Tesis sobre el tema "Surface defet"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Surface defet".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Wong, Boon Kwei. "Automatic surface defect recognition and classification". Thesis, University of Sunderland, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283762.
Texto completoTailor, Mitul. "Automatic surface defect quantification in 3D". Thesis, Loughborough University, 2013. https://dspace.lboro.ac.uk/2134/14429.
Texto completoSong, Keng Yew. "Surface defect detection on textured background". Thesis, University of Surrey, 1993. http://epubs.surrey.ac.uk/844113/.
Texto completoRosli, M. H. "Surface defect characterisation using non-contact ultrasound". Thesis, University of Warwick, 2013. http://wrap.warwick.ac.uk/59439/.
Texto completoSmith, Melvyn Lionel. "The integration of innovative vision and graphic modelling techniques for surface inspection". Thesis, University of the West of England, Bristol, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.387938.
Texto completoWilson, Daniel John. "Defect and surface properties of the silver halides". Thesis, University College London (University of London), 2005. http://discovery.ucl.ac.uk/1446536/.
Texto completoOutioua, Djedjiga. "Defect-1 Choosability of Graphs on Surfaces". Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/40568.
Texto completoRashid, Waleed Bin. "Surface defect machining : a new approach for hard turning". Thesis, Heriot-Watt University, 2014. http://hdl.handle.net/10399/2840.
Texto completoWoodley, Scott Marcus. "A real-space approach to surface and defect states". Thesis, University of Bath, 1997. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.338412.
Texto completoFerris, Andrew J. PhD. "Chiral Induction and Defect Structures in Liquid Crystal Systems". Case Western Reserve University School of Graduate Studies / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=case159293629900968.
Texto completoNgendangenzwa, Blaise. "Defect detection and classification on painted specular surfaces". Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-146063.
Texto completoVolvokoncernens hyttfabrik i Umeå är en av Norrlands största verkstadsindustrier.Hyttfabriken tillverkar bara hytter för lastbilar och tillhör en av världens modernaste produktionsanläggningar. Trots ett hög automatiserat och datoriserat system bland många processer så är kvalitetsinspektionen av målade hytter fortfarande utförd manuellt. En smart och automatiserad kvalitetskontroll kan leda till lägre kostnader, högre kvalitet samt högre produktions effektivitet. Den här studien är ett steg framåt mot en automatiserad kvalitetskontroll. Två slagsproblem undersöktes närmare i den här studien nämligen defekt inspektion och defekt klassificering. Dessa problem åtgärdades genom att förse fyra statistiskametoder, support vector machine, random forests, k-nearest neighbors och neuralnetworks, med extraherade HOG egenskaper från tagna bilder. Resultaten visade att support vector machine och random forests presterade bättre än dess konkurrenter i förhållande till förmågan att både inspektera och klassificera defekter.
Hopkins, Brad Michael. "A Wavelet-Based Rail Surface Defect Prediction and Detection Algorithm". Diss., Virginia Tech, 2012. http://hdl.handle.net/10919/77351.
Texto completoPh. D.
Kunze, Christian [Verfasser]. "Influence of oxygen and water adsorption on the surface chemistry and contact forces of defect rich metaloxide and nitride surfaces / Christian Kunze". Paderborn : Universitätsbibliothek, 2014. http://d-nb.info/1058406426/34.
Texto completoBlake, Richard John. "Numerical models for Rayleigh wave scattering from surface features". Thesis, University College London (University of London), 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.282401.
Texto completoWilliamson, Andrew. "Carrier dynamics, persistent photoconductivity and defect chemistry at zinc oxide photoanodes". Thesis, University of Manchester, 2017. https://www.research.manchester.ac.uk/portal/en/theses/carrier-dynamics-persistent-photoconductivity-and-defect-chemistry-at-zinc-oxide-photoanodes(ec59e44c-0f17-40e5-ab34-871afbea0ea9).html.
Texto completoBoyne, Andrew. "Modeling Evolution of Defect Structures in Surface Roughening and Irradiation Hardening". The Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1300905995.
Texto completoCaulier, Yannick. "Surface defect classification based on one-dimensional sensors and structured illumination". Aachen : Shaker, 2008. http://d-nb.info/991379101/04.
Texto completoFretwell, H. M. "Positron annihilation studies of electronic and defect structures in metallic systems". Thesis, University of Bristol, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.357787.
Texto completoMoodie, Daniel Thien-An. "Sensor Fused Scene Reconstruction and Surface Inspection". Thesis, Virginia Tech, 2014. http://hdl.handle.net/10919/47453.
Texto completoMaster of Science
Caulier, Yannick [Verfasser]. "Surface Defect Classification Based on One-Dimensional Sensors and Structured Illumination / Yannick Caulier". Aachen : Shaker, 2008. http://d-nb.info/1161303618/34.
Texto completoFoster, Geoffrey M. "DEFECT AND METAL OXIDE CONTROL OF SCHOTTKY BARRIERS AND CHARGE TRANSPORT AT ZINC OXIDE INTERFACES". The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1524050368601169.
Texto completoRead, Mark S. D. "Atomistic simulation studies of the defect and surface properties of perovskite-based oxide-catalysts". Thesis, University of Surrey, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.298920.
Texto completoLI, JINHUA. "AN INTELLIGENT SYSTEM FOR THE DEFECT INSPECTION OF SPECULAR PAINTED CERAMIC TILES". UKnowledge, 2006. http://uknowledge.uky.edu/gradschool_theses/355.
Texto completoPratiwada, Chaitanya. "High Fidelity Detection of Defects in Polymer Films Using Surface-Modified Nanoparticles". University of Akron / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=akron1345586565.
Texto completoRenström, René. "Impact of Metallic Projectiles on a Ceramic Target Surface : Transition Between Interface Defeat and Penetration". Doctoral thesis, Uppsala universitet, Hållfasthetslära, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-7264.
Texto completoMahendra, Adhiguna. "Methodology of surface defect detection using machine vision with magnetic particle inspection on tubular material". Thesis, Dijon, 2012. http://www.theses.fr/2012DIJOS051.
Texto completoIndustrial surface inspection of tubular material based on Magnetic Particle Inspection (MPI) is a challenging task. Magnetic Particle Inspection is a well known method for Non Destructive Testing with the goal to detect the presence of crack in the tubular surface. Currently Magnetic Particle Inspection for tubular material in Vallourec production site is stillbased on the human inspector judgment. It is time consuming and tedious job. In addition, itis prone to error due to human eye fatigue. In this thesis we propose a machine vision approach in order to detect the defect in the tubular surface MPI images automatically without human supervision with the best detection rate. We focused on crack like defects since they represent the major ones. In order to fulfill the objective, a methodology of machine vision techniques is developed step by step from image acquisition to defect classification. The proposed framework was developed according to industrial constraint and standard hence accuracy, computational speed and simplicity were very important. Based on Magnetic Particle Inspection principles, an acquisition system is developed and optimized, in order to acquire tubular material images for storage or processing. The characteristics of the crack-like defects with respect to its geometric model and curvature characteristics are used as priory knowledge for mathematical morphology and linear filtering. After the segmentation and binarization of the image, vast amount of defect candidates exist. Aside from geometrical and intensity features, Multi resolution Analysis wasperformed on the images to extract textural features. Finally classification is performed with Random Forest classifier due to its robustness and speed and compared with other classifiers such as with Support Vector Machine Classifier. The parameters for mathematical morphology, linear filtering and classification are analyzed and optimized with Design Of Experiments based on Taguchi approach and Genetic Algorithm. The most significant parameters obtained may be analyzed and tuned further. Experiments are performed ontubular materials and evaluated by its accuracy and robustness by comparing ground truth and processed images. This methodology can be replicated for different surface inspection application especially related with surface crack detection
Wang, Cheng-Yu y 王正宇. "PET sheet surface defect inspection". Thesis, 2016. http://ndltd.ncl.edu.tw/handle/2m9bzf.
Texto completo中原大學
機械工程研究所
106
Products are tested and improved continuously in the manufacturing processes. After extrusion molding, the way to judge the quality of the products is to check if there are any defeats on the surface of the products. Image defect detection methods are applied to check the quality of the product so that misjudgments from visual inspection can be minimized. If image segmentation techniques can be applied to judge the defeats, then we can have parameters adjusted in the pre-process to prevent the misjudgments. This study applies image segmentation techniques to inspect the surface defeats of the products and uses image camera with low-angle LED light source to get the image. During the process of analyzing defeats, 6 processes are utilized to show the area of mura defeats: ①Increase deposition and evaporation of the image. ②Convert the image to grayscale and then add gaussian noise. ③Apply contrast-limited adaptive histogram equalization method to improve the distortion of the image and brightness. ④Apply inverse discrete cosine transform and transform the image from frequency domain into spatial domain. ⑤Subtract the image of inverse discrete cosine transform and contrast-limited adaptive histogram equalization from each another. ⑥Lastly, apply image binarization to get the final image. In this study, by using image segmentation technique, the product defeats in each manufacturing process can be observed. Also, we can utilize the techniques and 6 processes mentioned above and use the same parameter to process the image with three different films. After analyzing the results, the defeats can be shown and more details of the defeats can be presented. By doing so, the cost of purchasing new equipment and misjudgment from visual inspection can be reduced. Ultimately, the more details of product surface defeats can be detected.
Chen, Shin-Yi y 陳心怡. "Surface Defect Detection for Solar Cells". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/53048121893493966957.
Texto completo國立中央大學
資訊工程研究所
95
Due to the decrease of the energy sources, the development of new energy sources is urgently pursued. One of the potential energy is the solar power. The solar cells are the primary devices to capture the solar energy. To maintain the quality of solar cells, we develop several inspection methods to detect defects on the solar cells. Several different kinds of solar cells are inspected. For the solar cell with uniform surface, we detect the defects using a multi-cased thresholding method. The border and busbar areas of solar cells are separated and inspected with a tracking style. For the solar cells with random texture surface, we use line-based detecting method to find brighter defects if the random textures of background is not clear; otherwise, we use an anisotropic diffusion based detection to blur the complex background while brighter defects would be preserved. Then the defects are also extracted by the line-based method. For the solar cells with regular texture surface, we use texture based method to detect the defects. We trained ten different texture patterns on defect-free solar images in advance. Then, we compare each patch of testing images with the corresponding trained patterns. The un-matched result shows defects in the patch. In the experiments, three proposed methods are evaluated with single crystal and polysilicon solar cells of 2048×2048 and 640×640 resolutions. The results show that the proposed methods are near practice for industry applications.
Jen, Po-Hao y 任柏澔. "Unsupervised Autoencoder for surface defect detection". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/63uq35.
Texto completo元智大學
工業工程與管理學系
107
Machine vision technology has been widely used in manufacturing for defect detection. Traditional machine vision needs to manually design features or indicators that can distinctly describe the surface texture and defect characteristics. It then uses high-dimensional classifiers to discriminate the defect. The collection of defective samples in the production process is often difficult, which may cause the classifier to fail for the model training due to imbalanced data. This study combines deep learning (DL) technique and image processing operations for defect detection, and no hand-crafted features are required. It applies the Variational Autoencoder (VAE) model to perform pixel-level defect detection, where each individual pixel in the inspection image is identified as defective or defect-free point. In pixel-level defect detection, only the normal sample is trained by the VAE model. A trained VAE model can reconstruct a defective image into a defect-free image. By subtracting the reconstructed image and the original input image, a simple binary thresholding can then accurately segment the position and size of the defect in the difference image. The proposed VAE image reconstruction scheme gives good detection results when the light source of an inspection image changes by ±20% w.r.t the training samples and the area of a defect is less than 20% of the input image size. Experimental results have shown that the VAE model is not affected by image displacement. To copy with image rotation, training samples with a variety of rotational angles can be applied for the VAE model training. For training samples with 0°, +5° and -5° degrees, the defect in a test image with arbitrary rotations between +5° and -5° degrees can be reliably detected.
SUN, HSUAN-MIN y 孫萱旻. "Surface Defect Detection For Anodized Aluminum Tube". Thesis, 2016. http://ndltd.ncl.edu.tw/handle/67715433887296619054.
Texto completo國立雲林科技大學
電機工程系
104
In this study of the tubes to be detected for the two types, one is the bicycle shock absorbers used by the shock tube, the other is the printer of the O.P.C. drum. Aluminum tubes have pre-anodized and anodized and as well as glossy and foggy surface. With the growing popularity of cycle racing, the quantity demand of relevant components is also increasing year by year, which accordingly leads to the increase of productivity. Since Taiwan bicycle industry is mainly for export, product quality is the main concern in the manufacturing process. At present the laser printer is the highest-level printer. It can print high-quality images. To print such images, an O.P.C. drum which is clean and has no defect is needed. Therefore, the quality of the O.P.C. drum plays an important role. Currently, the industry is still using human eyes to detect printing, which makes it not easy to meet the needs of industry and is labor-consuming. Moreover, errors occur easily. Therefore, this study is to develop a system which can automatically detect aluminum surface defects by using automated optical inspection (AOI) technology. This system includes a line-scan camera, high brightness linear light source, and a rotating mechanism. In the detection process, the rotating mechanism rotates the aluminum tube, and the vision module captures images. Then, the captured images go through pre-processing, in which complex background and defects are distinguished and removed. After that, the images are analyzed in different ways. This study uses the following four methods to analyze the images: the RFT method, the FFT method, the image subtraction method, and the FFT and image subtraction integration. The result of the study indicates that the four methods have respective process outcomes. Among them, the one with the best defect-detection rate and time-saving process is chosen to be developed. At present, the rate of the image subtraction defect detection is 100%. The processing time, in Halcon, is about 550ms~600ms per tube, while in C#/emgu, it’s about 900ms~1000ms per tube. However, in this study, the company provided only 13 tubes. Preferably, more extensive tests are needed in this system. Hopefully, human-eye detection can be improved or even replaced in the future with the development of an efficient and high-quality defect detection system.
Guo, Hong-Yi y 郭鴻益. "Surface Defect Detection of Tapered Cylindrical Metal". Thesis, 2015. http://ndltd.ncl.edu.tw/handle/9sd56y.
Texto completo國立雲林科技大學
電機工程系
103
With the growing popularity of golf sport all over the world, the production of relevant products is increasing year by year. In golf utilities, club is the remunerative goods requiring high quality, and Taiwan is No.2 in the worldwide field of golf club production. Within mass production, errors occur easily and drain on manpower hugely in traditional manual examination. Nowadays using automatic detect systems for heads, logo of clubs or balls is common but no similar system for club to reduce manpower consumption. To be more competitive in golf industry, it's urgent in developing related utilities. On the trend of golf automatic production, this study uses the AOI (Automated Optical Inspection) technology to detect defects on the steel club and classify them at the same time. To get good image of club’s surface in favor of image processing together with computer vision for detection, this study proposes using diffused dark-field side light illumination with mask to light, and area camera matrix on the dynamic rotating club to ignore picturing difficulty. Experiment results show this system can detect twenty types of flaw and achieve 87% of detection rate with lower cost. The system is close to visual inspection though we know there's still a room to grow. It takes 750ms/club for the system to detect so far which exceeds in the demand for 1ms/club practically. Progress widely even takes manpower place, have a competitive performance.
Chen, Ming-Chun y 陳明君. "Fast regularity measures for surface defect detection". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/61438953754931482012.
Texto completo元智大學
工業工程與管理學系
97
This research proposes machine vision schemes for detecting subtle defects in non-textured and homogeneously textured surfaces. The defects to be inspected are ill-defined and hardly visible in the surfaces, which make the automatic surface inspection task extremely difficult. In this study, regularity features of a small window sliding through the whole image are extracted based on the consistence of spatial distribution of gray levels in each window. Two methods are proposed. The first method is based on principal component analysis (PCA) that calculates the eigenvalues of the covariance matrix formed by the covariance of x- and y-coordinates with the gray level as the weight. The smaller eigenvalue λ2 is used as the regularity feature, where a defective region will generate a feature value smaller than that of a homogeneous defect-free region. The second method divides the sliding window into a set of small non-overlapped blocks. The sum of the gray levels in each block should be similar to each other if the window of the sensed image contains no defects. The Chi-square (χ2) that measures the difference between the gray-level sum of a block and the mean gray-level sum, and the entropy that measures the complexity of the gray-level sums in all the blocks are then used as the regularity measures. By using the integral image technique, the sum operations for all three proposed regularity measures can be efficiently calculated for on-line, real-time implementation. The experiments on a variety of textured and non-textured surfaces including plastic case images of laptop computers, leather, TFT-LCD backlight panels and backsides of solar wafers have shown the effectiveness of the proposed methods. The computation times for an image of size 400×400 are only 0.032 seconds for λ2 and 0.28 seconds for χ2 and the entropy measures on a typical personal computer.
Chung, Chung-Yu y 鐘崇毓. "Automated Surface Defect Inspection of LED Chips". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/08767772302586691277.
Texto completo朝陽科技大學
工業工程與管理系碩士班
95
A light-emitting diode (LED) is a semiconductor device that emits visible light when an electric current passes through it. Surface flaws are common defects arising in most LED chips. These defects not only influence appearances of LEDs but also have negative effects on functions and security of the products. This research explores the automated detection of water-drop defect in LED chip. We first use the one-level Haar wavelet transform to conduct image pre-processing for extraction of image features. Then, we apply principle component analysis (PCA) and factor analysis (FA) techniques of multivariate statistical analysis that have the ability of integrating multiple quality characteristics to combine multiple image features. After the image features are fused, the wavelet characteristic based multivariate statistic approaches are developed to judge the existence of the water-drop defects in an image. Experimental results demonstrate the proposed methods have 93% probability of accurately detecting the water-drop defects in LED chip. From the analysis of ROC curves, the PCA and FA methods performs better than the Otsu, T2 statistics and BPN methods in defect detection with respect to both false alarm and detection rate. This research contributes a solution to a common problem of the surface defect detection of LED chips, and offers a computer-aided visual defect inspection system to meet the inspection and quality control request.
Tsai, Huan-Hua y 蔡環樺. "Automated Surface Defect Inspection of Touch Panels". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/83987398922478315189.
Texto completo朝陽科技大學
工業工程與管理系碩士班
100
Capacitive touch panels (CTP) with advantages of water-proof, stain-proof, scratch-proof, fast response, are widely used in various electronic products built in touch technology functions. The surfaces of CTPs are multi-layer structured and are classified as structural textures. It is a difficult inspection task when defects embedded in surfaces of CTPs with structural textures. This research proposes the discrete Fourier transform (DFT) based multi-crisscross band-Gaussian filtering (MC-BGF) method and the discrete cosine transform (DCT) based three ways double band-Gaussian filtering (3W-DBGF) method to inspect surface defects of CTPs. The two filtering approaches design filters to filter out the frequencies of the regions of multiple high-energy bands with considering the width and angle of the high-energy band, band filtering, threshold filtering, and characteristics of filtering with Gaussian distribution. The filtered image is then transformed back to the spatial domain. In the restored image, the homogeneous line regions in the original image will have an approximately uniform gray level, whereas the defective region will be clearly retained. Finally, the restored image is segmented by a simple threshold method and defects are located. Real testing samples (including 36 normal images and 112 defective images) randomly selected from a manufacturing process are evaluated. Experimental results show that the DFT with MC-BGF method achieves a high 93.42% flaw detection rate , a low 1.96% false alarm rate , a high 98.02% correct classification rate (CR), and the performance indices of the DCT with 3W-DBGF method are 92.72% , 2.98% , and 97.00% (CR) on directional textured surfaces of CTPs. These results indicate that the two proposed methods have good detection effects. In additions, the two filtering methods were insensitive to small shift of band filtering angle and change of image brightness. In the source selection of thresholding parameters applied to restored images for defect separation, the use of parameters from training samples is better. Therefore, the proposed methods are also to maintain good defect detection results in moderate or little changes in environmental factors and have good robustness.
TSAI, CHIH-KANG y 蔡至剛. "Defect Detection For Surface Of Metal Bars". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/666r99.
Texto completo國立雲林科技大學
電機工程系
106
This article uses Automated Optical Inspection, AOI technology to detect flaws on metal surfaces. This article uses linear slides as the test object to reduce manpower, increase productivity, and increase product quality. At present, linear slides have a tendency to strengthen in Taiwan's machinery exports. With the popularization of Industry 4.0 automation, the demand for automated mechanical components has also increased. If the slide rails of the linear slide rails are uneven, vibration will occur, which will cause the coordinates or positioning of the automation mechanism to be inaccurate and have a great influence. Because the resulting protruding part will be smoothed at the end, but the flattening can not solve the problem of the sag of the depression, this paper will use the LED triangulation method in 3D mechanical vision to find the area of the linear sliding surface with a depression of 0.1mm. Areas with inconsistent specifications are marked to assist the manufacturer to establish a defect detection station on the production line, which will successfully detect the concave portion of the surface of the linear slide.
Chen, Nai-Ze y 陳乃澤. "Defect Detection for Oxidized Surface of Aluminum Foil". Thesis, 2016. http://ndltd.ncl.edu.tw/handle/63081184839657295913.
Texto completo國立雲林科技大學
電機工程系
104
With automated optical inspection (AOI) of development, has gradually replaced the traditional manual inspection, whether in electronic, semiconductor, printing, medical and other industries, more and more by the need to improve the value of machine vision in industrial production. In this paper, simulation and development of detection systems, applied to the surface flaw detection of metal thin sheet of aluminum foil on to find out all the flaws position faster than with the naked eye, the subsequent processing to help save manpower and increase production speed. In this study, using a servo motor to drive the two rollers, so that the aluminum foil in order to do more than 6 centimeters per second uniform motion, while the camera scans the surface of nearly 50 cm wide sheet of aluminum foil like to take and then do image processing on the original image and image stitching, and then calculate the image position and size of defects. During the test, because the area scan camera easily lead to uneven lighting, coupled with reflective aluminum foil itself will indirectly affect the results after image processing, image processing to do so before the first of the original image do ROI, then each 5 mosaic images do restore, you can avoid the problem of uneven lighting image. In accordance with the experimental results show that the moving speed of the laid sheets of aluminum foil, the defect can be detected.
Ye, Yao-Jhong y 葉耀中. "Defect Classification for Spherical Object with Uneven Surface". Thesis, 2016. http://ndltd.ncl.edu.tw/handle/10760493844769976100.
Texto completo國立雲林科技大學
電機工程系
104
With the growing popularity of golf sport all over the world, the production of relevant products is increasing year by year. In Taiwan, golf ball manufacturing factories use manual work to detect products at present. Then the golf ball AOI machine has been completed, and it is being used. Therefore this article purposes to improve previously encounter problems and to defect classification in a large number of tests, this not only achieve reduce human resource but also quality conformity and speed up production. The results of this study showed that this thesis can assist the company in identifying what kinds of defects on the golf ball, and the company can take more notice of the manufacturing process. However, some defects can be reconditioned and continue to sell. Consequently, if this system can classify and reroute them, the company will further reduce human resources on screening and automatically elect the golf ball which can be refurbished. Avoid to waste ball and reduce the cost. In this research, capture ninety-six images of golf balls by Area camera, using Sobel edge detection to find the defects and select of different size defects. And then filter out defects to classify by using similarity calculation. Finally, the experiment for golf ball defect detection system, the detection rate can be up to 94%, and golf ball defect classification, the correct rate reaches 76.5%.
Szu, Chun-Wei y 蘇俊瑋. "Defect Detection for Spherical Object with Uneven Surface". Thesis, 2015. http://ndltd.ncl.edu.tw/handle/qr7xpf.
Texto completo國立雲林科技大學
電機工程系
103
Automation inspection in the past mostly is confined to a flat or even spherical surface. This study designs two golf ball defect detection systems to detect marking deviation and surface defects on uneven and nonplanar surface. Marking deviation detection system calculates the relative position and angle of the golf ball equator and the marking on equator, then figures out whether the difference of the two exceeds standard. Defect detection system captures ninety-six images of golf balls and sifts qualified ones out of different size of defects based on Sobel edge detection. The result shows that for marking deviation inspection system, the error reaches one degree or deviation error reaches 300μm are regarded as defective and for defect inspection system, the detection rate reaches 96.69% in detecting eleven types (thirty-eight samples) of defects.
Kuan, Sheng-yen y 官聲嚴. "Optical Defect Inspection for Surface of Curved Objects". Thesis, 2014. http://ndltd.ncl.edu.tw/handle/02013008991866372522.
Texto completo國立臺灣科技大學
材料科學與工程系
102
Automated optical inspection (AOI) systems have been widely used in the liquid crystal display panel manufacturing process. But, the inspection of defects in a non-planar object still relies on traditional manual inspection methods. In this essay, we construct an AOI system to detect the defects in the surface of non-planar objects. The proposed AOI system in this essay can effectively detect defects and overcome the situation that the images photoed with uneven illumination. From the experimental results the detection rate is over 80%.
WU, YI-CI y 吳易錡. "A Study on Solar Wafer Surface Defect Inspection". Thesis, 2011. http://ndltd.ncl.edu.tw/handle/66516647331224322876.
Texto completo聖約翰科技大學
自動化及機電整合研究所
99
This article aims to explore the solar surface defects. The main contents include optical inspection equipment and visual inspection module. In the optical detection device, appropriate mechanical components are selected to assemble according to the conditions of the mechanical design. The Semi-closed loop system of the PC-based control is utilized. Regarding light source a ring lighting often employed for visual inspection is discussed. The visual inspection module uses image processing technology to simplify images in order to measure images and determine the various types of solar cell defects, such as dirt, edge chipping, the electrode line defects and cracks. The system precision can be up to 0.001mm and defect inspection accuracy rate reaches 91%, while it takes 4 seconds to inspect one defect . Besides the theoretical study, the system feasibility is inspected by practical experiences.
You, Jhih-Siang y 游志祥. "Development of Defect Inspection System for Glass Surface". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/43980857013524818951.
Texto completo國立東華大學
電機工程學系
97
The purpose of this thesis is to develop a defect inspection system for anti-reflection (AR) glass. Using a high resolution line scan charge-coupled device (CCD) with camera link card and a linear motor drive system loaded with glass, the image of AR glass is grabbed under high speed scan. A linear stage with 600mm stroke, 3m/s maximum speed and 1μm encoder resolution is used in this automatic optical inspection (AOI) bench. A 314mm × 476mm AR glass with 1.6mm thickness is inspected in this study. The study is focused on the classification of the defects of the AR glass which are consisted of scratch, fingerprint, particle, print scratch,and pinhole with two lighting sources. In the image processing, first,image enhancement and denoising are carried out. Then, the scanned image is segmented using binary method with adaptive threshold values.Moreover, rapid density-based clustering applications with noise (RDBSCAN) is adopted for defect clustering. Furthermore, four features are defined and calculated as the training patterns for the classification of defects using back-propagation neural network (BPNN). The defined features are the average grey level in the defect image, the contrast, the correlation, and the compactness. Finally, the experimental results show that the investigated method can detect and classify various defects effectively for AR glass.
Ku, Husan-Long y 古軒龍. "Defect detection of surface treatment for Aluminum pipes". Thesis, 2015. http://ndltd.ncl.edu.tw/handle/16672882692497699924.
Texto completo國立雲林科技大學
電機工程系
103
With the rapid technology development, in industry, it has become prevalent to use automated optical inspection to replace the time and labor consuming manual inspection. Generally, most pipe manufactures adopt visual (manual) inspection and its maximum recognition rate can only reach 70%. Besides, it results in the loss of companies’ cost and labor power in the long term; moreover, a deeper understanding of its full pipe processing process reveals that if the defect of visual inspection cannot be improved, the production efficiency and quality of the product will be disable to make further progress. In this thesis, to capture images, the experimental platform is desktop with image capture module, rotating mechanism, line-scan camera and coaxial light. This thesis aims to detect the defect of aluminum pipes by capturing the surface images via line-scan camera. The reason to use line-scan camera rather than area scan camera lies in its high shooting speed and feature of flattening the cylinder surface which is beneficial for image analysis. In the inspection process, the rotating mechanism rotates the aluminum pipes for the image capture module to catch images. After that, the image processing is implemented to remove complex background and display only defect images then to proceed image analysis via different ways. In this thesis, three different ways are applied and introduced: i. Defect detection by grayscale standard deviation ii. Defect detection by gray-level co-occurrence matrix then classify via support vector machines iii. Defect detection by edge detection via fuzzy theory The result shows that the three ways have each correspondent defect type. The share key point is whether the image capture processing can be unaffected to complex background and capture way and the handling methods is rather important as well. If the result can be unaffected, the defect recognition and finding rate can reach over than 95%.
Luo, Kou-Shiuan y 羅國軒. "Surface Defect Detection Based On Image Processing Techniques". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/84261636620560349297.
Texto completo國立交通大學
資訊科學學系
82
A surface defect inspection system is built up to inspect chip surface defect of silicon wafers. In this report, the techniques of the image analysis include segmentation, binary thresholding, template matching, and projection. The major defects in three regions of chip surface are: scratch in edge region, spots in active region, and dark coating in pad region. They are effectively detected by the designed defect detection modules in the proposed system. Experimental results show that the recognition rate of the proposed detection method for scratch defect in edge region is 87%, for spot defect in active region is 94%, and for coating defect in pad region is 99.66%.
Chan, Seong-heng y 曾祥慶. "Contact Angle Hysteresis by Superhydrophobic Surface Compression and Defect Pinning on Superhydrophobic Surface". Thesis, 2011. http://ndltd.ncl.edu.tw/handle/42941892557425511530.
Texto completo國立中央大學
化學工程與材料工程研究所
99
Abstract In this thesis, a homemade superhydrophobic surface,fabricated by spraying the coating of surface-modified nanosilica on glass slice, is employed as an experimental material to discuss the phenomenon of contact angle hysteresis. The experiment is divided into two parts. In the first part, a new measurement of contact angle hysteresis, compression of plate, is presented. Through observation of the droplet compressed and stretched by downward and upward movement of superhydrophobic surface, the relation between the height, base diameter and contact angle of droplet can be recorded and hence the behavior of contact angle hysteresis can be verified. In the second part, different sizes of defects are made on the superhydrophobic surface which is originally free of contact angle hysteresis. The cause of contact angle hysteresis can be simulated by observation of the relation between sizes of defects, sizes of droplets, the forward and backward contact angle of droplet and the sliding angle of droplet.
Yu, Bin Chi y 余彬齊. "Optical Coherence Tomography for Surface Defect Detection on Wafer". Thesis, 2016. http://ndltd.ncl.edu.tw/handle/6b5e2r.
Texto completoWu, Mu-Hsing y 吳木杏. "Surface Defect Inspection and Analysis of Color Filter Panel". Thesis, 2000. http://ndltd.ncl.edu.tw/handle/81361934914474922723.
Texto completo國立臺灣大學
資訊工程學研究所
88
LCDs will be the next combat ground after Taiwan’s computer monitors made of cathode ray tube become the world market leader. In the LCD flat panel production, the easiest way to realize colorization is to make use of the back illuminant and the color filter panel. In order to guarantee the output quality of the LCD flat panel, people have to inspect any killing defect from the surface of the color filter panel. Traditional, human operators simply inspect the color filter panel visually against prescribed standards. The decisions made by these inspectors often involve subjective judgment, in addition to being labor intensive and therefore costly, whereas automatic inspection systems remove the subjective aspects and provide fast, quantitative dimensional assessments. These automatic systems do not get tired, do not suffer burnouts, and are consistent day in and day out. All of this means better quality at a lower cost. In this thesis, we develop an automatic color filter surface defect inspection system that is based on the image subtraction method for the purpose of high-speed inspection. Our inspection algorithm solves the problems of golden image generation, orientation compensation, image registration, image segmentation, defect analysis, and noise elimination. The experimental result shows that our algorithm achieves high accuracy and high speed for industrial requirement.
Weng, Ruo-mian y 翁若綿. "A Study on Surface Defect Inspection for Salar cells". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/55327352131660327585.
Texto completo義守大學
工業工程與管理學系碩士班
97
In this paper, we propose a surface defect inspection method by using the machine vision and image processing techniques for poly-silicon solar cells. The objective is to perform quality assurance with high inspection rate and reduce manufacturing cost. The defects to be detected include edge cracks, finger interruptions, and stains. The solar cell images are grabbed by a scanner, then we use Fourier transformation (FT) and morphology to orientate solar cells image. The edge crack defect can be segmented by projection. For the printed lines, we use gray-scale morphology to remove vertical busbars, and find finger interruptions by image subtraction and thresholding. The stain defects are detected by gray-scale morphology and image subtraction. We also compare the effect of using FT on stain defect detection rate. Experimental results indicate the proposed orientation and defect detection methods perform well. The detection rate of stain defect is higher when we utilize Fourier transformation.
Chiang, I.-Yung y 江宜勇. "Optical-flow-based template matching for surface defect detection". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/32667123151452728602.
Texto completo元智大學
工業工程與管理學系
98
Template matching has been widely used in image processing for visual inspection. The current existing methods such as normalized cross correlation and golden template matching are very sensitive to displacement even the inspection object is well aligned with its fiducials. Some object surfaces found in industry may show repeated patterns or contain no textures and, therefore, there are no fiducials can be uniquely chosen for alignment. This research proposes an optical-flow-based template matching method for surface defect detection. Given a reference image, the optical flow field between the reference and the inspection image are evaluated. The optical flow of each pixel is calculated within a small neighborhood window. When the pixel value of the inspection image is similar to that of the reference image, the flow length will be short. It indicates the pixel under evaluation is defect-free. Conversely, the pixel value of a defect in the inspection image is distinct from that of the reference image and, thus, the corresponding flow length is significantly large. The flow length derived from the optical flow field is insensitive to minor shifts of an inspection image. It is then robust to displacement due to the misalignment of the algorithm or random production variations. The optical flow process is computationally expensive. The integral image technique is applied to replace the sum operations in a rectangular neighborhood window, and its computation time is invariant to the window size. In this study, the optical flow algorithms for defect detection in both gray-level and color images are individually proposed. The experiment on LED wafer inspection that involves needle mark shift defect-free samples and large area defective sample has shown that the proposed method can achieve 100% recognition rate. The computation time of an LED chip of image size 115×105 pixels takes only 0.0121 seconds with the help of integral images. Additional experiments on structurally-textured surfaces such as textile fabrics and non-textures surfaces such as LCD glass substrates have also shown that the proposed method outperforms the conventional template matching methods.
Hsieh, Kuan-shen y 謝冠申. "Automated Surface Distortion Defect Inspection of Curved Car Mirrors". Thesis, 2013. http://ndltd.ncl.edu.tw/handle/79319018431466742518.
Texto completo朝陽科技大學
工業工程與管理系碩士班
101
Comparing with plane car mirrors, curved car mirrors have characteristics of higher reflectance and wider field of view. Currently, the curved mirrors have been widely used in vehicle rearview mirrors and security mirrors on the driving roads and make drivers have better fields of views and driving information. In the production process of curved car mirrors, mirrors with surface distortion defects results from the unstable temperature changes of ovens and inappropriate control of over-flow fusion process. It is not easy to measure the magnitudes of distortion defects on curved car mirrors. Furthermore, the curved mirrors with the property of higher reflection increase the difficulty of discrimination of surface distortion defects on car mirrors. This study proposes a novel approach based on small-shift control scheme to inspect surface distortion defects on curved car mirrors. In order to quantize the deformation (degree of distortion) of a car mirror, a standard inspection pattern (checkerboard grids) is designed to reflect the pattern on a testing car mirror for image acquisition. The reflected pattern image of a defective mirror with distortion is compared with that of a normal mirror for quantifying the deformation and locating the distortion defects. We first detect the intersection points of the standard inspection pattern, then measure the distances of the intersection points from the origin, and calculate the distance deviations of the corresponding intersection points between the defective and normal images. Finally, we apply the small-shift control schemes, the cumulative sum (CUSUM) method and the exponentially weighted moving average (EWMA) method, to judge the existence of the distortion defects based on the accumulative deviation distances. Experimental results show that the proposed methods achieves a high 98% probability of correctly discriminating distortion defects on curved car mirrors.
Liu, Te-Cheng y 劉得政. "Automatic Inspection of IC Surface Defect in Packaging Process". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/uhaaft.
Texto completo元智大學
資訊工程學系
106
AOI (Automated Optical Inspection, AOI), widely used in the surface of the product Wafer, IC, PCB, PCB ... solar and other production processes in the defect detection, the use of machine vision technology as testing standards, improvement of traditional human use optical instruments the shortcomings detected, to enhance the yield of the manufacturing process and reduce production costs. The present paper on IC package manufacturing process, AOI machine detects the IC surface foreign matter or pattern abnormalities and other defects in the defect image IC pin and Defect bad no fixed position and defects and no fixed shape, making the current need through artificial visual way to view the image defect would not affect the IC pin of a short circuit or open circuit, spend more time costs, its artificial visual also need to go through professional training and familiarity have a positive correlation. Presented by the system automatically detects a defect would not affect the IC pin short circuit or open circuit method, the converted defective image input CIELab color space and obtain the luminance L channel, whereby defects and IC pins come out, followed by two the value of the image defects and IC pin carved out to make the Opening and Closing via morphological image edges smooth fine lines and eliminate the noise, capturing the detection region (ROI), IC pin and flaws, and then determine whether the defects caused by IC pin short circuit or open circuit. The misjudgment rate of Type I Error caused by AOI automatic optical inspection machine is improved, and the misjudgment rate of Type II Error caused by secondary manual visual inspection is not increased due to the reduction of Type I Error, resulting in loss of process yield. The identification rate of experimental results reached 99%.