueden considerar como conjunciones o disjunciones y que han sido aplicados a campos muy diversos. En este trabajo se estudian algunas ecuaciones funcionales que tienen como incógnitas las uninormas, o operadores definidos a partir de ellas.
Una de ellas es la distributividad, que se resuelve para las classes de uninormas conocidas, solucionando, en particular, un problema abierto en la teoría del análisis no estándar. También se estudian las implicaciones residuales y fuertes definidas a partir de uninormas, encontrando solución a la distributividad de estas implicaciones sobre uninormas. Como aplicación de estos estudios, se revisa y amplía la morfología matemática borrosa basada en uninormas, que proporciona un marco inicial favorable para un nuevo enfoque en el análisis de imágenes, que tendrá que ser estudiado en más profundidad.
Uninorms are aggregation operators that, due to its definition, can be considered as conjunctions or disjunctions, and they have been applied to very different fields. In this work, some functional equations are studied, involving uninorms, or operators defined from them as unknowns. One of them is the distributivity equation, that is solved for all the known classes of uninorms, finding solution, in particular, to one open problem in the non-standard analysis theory. Residual implications, as well as strong ones defined from uninorms are studied, obtaining solution to the distributivity equation of this implications over uninorms. As an application of all these studies, the fuzzy mathematical morphology based on uninorms is revised and deeply studied, getting a new framework in image processing, that it will have to be studied in more detail.

Le terme "usinage à porte fermée", fréquemment employé par les PME de l'aéronautique et de l'automobile, désigne l'automatisation sécurisée du processus d'usinage des pièces mécaniques. Dans le cadre de notre travail, nous nous focalisons sur la vérification du montage d'usinage, avant de lancer la phase d'usinage proprement dite. Nous proposons une solution sans contact, basée sur la vision monoculaire (une caméra), permettant de reconnaitre automatiquement les éléments du montage (brut à usiner, pions de positionnement, tiges de fixation,etc.), de vérifier que leur implantation réelle (réalisée par l'opérateur) est conforme au modèle 3D numérique de montage souhaité (modèle CAO), afin de prévenir tout risque de collision avec l'outil d'usinage.

碩士
中原大學
電子工程學系
82
In this paper, we propose a new edge operator for edge detection of noisy blurred images.Our new operator "fuzzy-edge- operator" based on the theory of fuzzy sets performs edge detection of noisy blurred images faster and more perfectly than other existed operators in both speed and resolution. In the edge detection of a noisy blurred image, the conventional edge operators may require noise elimination and noise suppressing processes which may lose some original important information of edge. On the other hand, edge detection systems using our fuzzy-edge-operator can detect edge directly without preprocessing noise. Also, the results of edge detection using our fuzzy-edge-operator in both speed and cost are much better because the edge detection system using fuzzy-edge-operator is composed of coincidence, XOR and comparators only. Experimental results of noisy blurred images are given.From our experimental results, it shows that the performance of fuzzy-edge-operator for edge detection is much more satisfactory than that of other operators in considerations of noise tolerance, speed and cost.

In this thesis we investigate how artificial intelligent techniques, namely fuzzy logic and genetic/evolutionary algorithms can be used for digital image processing applications. We demonstrate our techniques with respect to two main research areas: removal of heavy impulse noise from corrupted gray scale images and edge detection in digital images. Very often fuzzy logic systems need to deal with large number of rules. This results in two major design issues: (i) How to formulate the fuzzy knowledge base using human expertise and experience? (ii) How to reduce the high computational power and the high processing times required? In this thesis we use evolutionary algorithms (including coevolutionary algorithms) to learn fuzzy knowledge bases to handle the design issue (i) described above, while using multi-layered and hierarchical fuzzy logic systems to reduce the number of rules and hence the computational overhead involved, thereby addressing issue (ii) stated above. In this research, when fuzzy rules are learnt using evolutionary algorithms, each individual in the evolutionary algorithm is appropriately encoded to uniquely represent the fuzzy knowledge base. The fitness of each individual in the evolutionary algorithm is calculated with respect to a predefined reference. In the case of an algorithm learning to enhance a digital image this reference is often associated with the uncorrupted perfect image. Designing multi-layered and hierarchical fuzzy structures involves breaking down the total number of rules, to be fed into multiple fuzzy layers in the system. This process needs careful consideration in forming the appropriate fuzzy layers as well as deciding the parameters to be input to different layers, so that the desired result is obtained with highest precision using the least computation time. Coevolutionary algorithms are powerful tools that can be used in situations where several factors contributing towards the system performance need to be learnt simultaneously. Here multiple populations consisting of candidate solutions are evolved in parallel and the fitness of individuals in each of the population are evaluated by forming a vector of candidate solutions selected from each population. The artificial intelligence techniques briefly described above will be used in this thesis with application to enhancement and edge detection in digital images.

碩士
大同大學
電機工程學系(所)
100
To overcome the drawbacks of the traditional Pal and King’s algorithm, a new algorithm of adaptive fuzzy image enhancement based on edge detection is proposed in this thesis. We apply the edge detection to find the edges of images and then set the mean of edges as the threshold to obtain the crossover point for edge preserving. Using the crossover point, we devise a new membership function and construct a new contrast intensification operator to achieve effective fuzzy image enhancement. The experimental results show that the proposed algorithm can enhance the contrast and preserve better details for different types of images.

碩士
大同大學
電機工程學系(所)
101
To improve the shortcomings of the traditional edge detection algorithm and increase the reliability of the edge information, this thesis proposes a new adaptive fuzzy edge detection algorithm based on the gradient features. First, we use Sobel operator to find the gradient of the image, and then calculate the maximum average gradient. Finally, we apply fuzzy system to detect the edges of images. The parameters of the proposed fuzzy edge detection algorithm are automatically optimized by maximizing of a performance index. The experimental results show that not only our proposed algorithm can detect edges but also its performance index is better than the other methods.

This paper proposes an approach to edge detection of blurred color images. The edge detector involves two phases –Deblurring of color image using wavelet and edge detection using bacteria foraging. Here deblurring is performed without estimating the imge blur. The deblurring algorithm performs deblurring in the spectrum domain. In edge detection process, we find out the edge pixels on the basis of intensity difference value of pixel in their 8-neighbourhood. First step is Chemotaxis step in which we calculate the eight directional nutrients in the form of intensity difference and find out the edge pixels in the neighborhood of bacteria. Next in the Elimination and Dispersal step if a bacterium found itself low on nutrients than it will be eliminated from its current location and dispersed to some other location. Now if we trace all the edge pixels, given by the movement of bacteria than we will get an image highlighted with all the associated edges. By using the proposed technique, a marked visible improvement in the important edges is observed on various test images over common edge detectors.

Edges characterize boundaries and edge detection is one of the most difficult tasks in image processing hence it is a problem of fundamental importance in image processing. Edges in images are areas with strong intensity contrasts and a jump in intensity from one pixel to the next can create major variation in the picture quality. Edge detection of an image significantly reduces the amount of data and filters out useless information, while preserving the important structural properties in an image.In the proposed method, the bacteria foraging is used along with contemporary fuzzy logic which implements a relative pixel similarity value algorithm.The similarity between two pixels is calculated using the weighted participation of each fuzzy rule. Low similarity between the pixels represents the probability of a pixel to be an edge pixel. The bacteria moves over the low similarity region, thus maximizing the edge content while minimizing the presence of non-edge content in the movement path. Directional Pixel Similarity is used to locate the similar pixel to the edge pixel and thus the movement of bacteria is decided.Bacteria with sufficient nutrients are reproduced, i.e., at the intersection of more than one edge a bacterium will split into the number of edges. If a bacterium found itself low on nutrients than it will be eliminated from its current location and dispersed to some other location. The path traced by the bacteria is the edge map. Thus with proposed method, edge pixels in a color image are detected simultaneously without any complex calculations such as gradient, Laplace and statistical calculations.

碩士
國立交通大學
電控工程研究所
98
In this thesis, we have proposed an improvement of color edge detector based on vector order statistics. The proposed detector consists of two stages. In the first stage, we use the concept of fuzzy gradient to estimate the direction of the gradient for every processing pixel in the image and adjust the corresponding processing window according to this detected direction for reliable edge detection setup. The second stage computes the vector mean distance (VMD) based on vector order statistics. Hence, the proposed detector, which integrates vector order statistics and fuzzy gradient, can provide more robust response for edge detection. Furthermore, we also combine the edge detector to our proposed thresholding method, which can automatically determine an optimal threshold and be adaptive to different image contents without manual intervention. Thus, the excellent results by our proposed edge detection scheme demonstrate that it is very user friendly and confident.

Detecting regions of change while reducing unimportant changes in multiple outdoor images of the same scene containing fence wires (i.e., a chain-link mesh fence) acquired by a mobile camera from slightly different viewing positions, angles and at different times is a very difficult problem. Regions of change include appearing of new objects and/or disappearing of old objects behind fence wires, breaches in the integrity of fence wires and attached objects in front of fence wires. Unimportant changes are mainly caused by camera movement, considerable background clutter, illumination variation, tiny sizes of fence wires and non-uniform illumination that occurs across fence wires. There are several issues that arise from these kinds of multiple outdoor images. The issues are: (1) parallax (the apparent displacement of an object as seen from two different positions that are not on a line with the object) among objects in the scene, (2) changing in size of same objects as a result of camera movement in forward or backward direction, (3) background clutter of outdoor scenes, (4) thinness of fence wires and (5) significant illumination variation that occurs in outdoor scenes and across fence wires. In this dissertation, an automated change detection method is proposed for these kinds of multiple outdoor images. The change detection method is composed of two distinct modules, which are a module for detecting object presence and/or absence behind fence wires and another module for detecting breaches in the integrity of fence wires and/or attached objects in front of fence wires. The first module consist of five main steps: (1) automated image registration, (2) confidence map image production by the Zitnick and Kanade algorithm, (3) occlusion map image generation, (4) significant or unimportant changes decision by the first hybrid decision-making system and (5) false positives reduction by the template subtraction approach. The second module integrates: (1) the Sobel edge detector combined with an adaptive thresholding technique in extracting edges of fence wires, (2) an area-based measuring in separating small and big objects based on their average areas determined once in the calibration process and (3) the second hybrid decision-making system in classifying objects as significant or unimportant changes. Experimental results demonstrate that the change detection method can identify and indicate approximate locations and possible percentages of significant changes whilst reducing unimportant changes in these kinds of multiple outdoor images. The study has utilized occluded regions in a confidence map image produced by the Zitnick and Kanade algorithm as potential significant changes in the image change detection research. Moreover, the study proves that the use of the Sobel edge detector combined with an adaptive thresholding technique is applicable in extracting edges of outdoor fence wires. In the future, the method could be integrated into patrol robots in order to provide assistance to human guards in protecting outdoor perimeter security.
http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1522689
Thesis (Ph.D.) -- University of Adelaide, School of Mechanical Engineering, 2010

Detecting regions of change while reducing unimportant changes in multiple outdoor images of the same scene containing fence wires (i.e., a chain-link mesh fence) acquired by a mobile camera from slightly different viewing positions, angles and at different times is a very difficult problem. Regions of change include appearing of new objects and/or disappearing of old objects behind fence wires, breaches in the integrity of fence wires and attached objects in front of fence wires. Unimportant changes are mainly caused by camera movement, considerable background clutter, illumination variation, tiny sizes of fence wires and non-uniform illumination that occurs across fence wires. There are several issues that arise from these kinds of multiple outdoor images. The issues are: (1) parallax (the apparent displacement of an object as seen from two different positions that are not on a line with the object) among objects in the scene, (2) changing in size of same objects as a result of camera movement in forward or backward direction, (3) background clutter of outdoor scenes, (4) thinness of fence wires and (5) significant illumination variation that occurs in outdoor scenes and across fence wires. In this dissertation, an automated change detection method is proposed for these kinds of multiple outdoor images. The change detection method is composed of two distinct modules, which are a module for detecting object presence and/or absence behind fence wires and another module for detecting breaches in the integrity of fence wires and/or attached objects in front of fence wires. The first module consist of five main steps: (1) automated image registration, (2) confidence map image production by the Zitnick and Kanade algorithm, (3) occlusion map image generation, (4) significant or unimportant changes decision by the first hybrid decision-making system and (5) false positives reduction by the template subtraction approach. The second module integrates: (1) the Sobel edge detector combined with an adaptive thresholding technique in extracting edges of fence wires, (2) an area-based measuring in separating small and big objects based on their average areas determined once in the calibration process and (3) the second hybrid decision-making system in classifying objects as significant or unimportant changes. Experimental results demonstrate that the change detection method can identify and indicate approximate locations and possible percentages of significant changes whilst reducing unimportant changes in these kinds of multiple outdoor images. The study has utilized occluded regions in a confidence map image produced by the Zitnick and Kanade algorithm as potential significant changes in the image change detection research. Moreover, the study proves that the use of the Sobel edge detector combined with an adaptive thresholding technique is applicable in extracting edges of outdoor fence wires. In the future, the method could be integrated into patrol robots in order to provide assistance to human guards in protecting outdoor perimeter security.
Thesis (Ph.D.) -- University of Adelaide, School of Mechanical Engineering, 2010