Pub Date : 2010-10-01DOI: 10.1109/IRANIANMVIP.2010.5941163
O. Khayat, E. Noori, M. Ghergherehchi, H. Afarideh, Noushin Khatib
Transmission electron microscopy (TEM) is one of the most useful methods to clarify the structure in micro and Nano materials. We developed a quantitative analysis method for structure identification of Nano materials containing Nano-space by using electron microscopy combined with a contrast enhancement technique. In this paper an entropic-like index of fuzziness is presented to be an indication of information transfer from a TEM image to its enhanced one. The image is firstly transmitted to fuzzy domain. The membership values are then modified according to a 5-parametric transfer function aiming to maximize the maximum variance index of fuzziness. In the proposed index of fuzziness, the Sugeno class of complement is employed to make the index more adaptable and flexible to various types of applications a TEM image may involve. A common involvement of microscopic image processing techniques is the non-uniform backlight illumination of the images. To this aim, the image is split into sub-images of with quite uniform illumination and then the segments are analyzed separately. An implementation and simulation is performed finally to demonstrate the effectiveness, adaptability and generally applicability of the proposed method in case of microscopic Nano-scale image enhancement.
{"title":"Using maximum variance index of fuzziness for contrast enhancement of Nano and micro-images of TEM","authors":"O. Khayat, E. Noori, M. Ghergherehchi, H. Afarideh, Noushin Khatib","doi":"10.1109/IRANIANMVIP.2010.5941163","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2010.5941163","url":null,"abstract":"Transmission electron microscopy (TEM) is one of the most useful methods to clarify the structure in micro and Nano materials. We developed a quantitative analysis method for structure identification of Nano materials containing Nano-space by using electron microscopy combined with a contrast enhancement technique. In this paper an entropic-like index of fuzziness is presented to be an indication of information transfer from a TEM image to its enhanced one. The image is firstly transmitted to fuzzy domain. The membership values are then modified according to a 5-parametric transfer function aiming to maximize the maximum variance index of fuzziness. In the proposed index of fuzziness, the Sugeno class of complement is employed to make the index more adaptable and flexible to various types of applications a TEM image may involve. A common involvement of microscopic image processing techniques is the non-uniform backlight illumination of the images. To this aim, the image is split into sub-images of with quite uniform illumination and then the segments are analyzed separately. An implementation and simulation is performed finally to demonstrate the effectiveness, adaptability and generally applicability of the proposed method in case of microscopic Nano-scale image enhancement.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116399010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/IRANIANMVIP.2010.5941169
S. Jalali, H. B. Ghavifekr, A. Ebrahimi
Extracted data from a tensile test applied on a compact tension specimen are not sufficient to have an accurate statement about fracture mechanical properties of materials. Verification of these data using finite element analysis cannot be directly validated on the crack tip due to its singularity and material nonhomogeneity. This paper presents implementation of digital image correlation (DIC) algorithms to fill this deficiency. A brittle material is chosen as the case study. Required measurement setup is explained. Experimental results are reported and verified by finite element analysis. The used DIC algorithm is explained and its reliability is discussed.
{"title":"Investigation of fracture mechanical properties of materials using digital image correlation","authors":"S. Jalali, H. B. Ghavifekr, A. Ebrahimi","doi":"10.1109/IRANIANMVIP.2010.5941169","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2010.5941169","url":null,"abstract":"Extracted data from a tensile test applied on a compact tension specimen are not sufficient to have an accurate statement about fracture mechanical properties of materials. Verification of these data using finite element analysis cannot be directly validated on the crack tip due to its singularity and material nonhomogeneity. This paper presents implementation of digital image correlation (DIC) algorithms to fill this deficiency. A brittle material is chosen as the case study. Required measurement setup is explained. Experimental results are reported and verified by finite element analysis. The used DIC algorithm is explained and its reliability is discussed.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131999031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/IRANIANMVIP.2010.5941172
M. Alipoor, H. Ahopay, J. Haddadnia
Iris detection is a computationally intensive task in the overall iris biometric processing. In this paper we proposed a technique to localize the iris and the pupil in eye images efficiently and accurately. This paper includes three stages: The first stage is related to finding the centre and radius of pupil. In this stage, the problem of pupil non-uniformity which may appear in some images is solved and the pupil is detected. In the second stage a new approach, based on circular arc search, is proposed to extract iris boundary. The last stage includes wavelet-based feature extraction and classifier design. Our approach has been applied on the CASIA standard database. High accuracy of the proposed iris localization method resulted in a high performance iris recognition system.
{"title":"A novel high performance iris and pupil localization method","authors":"M. Alipoor, H. Ahopay, J. Haddadnia","doi":"10.1109/IRANIANMVIP.2010.5941172","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2010.5941172","url":null,"abstract":"Iris detection is a computationally intensive task in the overall iris biometric processing. In this paper we proposed a technique to localize the iris and the pupil in eye images efficiently and accurately. This paper includes three stages: The first stage is related to finding the centre and radius of pupil. In this stage, the problem of pupil non-uniformity which may appear in some images is solved and the pupil is detected. In the second stage a new approach, based on circular arc search, is proposed to extract iris boundary. The last stage includes wavelet-based feature extraction and classifier design. Our approach has been applied on the CASIA standard database. High accuracy of the proposed iris localization method resulted in a high performance iris recognition system.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132576959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/IRANIANMVIP.2010.5941130
Seyed Mehdi Moghadas, Navid Rabbani
Presence of foreign substances in medical liquids can make serious problems for both patients and companies. To avoid these problems, there is a vast need of an automatic process to identify the bottles with foreign substances. In this paper, a new method is proposed to detect and classify the foreign substances in medicine bottles and vials based on machine vision. Several cameras are located in production line, to get images from medicine bottles. The captured images are thresholded to gather a collection of connected components. For each one a set of novel features are computed, the feature vectors are fed into a classifier, to distinguish the foreign substances from bubbles and also classify them in four groups, so the operator can find the source of the problem and fixes the failure in machine which causes it. An original method is also described to find out the scratches and spots on the bottle surface and distinguish them from foreign substances. The proposed method achieves detection rates over 97% and classification rates over 93%.
{"title":"Detection and classification of foreign substances in medical vials using MLP neural network and SVM","authors":"Seyed Mehdi Moghadas, Navid Rabbani","doi":"10.1109/IRANIANMVIP.2010.5941130","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2010.5941130","url":null,"abstract":"Presence of foreign substances in medical liquids can make serious problems for both patients and companies. To avoid these problems, there is a vast need of an automatic process to identify the bottles with foreign substances. In this paper, a new method is proposed to detect and classify the foreign substances in medicine bottles and vials based on machine vision. Several cameras are located in production line, to get images from medicine bottles. The captured images are thresholded to gather a collection of connected components. For each one a set of novel features are computed, the feature vectors are fed into a classifier, to distinguish the foreign substances from bubbles and also classify them in four groups, so the operator can find the source of the problem and fixes the failure in machine which causes it. An original method is also described to find out the scratches and spots on the bottle surface and distinguish them from foreign substances. The proposed method achieves detection rates over 97% and classification rates over 93%.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128466387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-10-01DOI: 10.1109/IRANIANMVIP.2010.5941178
Zohre Foroushi, M. Ardestani, A. Shirazi
Multiple description coding is a technique where all the transmitted segments of data, or descriptions, can be independently decoded. In this paper, a multiple description coding technique for videos is proposed, based on optimal Lagrangian rate allocation. in "T+2D" wavelet video coding, first, motion compensated temporal filtering (MCTF) is performed along the temporal direction to efficiently de-correlate frames within a GOP. Then, all low-pass filtered frames are encoded using JPEG2000 coder. All code blocks are coded at two different rates. Then blocks are split into three subsets with similar rate distortion characteristics; three balanced descriptions are generated by combining code blocks belonging to the three subsets encoded at opposite rates. A theoretical analysis is carried out, and the optimal rate distortion conditions are worked out. Simulation results show a noticeable performance improvement with respect to Akyol algorithm.
{"title":"Multiple description video coding based on Lagrangian rate allocation and JPEG2000","authors":"Zohre Foroushi, M. Ardestani, A. Shirazi","doi":"10.1109/IRANIANMVIP.2010.5941178","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2010.5941178","url":null,"abstract":"Multiple description coding is a technique where all the transmitted segments of data, or descriptions, can be independently decoded. In this paper, a multiple description coding technique for videos is proposed, based on optimal Lagrangian rate allocation. in \"T+2D\" wavelet video coding, first, motion compensated temporal filtering (MCTF) is performed along the temporal direction to efficiently de-correlate frames within a GOP. Then, all low-pass filtered frames are encoded using JPEG2000 coder. All code blocks are coded at two different rates. Then blocks are split into three subsets with similar rate distortion characteristics; three balanced descriptions are generated by combining code blocks belonging to the three subsets encoded at opposite rates. A theoretical analysis is carried out, and the optimal rate distortion conditions are worked out. Simulation results show a noticeable performance improvement with respect to Akyol algorithm.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115155396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a new method for signature identification and verification based on contourlet transform (CT) is proposed. This method uses contourlet coefficient as the feature extractor and Support Vector Machine (SVM) as the classifier. In proposed method, first signature image is normalized based on size. After preprocessing, contourlet coefficients are computed on specified scale and direction. Next, all extracted coefficients are fed to a layer of SVM classifiers as feature vector. The number of SVM classifiers is equal to the number of classes. Each SVM classifier determines if the input image belongs to the corresponding class or not. The main characteristic of proposed method is independency to nation of signers. Two experiments on two signature sets are performed. The first is on a Persian signature set and the other is on Stellenbosch (Turkish) signature set. Based on these experiments, we achieve a 100% recognition (identification) rate and more than 96.5% on Persian and Turkish signature sets respectively and 4.5% error in verification.
{"title":"Offline handwritten signature identification and verification using contourlet transform and Support Vector Machine","authors":"Muhammad Reza Pourshahabi, M. Sigari, H. Pourreza","doi":"10.1109/SoCPaR.2009.132","DOIUrl":"https://doi.org/10.1109/SoCPaR.2009.132","url":null,"abstract":"In this paper, a new method for signature identification and verification based on contourlet transform (CT) is proposed. This method uses contourlet coefficient as the feature extractor and Support Vector Machine (SVM) as the classifier. In proposed method, first signature image is normalized based on size. After preprocessing, contourlet coefficients are computed on specified scale and direction. Next, all extracted coefficients are fed to a layer of SVM classifiers as feature vector. The number of SVM classifiers is equal to the number of classes. Each SVM classifier determines if the input image belongs to the corresponding class or not. The main characteristic of proposed method is independency to nation of signers. Two experiments on two signature sets are performed. The first is on a Persian signature set and the other is on Stellenbosch (Turkish) signature set. Based on these experiments, we achieve a 100% recognition (identification) rate and more than 96.5% on Persian and Turkish signature sets respectively and 4.5% error in verification.","PeriodicalId":350778,"journal":{"name":"2010 6th Iranian Conference on Machine Vision and Image Processing","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115844151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：