D. McClymont, A. Mehnert, A. Trakic, S. Crozier, D. Kennedy
This paper presents an investigation of the apparent diffusion coefficient (ADC) for improving the discrimination of benign and malignant lesions in breast magnetic resonance imaging (MRI). In particular a method is presented for automatically selecting hyper intense tumour voxels in dynamic contrast enhanced (DCE) MRI data and evaluating their average ADC in the corresponding diffusion-weighted (DW) MRI data. The method was applied to ten breast MRI datasets obtained from routine clinical practice. The results demonstrate that the combination of the relative signal increase (DCE-MRI) with the apparent diffusion coefficient (DW-MRI) leads to better discrimination than with either feature alone. The results also suggest that it is important to acquire the DWMRI data in a consistent fashion, i.e. either before or after the acquisition of the DCE-MRI data.
{"title":"Improving the Discrimination of Benign and Malignant Breast MRI Lesions Using the Apparent Diffusion Coefficient","authors":"D. McClymont, A. Mehnert, A. Trakic, S. Crozier, D. Kennedy","doi":"10.1109/DICTA.2010.101","DOIUrl":"https://doi.org/10.1109/DICTA.2010.101","url":null,"abstract":"This paper presents an investigation of the apparent diffusion coefficient (ADC) for improving the discrimination of benign and malignant lesions in breast magnetic resonance imaging (MRI). In particular a method is presented for automatically selecting hyper intense tumour voxels in dynamic contrast enhanced (DCE) MRI data and evaluating their average ADC in the corresponding diffusion-weighted (DW) MRI data. The method was applied to ten breast MRI datasets obtained from routine clinical practice. The results demonstrate that the combination of the relative signal increase (DCE-MRI) with the apparent diffusion coefficient (DW-MRI) leads to better discrimination than with either feature alone. The results also suggest that it is important to acquire the DWMRI data in a consistent fashion, i.e. either before or after the acquisition of the DCE-MRI data.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129497158","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}
Salma Kammoun Jarraya, Mohamed Hammami, H. Ben-Abdallah
Fast and accurate foreground detection in video sequences is the first step in many computer vision applications. In this paper, we propose a new method for background modeling that operates in color and gray spaces and that manages the entropy information to obtain the pixel state card. Our method is recursive and does not require a training period to handle various problems when classify pixels into either foreground or background. First, it starts by analyzing the pixel state card to build a dynamic matrix. This latter is used to selectively update background model. Secondly, our method eliminates noise and holes from the moving areas, removes uninteresting moving regions and refines the shape of foregrounds. A comparative study through quantitative and qualitative evaluations shows that our method can detect foreground efficiently and accurately in videos even in the presence of various problems including sudden and gradual illumination changes, shaking camera, background component changes, ghost, and foreground speed.
{"title":"Accurate Background Modeling for Moving Object Detection in a Dynamic Scene","authors":"Salma Kammoun Jarraya, Mohamed Hammami, H. Ben-Abdallah","doi":"10.1109/DICTA.2010.18","DOIUrl":"https://doi.org/10.1109/DICTA.2010.18","url":null,"abstract":"Fast and accurate foreground detection in video sequences is the first step in many computer vision applications. In this paper, we propose a new method for background modeling that operates in color and gray spaces and that manages the entropy information to obtain the pixel state card. Our method is recursive and does not require a training period to handle various problems when classify pixels into either foreground or background. First, it starts by analyzing the pixel state card to build a dynamic matrix. This latter is used to selectively update background model. Secondly, our method eliminates noise and holes from the moving areas, removes uninteresting moving regions and refines the shape of foregrounds. A comparative study through quantitative and qualitative evaluations shows that our method can detect foreground efficiently and accurately in videos even in the presence of various problems including sudden and gradual illumination changes, shaking camera, background component changes, ghost, and foreground speed.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131280023","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}
Recognizing human actions in realistic scenes has emerged as a challenging topic due to various aspects such as dynamic backgrounds. In this paper, we present a novel approach to taking audio context into account for better action recognition performance, since audio can provide strong evidence to certain actions such as phone-ringing to answer-phone. At first, classifiers are established for visual and audio modalities, respectively. Specifically, bag of visual-words model is employed to represent human actions in visual modality, a number of audio features are extracted for audio modality, and Support Vector Machine (SVM) is employed as the classification technique. Then, a decision fusion scheme is utilized to fuse classification results from two modalities. Since audio context is not always helpful, two simple yet effective decision rules are developed for selective fusion. Experimental results on the Hollywood Human Actions (HOHA) dataset demonstrate that the proposed approach can achieve better recognition performance than that of integrating scene context. Therefor, our work provides strong confidence to further explore how audio context influences realistic human action recognition.
{"title":"Realistic Human Action Recognition with Audio Context","authors":"Qiuxia Wu, Zhiyong Wang, F. Deng, D. Feng","doi":"10.1109/DICTA.2010.57","DOIUrl":"https://doi.org/10.1109/DICTA.2010.57","url":null,"abstract":"Recognizing human actions in realistic scenes has emerged as a challenging topic due to various aspects such as dynamic backgrounds. In this paper, we present a novel approach to taking audio context into account for better action recognition performance, since audio can provide strong evidence to certain actions such as phone-ringing to answer-phone. At first, classifiers are established for visual and audio modalities, respectively. Specifically, bag of visual-words model is employed to represent human actions in visual modality, a number of audio features are extracted for audio modality, and Support Vector Machine (SVM) is employed as the classification technique. Then, a decision fusion scheme is utilized to fuse classification results from two modalities. Since audio context is not always helpful, two simple yet effective decision rules are developed for selective fusion. Experimental results on the Hollywood Human Actions (HOHA) dataset demonstrate that the proposed approach can achieve better recognition performance than that of integrating scene context. Therefor, our work provides strong confidence to further explore how audio context influences realistic human action recognition.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116912626","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}
A. Bhuiyan, R. Kawasaki, E. Lamoureux, T. Wong, K. Ramamohanarao
Clinical research suggests that changes in the retinal blood vessels (e.g., vessel caliber) are important indicators for earlier diagnosis of diabetes and cardiovascular diseases. Reliable vessel detection or segmentation is a prerequisite for quantifiable retinal blood vessel analysis for predicting these diseases. However, the segmentation of blood vessels is complicated by its huge variations such as abrupt changes in local contrast, a wide range of vessel width and central reflex in the vessel. In this paper, we propose a novel technique to detect retinal blood vessels which is able to address these issues. The core of the technique is a new vessel edge tracking method which combines the method of finding pattern of vessel start point and pixel grouping and profiling techniques. An edge profile checking method is developed for filtering noise and other objects, and tracking the real vessel edges. From the filtered edges a rule based technique is adopted for grouping the edges of individual vessels. Experimental results show that 92.4% success rate in the identification of vessel start-points and 82.01% success rate in tracking the major vessels.
{"title":"Vessel Segmentation from Color Retinal Images with Varying Contrast and Central Reflex Properties","authors":"A. Bhuiyan, R. Kawasaki, E. Lamoureux, T. Wong, K. Ramamohanarao","doi":"10.1109/DICTA.2010.42","DOIUrl":"https://doi.org/10.1109/DICTA.2010.42","url":null,"abstract":"Clinical research suggests that changes in the retinal blood vessels (e.g., vessel caliber) are important indicators for earlier diagnosis of diabetes and cardiovascular diseases. Reliable vessel detection or segmentation is a prerequisite for quantifiable retinal blood vessel analysis for predicting these diseases. However, the segmentation of blood vessels is complicated by its huge variations such as abrupt changes in local contrast, a wide range of vessel width and central reflex in the vessel. In this paper, we propose a novel technique to detect retinal blood vessels which is able to address these issues. The core of the technique is a new vessel edge tracking method which combines the method of finding pattern of vessel start point and pixel grouping and profiling techniques. An edge profile checking method is developed for filtering noise and other objects, and tracking the real vessel edges. From the filtered edges a rule based technique is adopted for grouping the edges of individual vessels. Experimental results show that 92.4% success rate in the identification of vessel start-points and 82.01% success rate in tracking the major vessels.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114424016","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}
Malaria is one of the most serious parasitic infections of human. The accurate and timely diagnosis of malaria infection is essential to control and cure the disease. Some image processing algorithms to automate the diagnosis of malaria on thin blood smears are developed, but the percentage of parasitaemia is often not as precise as manual count. One reason resulting in this error is ignoring the cells at the borders of images. In order to solve this problem, a kind of diagnosis scheme within large field of view (FOV) is proposed. It includes three steps. The first step is image mosaicing to obtain large FOV based on space-time manifolds. The second step is the segmentation of erythrocytes where an improved Hough Transform is used. The third step is the detection of nucleated components. At last, it is concluded that the counting accuracy of malaria infection within large FOV is finer than several regular FOVs.
{"title":"Malaria Cell Counting Diagnosis within Large Field of View","authors":"Li-hui Zou, Jie Chen, Juan Zhang, Narciso García","doi":"10.1109/DICTA.2010.40","DOIUrl":"https://doi.org/10.1109/DICTA.2010.40","url":null,"abstract":"Malaria is one of the most serious parasitic infections of human. The accurate and timely diagnosis of malaria infection is essential to control and cure the disease. Some image processing algorithms to automate the diagnosis of malaria on thin blood smears are developed, but the percentage of parasitaemia is often not as precise as manual count. One reason resulting in this error is ignoring the cells at the borders of images. In order to solve this problem, a kind of diagnosis scheme within large field of view (FOV) is proposed. It includes three steps. The first step is image mosaicing to obtain large FOV based on space-time manifolds. The second step is the segmentation of erythrocytes where an improved Hough Transform is used. The third step is the detection of nucleated components. At last, it is concluded that the counting accuracy of malaria infection within large FOV is finer than several regular FOVs.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123324170","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 new model for capturing spatial information for object categorization with bag-of-words (BOW). BOW models have recently become popular for the task of object recognition, owing to their good performance and simplicity. Much work has been proposed over the years to improve the BOW model, where the Spatial Pyramid Matching (SPM) technique is the most notable. We propose a new method to exploit spatial relationships between image features, based on binned log-polar grids. Our model works by partitioning the image into grids of different scales and orientations and computing histogram of local features within each grid. Experimental results show that our approach improves the results on three diverse datasets over the SPM technique.
{"title":"Enhanced Spatial Pyramid Matching Using Log-Polar-Based Image Subdivision and Representation","authors":"E. Zhang, M. Mayo","doi":"10.1109/DICTA.2010.46","DOIUrl":"https://doi.org/10.1109/DICTA.2010.46","url":null,"abstract":"This paper presents a new model for capturing spatial information for object categorization with bag-of-words (BOW). BOW models have recently become popular for the task of object recognition, owing to their good performance and simplicity. Much work has been proposed over the years to improve the BOW model, where the Spatial Pyramid Matching (SPM) technique is the most notable. We propose a new method to exploit spatial relationships between image features, based on binned log-polar grids. Our model works by partitioning the image into grids of different scales and orientations and computing histogram of local features within each grid. Experimental results show that our approach improves the results on three diverse datasets over the SPM technique.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129894875","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}
Yiran Xie, Rui Cao, Hanyang Tong, Sheng Liu, Nianjun Liu
The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.
{"title":"Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs","authors":"Yiran Xie, Rui Cao, Hanyang Tong, Sheng Liu, Nianjun Liu","doi":"10.1109/DICTA.2010.50","DOIUrl":"https://doi.org/10.1109/DICTA.2010.50","url":null,"abstract":"The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"4032 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127544022","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}
A new feature selection approach is proposed for facial expression recognition system. The features are extracted using Gabor filters from Grey-scale images for characterizing facial texture. Then, an adaptive filter selection (AFS) algorithm is applied to choose the best subset of Gabor filters with different scales and orientations. In AFS algorithm, the filters are selected based on spectral difference between the original image and the noisy image in Gabor wavelet domain. After that, the optimum subset of filters is selected based on minimum error rate. This subset of Gabor filters is used for feature extraction. The extracted features are classified by adopting a multiple linear discriminant analysis (LDA) classifier. Experiments on different databases are carried out that the method is efficient for facial expression recognition.
{"title":"A Novel Gabor Filter Selection Based on Spectral Difference and Minimum Error Rate for Facial Expression Recognition","authors":"S. Lajevardi, Z. M. Hussain","doi":"10.1109/DICTA.2010.33","DOIUrl":"https://doi.org/10.1109/DICTA.2010.33","url":null,"abstract":"A new feature selection approach is proposed for facial expression recognition system. The features are extracted using Gabor filters from Grey-scale images for characterizing facial texture. Then, an adaptive filter selection (AFS) algorithm is applied to choose the best subset of Gabor filters with different scales and orientations. In AFS algorithm, the filters are selected based on spectral difference between the original image and the noisy image in Gabor wavelet domain. After that, the optimum subset of filters is selected based on minimum error rate. This subset of Gabor filters is used for feature extraction. The extracted features are classified by adopting a multiple linear discriminant analysis (LDA) classifier. Experiments on different databases are carried out that the method is efficient for facial expression recognition.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127813744","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 averaging can be performed very efficiently using either separable moving average filters or by using summed area tables, also known as integral images. Both these methods allow averaging to be performed at a small fixed cost per pixel, independent of the averaging filter size. Repeated filtering with averaging filters can be used to approximate Gaussian filtering. Thus a good approximation to Gaussian filtering can be achieved at a fixed cost per pixel independent of filter size. This paper describes how to determine the averaging filters that one needs to approximate a Gaussian with a specified standard deviation. The design of bandpass filters from the difference of Gaussians is also analysed. It is shown that difference of Gaussian bandpass filters share some of the attributes of log-Gabor filters in that they have a relatively symmetric transfer function when viewed on a logarithmic frequency scale and can be constructed with large bandwidths.
{"title":"Fast Almost-Gaussian Filtering","authors":"P. Kovesi","doi":"10.1109/DICTA.2010.30","DOIUrl":"https://doi.org/10.1109/DICTA.2010.30","url":null,"abstract":"Image averaging can be performed very efficiently using either separable moving average filters or by using summed area tables, also known as integral images. Both these methods allow averaging to be performed at a small fixed cost per pixel, independent of the averaging filter size. Repeated filtering with averaging filters can be used to approximate Gaussian filtering. Thus a good approximation to Gaussian filtering can be achieved at a fixed cost per pixel independent of filter size. This paper describes how to determine the averaging filters that one needs to approximate a Gaussian with a specified standard deviation. The design of bandpass filters from the difference of Gaussians is also analysed. It is shown that difference of Gaussian bandpass filters share some of the attributes of log-Gabor filters in that they have a relatively symmetric transfer function when viewed on a logarithmic frequency scale and can be constructed with large bandwidths.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115803068","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 framework to track non-rigid objects adaptively by fusion of visual and motional feature descriptors. The proposed technique can automatically detect an object from different points of view as soon as the object starts moving. Moreover an object model is created and gradually updated using both new and previous features. As a result, the proposed technique is able to track a non-rigid object even if the object is rotating or distorting. The efficacy of the proposed method is verified using the experimental results obtained from a grayscale camera.
{"title":"Adaptive Non-rigid Object Tracking by Fusing Visual and Motional Descriptors","authors":"H. Firouzi, H. Najjaran","doi":"10.1109/DICTA.2010.19","DOIUrl":"https://doi.org/10.1109/DICTA.2010.19","url":null,"abstract":"This paper presents a framework to track non-rigid objects adaptively by fusion of visual and motional feature descriptors. The proposed technique can automatically detect an object from different points of view as soon as the object starts moving. Moreover an object model is created and gradually updated using both new and previous features. As a result, the proposed technique is able to track a non-rigid object even if the object is rotating or distorting. The efficacy of the proposed method is verified using the experimental results obtained from a grayscale camera.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812522","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：