Breast cancer is one of the leading causes of death for women. Small clusters of micro calcifications appearing as collection of white spots on mammograms show an early warning of breast cancer. In present paper a novel approach of segmentation implemented on X-ray mammograms for more accurate detection of microcalcification clusters has been introduced. The method is based on discrete wavelet transform due to its multiresolution properties. Morphological tophat algorithm is applied for contrast enhancement of the calcification clusters. Finally fuzzy c-means clustering (FCM) algorithm has been implemented for intensity-based segmentation. The proposed technique is compared with conventional global thresholding method and experimental results show the good properties of the proposed technique.
{"title":"Fuzzy Logic Based Segmentation of Microcalcification in Breast Using Digital Mammograms Considering Multiresolution","authors":"M. Bhattacharya, A. Das","doi":"10.1109/IMVIP.2007.20","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.20","url":null,"abstract":"Breast cancer is one of the leading causes of death for women. Small clusters of micro calcifications appearing as collection of white spots on mammograms show an early warning of breast cancer. In present paper a novel approach of segmentation implemented on X-ray mammograms for more accurate detection of microcalcification clusters has been introduced. The method is based on discrete wavelet transform due to its multiresolution properties. Morphological tophat algorithm is applied for contrast enhancement of the calcification clusters. Finally fuzzy c-means clustering (FCM) algorithm has been implemented for intensity-based segmentation. The proposed technique is compared with conventional global thresholding method and experimental results show the good properties of the proposed technique.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"11 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113976217","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}
This paper describes initial work on a framework for automatic detection of illegal dumping from CCTV footage from recycle centres. Frames are seperated into foreground and background regions using a Bayesian approach that combines global motion estimates with image based information to generate a robust segmentation. The framework hence avoids explicit modelling and tracking of objects in the scene such as cars, people or rubbish bags. A feature extraction stage with diagnostics will be presented.
{"title":"Detection of Illegal Dumping from CCTV at Recycling Centres","authors":"N. Harte, A. Rankin, G. Baugh, A. Kokaram","doi":"10.1109/IMVIP.2007.17","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.17","url":null,"abstract":"This paper describes initial work on a framework for automatic detection of illegal dumping from CCTV footage from recycle centres. Frames are seperated into foreground and background regions using a Bayesian approach that combines global motion estimates with image based information to generate a robust segmentation. The framework hence avoids explicit modelling and tracking of objects in the scene such as cars, people or rubbish bags. A feature extraction stage with diagnostics will be presented.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117339172","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}
This paper presents a visual odometer system using a monocular camera for vehicle navigation. A novel algorithm for vehicle ego-motion estimation based on optical flow and image segmentation is proposed. By applying a pulse-coupled neural network (PCNN), the image is dynamically divided into road area and non-road area by analysing texture smoothness. Correct road region detection effectively reduces computation cost and improves accuracy of ego-motion estimation. Then a novel optical flow optimization method is proposed to produce reliable optical flow field in the road area detected previously. It's known when the vehicle is moving on a planar structured road, its 2D motion field is expected to have specific form. Therefore ego-motion of vehicle, instantaneous speed and angular velocity, can be recovered from optical flow field of road area. Experiments show that the visual odometer successfully provides driver with robust and accurate vehicle self motion information.
{"title":"Vehicle Ego-Motion Estimation by using Pulse-Coupled Neural Network","authors":"Yanpeng Cao, Paul Cook, A. Renfrew","doi":"10.1109/IMVIP.2007.42","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.42","url":null,"abstract":"This paper presents a visual odometer system using a monocular camera for vehicle navigation. A novel algorithm for vehicle ego-motion estimation based on optical flow and image segmentation is proposed. By applying a pulse-coupled neural network (PCNN), the image is dynamically divided into road area and non-road area by analysing texture smoothness. Correct road region detection effectively reduces computation cost and improves accuracy of ego-motion estimation. Then a novel optical flow optimization method is proposed to produce reliable optical flow field in the road area detected previously. It's known when the vehicle is moving on a planar structured road, its 2D motion field is expected to have specific form. Therefore ego-motion of vehicle, instantaneous speed and angular velocity, can be recovered from optical flow field of road area. Experiments show that the visual odometer successfully provides driver with robust and accurate vehicle self motion information.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126379200","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}
Segmentation is a significant preliminary step for many image-based object recognition activities. Microscopy images often present segmentation problems, namely low contrast (the objects are translucent) and occlusions. Fortunately, translucency provides some possibility of solving the occlusion problem; edge-based methods can be used to tackle the low contrast (translucency) problem, but the edges are noisy and edge tracking must be used. In occluded regions edges can be very faint and noise and conflicting edges can confuse even edge tracking: an edge contour containing gaps may result. This poster presents work on a gap filling algorithm that uses model-based prediction to augment noisy edge data.
{"title":"Model-based Edge Tracking for Segmentation of Low Contrast Images","authors":"C. Hudy, J. Campbell, J. Slater","doi":"10.1109/IMVIP.2007.28","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.28","url":null,"abstract":"Segmentation is a significant preliminary step for many image-based object recognition activities. Microscopy images often present segmentation problems, namely low contrast (the objects are translucent) and occlusions. Fortunately, translucency provides some possibility of solving the occlusion problem; edge-based methods can be used to tackle the low contrast (translucency) problem, but the edges are noisy and edge tracking must be used. In occluded regions edges can be very faint and noise and conflicting edges can confuse even edge tracking: an edge contour containing gaps may result. This poster presents work on a gap filling algorithm that uses model-based prediction to augment noisy edge data.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123477832","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}
Yinhai Wang, R. Turner, D. Crookes, J. Diamond, Peter Hamilton
This paper investigates image segmentation methods for the automated identification of Squamous epithelium from cervical virtual slides. Such images can be up to 120Ktimes80K pixels in size. Through investigation a multiresolution segmentation strategy was developed to give the best segmentation results in addition to saving processing time and memory. Squamous epithelium is initially segmented at a low resolution of 2X magnification. The boundaries of segmented Squamous epithelium are further fine tuned at the highest resolution of 40X magnification. Robust texture feature vectors were developed in conjunction with a support vector machine (SVM) to do classification. Finally medical histology rules are applied to remove misclassifications. Results show that with selected texture features, SVM achieved more than 92.1% accuracy in testing. In tests with 20 virtual slides, results are promising.
{"title":"Investigation of Methodologies for the Segmentation of Squamous Epithelium from Cervical Histological Virtual Slides","authors":"Yinhai Wang, R. Turner, D. Crookes, J. Diamond, Peter Hamilton","doi":"10.1109/IMVIP.2007.26","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.26","url":null,"abstract":"This paper investigates image segmentation methods for the automated identification of Squamous epithelium from cervical virtual slides. Such images can be up to 120Ktimes80K pixels in size. Through investigation a multiresolution segmentation strategy was developed to give the best segmentation results in addition to saving processing time and memory. Squamous epithelium is initially segmented at a low resolution of 2X magnification. The boundaries of segmented Squamous epithelium are further fine tuned at the highest resolution of 40X magnification. Robust texture feature vectors were developed in conjunction with a support vector machine (SVM) to do classification. Finally medical histology rules are applied to remove misclassifications. Results show that with selected texture features, SVM achieved more than 92.1% accuracy in testing. In tests with 20 virtual slides, results are promising.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116290655","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, we describe a simple method for automatic detection of melanin spots in Atlantic salmon fillets. Melanin spots are visible dark spots that reduce the quality grade of the fillets. Atlantic salmon processing lines have several operations that involve manual quality evaluation of fillets. One such operation is the inspection of fillets to detect melanin spots. This inspection is labor intensive, and therefore desirable to automate. Two simple computer vision algorithms for melanin spot detection are presented. One algorithm operates on the red channel of RGB images and the second algorithm uses linear discriminant analysis (IDA) on all three RGB channels. A comparison between these two algorithms shows that, for most detection rates, using LDA gives a lower number of false-detections per fillet. We show that the melanin spot detection task can potentially be automated using computer vision.
{"title":"A Simple Computer Vision Method for Automatic Detection of Melanin Spots in Atlantic Salmon Fillets","authors":"J. R. Mathiassen, E. Misimi, A. Skavhaug","doi":"10.1109/IMVIP.2007.6","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.6","url":null,"abstract":"In this paper, we describe a simple method for automatic detection of melanin spots in Atlantic salmon fillets. Melanin spots are visible dark spots that reduce the quality grade of the fillets. Atlantic salmon processing lines have several operations that involve manual quality evaluation of fillets. One such operation is the inspection of fillets to detect melanin spots. This inspection is labor intensive, and therefore desirable to automate. Two simple computer vision algorithms for melanin spot detection are presented. One algorithm operates on the red channel of RGB images and the second algorithm uses linear discriminant analysis (IDA) on all three RGB channels. A comparison between these two algorithms shows that, for most detection rates, using LDA gives a lower number of false-detections per fillet. We show that the melanin spot detection task can potentially be automated using computer vision.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132933992","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}
This paper describes a new segmentation approach used for detecting the location and the orientation of the cervical spinal column in medical X-ray images. A first preprocessing step consists on determining a global polygonal region for each vertebra. After this, we propose two different methods to calculate vertebrae orientation. The first method is based on the four faces detection of each vertebra contour when the second is essentially based on automatic corners localization. A specific goal of the proposed application is to create an efficient semi-automated method of identifying the overall spine curvature and the orientation angles of each vertebra. The final goal is to determine vertebrae motion induced by their movement between two or several positions.
{"title":"Mobility Estimation and Analysis in Medical X-ray Images Using Corners and Faces Contours Detection","authors":"M. Benjelloun, S. Mahmoudi","doi":"10.1109/IMVIP.2007.27","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.27","url":null,"abstract":"This paper describes a new segmentation approach used for detecting the location and the orientation of the cervical spinal column in medical X-ray images. A first preprocessing step consists on determining a global polygonal region for each vertebra. After this, we propose two different methods to calculate vertebrae orientation. The first method is based on the four faces detection of each vertebra contour when the second is essentially based on automatic corners localization. A specific goal of the proposed application is to create an efficient semi-automated method of identifying the overall spine curvature and the orientation angles of each vertebra. The final goal is to determine vertebrae motion induced by their movement between two or several positions.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124802701","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 order to localise tagged proteins in living cells, the surrounding cells must be recognised first. Based on previous work regarding cell recognition in bright-field images, we propose an approach to the automated recognition of unstained live Drosophila cells, which are of high biological relevance. In order to achieve this goal, the original methods were extended to enable the additional application of an alternative microscopy technique, since the exclusive usage of bright-field images does not allow for an accurate segmentation of the considered cells. In order to cope with the increased number of parameters to be set, a genetic algorithm is applied. Furthermore, the employed segmentation and classification techniques needed to be adapted to the new cell characteristics. Therefore, a modified active contour approach and an enhanced feature set, allowing for a more detailed description of the obtained segments, are introduced.
{"title":"Recognition of Unstained Live Drosophila Cells in Microscope Images","authors":"M. Tscherepanow, N. Jensen, F. Kummert","doi":"10.1109/IMVIP.2007.33","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.33","url":null,"abstract":"In order to localise tagged proteins in living cells, the surrounding cells must be recognised first. Based on previous work regarding cell recognition in bright-field images, we propose an approach to the automated recognition of unstained live Drosophila cells, which are of high biological relevance. In order to achieve this goal, the original methods were extended to enable the additional application of an alternative microscopy technique, since the exclusive usage of bright-field images does not allow for an accurate segmentation of the considered cells. In order to cope with the increased number of parameters to be set, a genetic algorithm is applied. Furthermore, the employed segmentation and classification techniques needed to be adapted to the new cell characteristics. Therefore, a modified active contour approach and an enhanced feature set, allowing for a more detailed description of the obtained segments, are introduced.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115266833","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}
Huaizhong Zhang, P. Morrow, S. McClean, K. Saetzler
This paper presents improvements to the geodesic active contour (GAC) model obtained by incorporating user defined prior information into the model itself. Specifically, the stopping function in the GAC model is revised by designing an indicator function derived from a-priori information. The numerical implementation is based on the level set technique. Experimental results illustrate that our approach is efficient and feasible for both artificial and real images. In particular, the proposed method performs well in situations where existing methods are known to fail.
{"title":"Incorporating Feature Based Priors into the Geodesic Active Contour Model and its Application in Biomedical Imagery","authors":"Huaizhong Zhang, P. Morrow, S. McClean, K. Saetzler","doi":"10.1109/IMVIP.2007.21","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.21","url":null,"abstract":"This paper presents improvements to the geodesic active contour (GAC) model obtained by incorporating user defined prior information into the model itself. Specifically, the stopping function in the GAC model is revised by designing an indicator function derived from a-priori information. The numerical implementation is based on the level set technique. Experimental results illustrate that our approach is efficient and feasible for both artificial and real images. In particular, the proposed method performs well in situations where existing methods are known to fail.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121198106","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}
Image processing tasks have traditionally involved the use of square operators on regular rectangular image lattices. For many years the concept of using hexagonal pixels for image capture has been investigated, and several advantages of such an approach have been highlighted. Therefore, we present a design procedure for hexagonal gradient operators, developed within the finite element framework, for use on hexagonal pixel based images. In order to evaluate the approach we generate pseudo hexagonal images via resizing and resampling which also allows us to present results visually without the use of hexagonal lattice capture or display hardware. We provide comparative results with existing gradient operators, both rectangular and hexagonal.
{"title":"A Design Procedure for Gradient Operators on Hexagonal Images","authors":"B. Gardiner, S. Coleman, B. Scotney","doi":"10.1109/IMVIP.2007.1","DOIUrl":"https://doi.org/10.1109/IMVIP.2007.1","url":null,"abstract":"Image processing tasks have traditionally involved the use of square operators on regular rectangular image lattices. For many years the concept of using hexagonal pixels for image capture has been investigated, and several advantages of such an approach have been highlighted. Therefore, we present a design procedure for hexagonal gradient operators, developed within the finite element framework, for use on hexagonal pixel based images. In order to evaluate the approach we generate pseudo hexagonal images via resizing and resampling which also allows us to present results visually without the use of hexagonal lattice capture or display hardware. We provide comparative results with existing gradient operators, both rectangular and hexagonal.","PeriodicalId":249544,"journal":{"name":"International Machine Vision and Image Processing Conference (IMVIP 2007)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128519162","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：