In 2002, Kim et al described a fast and robust technique for the automatic detection of ellipses from a binary edge image. The current paper introduces some modifications to this algorithm which retain its speed, while increasing its detection performance. The two algorithms are then compared for the application of detecting wheels within images using a data-set of 100 images of cars.
{"title":"A Fast Automatic Ellipse Detector","authors":"T. Cooke","doi":"10.1109/DICTA.2010.102","DOIUrl":"https://doi.org/10.1109/DICTA.2010.102","url":null,"abstract":"In 2002, Kim et al described a fast and robust technique for the automatic detection of ellipses from a binary edge image. The current paper introduces some modifications to this algorithm which retain its speed, while increasing its detection performance. The two algorithms are then compared for the application of detecting wheels within images using a data-set of 100 images of cars.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"88 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":"132919501","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, an approach for human action recognition is presented based on adaptive bag-of-words features. Bag-of-words techniques employ a codebook to describe a human action. For successful recognition, most action recognition systems currently require the optimal codebook size to be determined, as well as all instances of human actions to be available for computing the features. These requirements are difficult to satisfy in real life situations. An update - describe method for addressing these problems is proposed. Initially, interest point patches are extracted from action clips. Then, in the update step these patches are clustered using the Clustream algorithm. Each cluster centre corresponds to a visual word. A histogram of these visual words representing an action is constructed in the describe step. A chi-squared distance-based classifier is utilised for recognising actions. The proposed approach is implemented on benchmark KTH and Weizmann datasets.
{"title":"An Update-Describe Approach for Human Action Recognition in Surveillance Video","authors":"A. Wiliem, V. Madasu, W. Boles, P. Yarlagadda","doi":"10.1109/DICTA.2010.55","DOIUrl":"https://doi.org/10.1109/DICTA.2010.55","url":null,"abstract":"In this paper, an approach for human action recognition is presented based on adaptive bag-of-words features. Bag-of-words techniques employ a codebook to describe a human action. For successful recognition, most action recognition systems currently require the optimal codebook size to be determined, as well as all instances of human actions to be available for computing the features. These requirements are difficult to satisfy in real life situations. An update - describe method for addressing these problems is proposed. Initially, interest point patches are extracted from action clips. Then, in the update step these patches are clustered using the Clustream algorithm. Each cluster centre corresponds to a visual word. A histogram of these visual words representing an action is constructed in the describe step. A chi-squared distance-based classifier is utilised for recognising actions. The proposed approach is implemented on benchmark KTH and Weizmann datasets.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"11 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":"133060163","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}
Orthogonal Matching Pursuit (OMP) algorithm is widely applied to compressive sensing (CS) image signal recovery because of its low computation complexity and its ease of implementation. However, OMP usually needs more measurements than some other recovery algorithms in order to achieve equal-quality reconstructions. This article firstly illustrates the fundamental idea of OMP and the specific algorithm steps. And then, two limitations leading to the previous issue are addressed. Finally, a sorted random matrix is proposed to be used as a measurement matrix to improve those two limitations. The experimental results show the proposed measurement matrix is able to help OMP make a great progress on the quality of recovered approximations.
{"title":"Sorted Random Matrix for Orthogonal Matching Pursuit","authors":"Zhenglin Wang, Ivan Lee","doi":"10.1109/DICTA.2010.29","DOIUrl":"https://doi.org/10.1109/DICTA.2010.29","url":null,"abstract":"Orthogonal Matching Pursuit (OMP) algorithm is widely applied to compressive sensing (CS) image signal recovery because of its low computation complexity and its ease of implementation. However, OMP usually needs more measurements than some other recovery algorithms in order to achieve equal-quality reconstructions. This article firstly illustrates the fundamental idea of OMP and the specific algorithm steps. And then, two limitations leading to the previous issue are addressed. Finally, a sorted random matrix is proposed to be used as a measurement matrix to improve those two limitations. The experimental results show the proposed measurement matrix is able to help OMP make a great progress on the quality of recovered approximations.","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":"133260578","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}
We define a “generic” non-rigid face tracker as any system that exhibits robustness to changes in illumination, expression and viewpoint during the tracking of facial land-marks in a video sequence. A popular approach to the problem is to detect/track an ensemble of local features over time whilst enforcing they conform to a global non-rigid shape prior. In general these approaches employ a strategy that assumes: (i) the feature points being tracked, ignoring occlusion, should roughly correspond across all frames, and (ii) that these feature points should correspond to the landmark points defining the non-rigid face shape model. In this paper, we challenge these two assumptions through the novel application of interest point detectors and descriptors (e.g. SIFT & SURF). We motivate this strategy by demonstrating empirically that salient features on the face for tracking on average only have a “track-life” of a few frames and rarely co-occur at the vertex points of the shape model. Due to the short track-life of these features we propose that new features should be detected at every frame rather than tracked from previous frames. By employing such a strategy we demonstrate that our proposed method has natural invariance to large discontinuous changes in motion. We additionally propose the employment of an online feature registration step that is able to rectify error accumulation and provides fast recovery from occlusion during tracking.
{"title":"Non-rigid Face Tracking Using Short Track-Life Features","authors":"S. Lucey, Jun-Su Jang","doi":"10.1109/DICTA.2010.51","DOIUrl":"https://doi.org/10.1109/DICTA.2010.51","url":null,"abstract":"We define a “generic” non-rigid face tracker as any system that exhibits robustness to changes in illumination, expression and viewpoint during the tracking of facial land-marks in a video sequence. A popular approach to the problem is to detect/track an ensemble of local features over time whilst enforcing they conform to a global non-rigid shape prior. In general these approaches employ a strategy that assumes: (i) the feature points being tracked, ignoring occlusion, should roughly correspond across all frames, and (ii) that these feature points should correspond to the landmark points defining the non-rigid face shape model. In this paper, we challenge these two assumptions through the novel application of interest point detectors and descriptors (e.g. SIFT & SURF). We motivate this strategy by demonstrating empirically that salient features on the face for tracking on average only have a “track-life” of a few frames and rarely co-occur at the vertex points of the shape model. Due to the short track-life of these features we propose that new features should be detected at every frame rather than tracked from previous frames. By employing such a strategy we demonstrate that our proposed method has natural invariance to large discontinuous changes in motion. We additionally propose the employment of an online feature registration step that is able to rectify error accumulation and provides fast recovery from occlusion during tracking.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"12 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":"117180702","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}
Surface colour changes and specular reflections are two major problems in 3D modelling using shape-from-shading (SFS). This paper proposes to pre-process the input image for a typical SFS algorithm, so that the resultant image has no colour changes and specular reflection. First, a chromaticity-based specular reflection removal algorithm is applied to achieve a pure diffuse (Lambertian) reflected image. Then, a novel chromaticity-based colour adjustment approach is proposed to generate an image without surface colour changes. The standard SFS algorithms can then be applied successfully onto the processed images to produce plausible 3D models. In experiments, the proposed approach was tested on standard SFS datasets with complex surface colours. The experimental results show it’s promising to facilitate SFS algorithms to handle SFS problems with more complex surface properties and illumination conditions.
{"title":"Colour Adjustment and Specular Removal for Non-uniform Shape from Shading","authors":"Xiaozheng Zhang, Yongsheng Gao, T. Caelli","doi":"10.1109/DICTA.2010.100","DOIUrl":"https://doi.org/10.1109/DICTA.2010.100","url":null,"abstract":"Surface colour changes and specular reflections are two major problems in 3D modelling using shape-from-shading (SFS). This paper proposes to pre-process the input image for a typical SFS algorithm, so that the resultant image has no colour changes and specular reflection. First, a chromaticity-based specular reflection removal algorithm is applied to achieve a pure diffuse (Lambertian) reflected image. Then, a novel chromaticity-based colour adjustment approach is proposed to generate an image without surface colour changes. The standard SFS algorithms can then be applied successfully onto the processed images to produce plausible 3D models. In experiments, the proposed approach was tested on standard SFS datasets with complex surface colours. The experimental results show it’s promising to facilitate SFS algorithms to handle SFS problems with more complex surface properties and illumination conditions.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"21 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":"127283479","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 direction-oriented covariance based deinterlacing method is presented. First, the local direction of edge is determined by modified edge-based line average (MELA) method. Then, based on the geometric duality, the optimal interpolation coefficients for the neighbor pixels of corresponding direction are estimated using the Wiener filtering. Experimental results prove that the proposed method provides a significant improvement over the other existing deinterlacing methods.
{"title":"Direction-Oriented Line Interpolation Using Geometric Duality","authors":"Sang-Jun Park, Jechang Jeong, Gwanggil Jeon","doi":"10.1109/DICTA.2010.24","DOIUrl":"https://doi.org/10.1109/DICTA.2010.24","url":null,"abstract":"In this paper, a direction-oriented covariance based deinterlacing method is presented. First, the local direction of edge is determined by modified edge-based line average (MELA) method. Then, based on the geometric duality, the optimal interpolation coefficients for the neighbor pixels of corresponding direction are estimated using the Wiener filtering. Experimental results prove that the proposed method provides a significant improvement over the other existing deinterlacing methods.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"144 5 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":"129569300","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}
Due to its potential applications, face recognition has been receiving more and more research attention recently. In this paper, we present a robust real-time facial recognition system. The system comprises three functional components, which are face detection, eye alignment and face recognition, respectively. Within the context of computer vision, there are lots of candidate algorithms to accomplish the above tasks. Having compared the performance of a few state-of-the-art candidates, robust and efficient algorithms are implemented. As for face detection, we have proposed a new approach termed Boosted Greedy Sparse Linear Discriminant Analysis (BGSLDA) that produces better performances than most reported face detectors. Since face misalignment significantly deteriorates the recognition accuracy, we advocate a new cascade framework including two different methods for eye detection and face alignment. We have adopted a recent algorithm termed Sparse Representation-based Classification (SRC) for the face recognition component. Experiments demonstrate that the whole system is highly qualified for efficiency as well as accuracy.
{"title":"Robust Face Recognition via Accurate Face Alignment and Sparse Representation","authors":"Hanxi Li, Peng Wang, Chunhua Shen","doi":"10.1109/DICTA.2010.54","DOIUrl":"https://doi.org/10.1109/DICTA.2010.54","url":null,"abstract":"Due to its potential applications, face recognition has been receiving more and more research attention recently. In this paper, we present a robust real-time facial recognition system. The system comprises three functional components, which are face detection, eye alignment and face recognition, respectively. Within the context of computer vision, there are lots of candidate algorithms to accomplish the above tasks. Having compared the performance of a few state-of-the-art candidates, robust and efficient algorithms are implemented. As for face detection, we have proposed a new approach termed Boosted Greedy Sparse Linear Discriminant Analysis (BGSLDA) that produces better performances than most reported face detectors. Since face misalignment significantly deteriorates the recognition accuracy, we advocate a new cascade framework including two different methods for eye detection and face alignment. We have adopted a recent algorithm termed Sparse Representation-based Classification (SRC) for the face recognition component. Experiments demonstrate that the whole system is highly qualified for efficiency as well as accuracy.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"116 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":"132485207","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}
Human identification by gait has created a great deal of interest in computer vision community due to its advantage of inconspicuous recognition at a relatively far distance. This paper provides a comprehensive survey of recent developments on gait recognition approaches. The survey emphasizes on three major issues involved in a general gait recognition system, namely gait image representation, feature dimensionality reduction and gait classification. Also, a review of the available public gait datasets is presented. The concluding discussions outline a number of research challenges and provide promising future directions for the field.
{"title":"A Review of Vision-Based Gait Recognition Methods for Human Identification","authors":"Jin Wang, M. She, S. Nahavandi, A. Kouzani","doi":"10.1109/DICTA.2010.62","DOIUrl":"https://doi.org/10.1109/DICTA.2010.62","url":null,"abstract":"Human identification by gait has created a great deal of interest in computer vision community due to its advantage of inconspicuous recognition at a relatively far distance. This paper provides a comprehensive survey of recent developments on gait recognition approaches. The survey emphasizes on three major issues involved in a general gait recognition system, namely gait image representation, feature dimensionality reduction and gait classification. Also, a review of the available public gait datasets is presented. The concluding discussions outline a number of research challenges and provide promising future directions for the field.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"52 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":"130379026","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}
WebEpi is an epidemiological WebGIS service developed for the Population Health Epidemiology Unit of the Tasmania Department of Health and Human Services (DHHS). Epidemiological geographical studies help analyze public health surveillance and medical situations. It is still a challenge to conduct large-scale geographical information exploration of epidemiology surveillance based on patterns and relationships. Generally, there are two crucial stages for GIS mapping of epidemiological data: one precisely clusters areas according to their health rate, the other efficiently presents the clustering result on GIS map which aims to help health researchers plan health resources for disease prevention and control. There are two major cluster algorithms for health data exploration, namely Self Organizing Maps (SOM) and K-means. In this paper, the clustering based on SOM and K-means are presented and their clustering results are compared by their clustering process and mapping results. It is concluded from experimental results that K-means produces a more promising mapping result for visualizing the highest mortality rate municipalities.
{"title":"Geo-visualization and Clustering to Support Epidemiology Surveillance Exploration","authors":"Jingyuan Zhang, Hao Shi","doi":"10.1109/DICTA.2010.71","DOIUrl":"https://doi.org/10.1109/DICTA.2010.71","url":null,"abstract":"WebEpi is an epidemiological WebGIS service developed for the Population Health Epidemiology Unit of the Tasmania Department of Health and Human Services (DHHS). Epidemiological geographical studies help analyze public health surveillance and medical situations. It is still a challenge to conduct large-scale geographical information exploration of epidemiology surveillance based on patterns and relationships. Generally, there are two crucial stages for GIS mapping of epidemiological data: one precisely clusters areas according to their health rate, the other efficiently presents the clustering result on GIS map which aims to help health researchers plan health resources for disease prevention and control. There are two major cluster algorithms for health data exploration, namely Self Organizing Maps (SOM) and K-means. In this paper, the clustering based on SOM and K-means are presented and their clustering results are compared by their clustering process and mapping results. It is concluded from experimental results that K-means produces a more promising mapping result for visualizing the highest mortality rate municipalities.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"3 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":"130445013","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}
Chao Zhang, Changming Sun, T. Pham, P. Vallotton, M. Fenech
Assays of micronucleus are extensively used in genotoxicity testing and in monitoring of human exposure to genotoxic materials. As nuclear buds could be a new source of micronuclei formed in interphase, the assay of contents of nuclear bud in normal and comparison group is needed. In this paper, we proposed a new automatic nuclear buds detection algorithm based on ellipse fitting. Experimental results show that our algorithm is effective and efficient. We believe that this is the first report on automated nuclear bud detection for DNA damage scoring.
{"title":"Detection of Nuclear Buds Based on Ellipse Fitting","authors":"Chao Zhang, Changming Sun, T. Pham, P. Vallotton, M. Fenech","doi":"10.1109/DICTA.2010.41","DOIUrl":"https://doi.org/10.1109/DICTA.2010.41","url":null,"abstract":"Assays of micronucleus are extensively used in genotoxicity testing and in monitoring of human exposure to genotoxic materials. As nuclear buds could be a new source of micronuclei formed in interphase, the assay of contents of nuclear bud in normal and comparison group is needed. In this paper, we proposed a new automatic nuclear buds detection algorithm based on ellipse fitting. Experimental results show that our algorithm is effective and efficient. We believe that this is the first report on automated nuclear bud detection for DNA damage scoring.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"7 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":"133896806","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：