Sandra Mau, Shaokang Chen, Conrad Sanderson, B. Lovell
{"title":"Video face matching using subset selection and clustering of probabilistic Multi-Region Histograms","authors":"Sandra Mau, Shaokang Chen, Conrad Sanderson, B. Lovell","doi":"10.1109/IVCNZ.2010.6148860","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148860","url":null,"abstract":"Balancing computational efficiency with recognition accuracy is one of the major challenges in real-world video-based face recognition. A significant design decision for any such system is whether to process and use all possible faces detected over the video frames, or whether to select only a few ‘best’ faces. This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering. Three face selection metrics are evaluated for choosing a subset: face detection confidence, random subset, and sequential selection. Experiments on the recently introduced MOBIO dataset indicate that the usage of all faces through clustering always outperformed selecting only a subset of faces. The experiments also show that the face selection metric based on face detection confidence generally provides better recognition performance than random or sequential sampling. Moreover, the optimal number of faces varies drastically across selection metric and subsets of MOBIO. Given the trade-offs between computational effort, recognition accuracy and robustness, it is recommended that face feature clustering would be most advantageous in batch processing (particularly for video-based watchlists), whereas face selection methods should be limited to applications with significant computational restrictions.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128544913","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}
{"title":"An improved Kernel-based Fuzzy C-means Algorithm with spatial information for brain MR image segmentation","authors":"Rong Xu, J. Ohya","doi":"10.1109/IVCNZ.2010.6148819","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148819","url":null,"abstract":"In this paper, we propose an improved Kernel-based Fuzzy C-means Algorithm (iKFCM) with spatial information to reduce the effect of noise for brain MR image segmentation. We use k-nearest neighbour model and a neighbourhood controlling factor by estimating image contextual constraints to optimize the objective function of conventional KFCM method. Conventional KFCM algorithms classify each pixel in image only by its own gray value, but the proposed method classifies by the gray values of its neighbourhood system. For this reason, the proposed iKFCM has a strong robustness for image noise in image segmentation. In experiments, some synthetic grayscale images and simulated brain MR images are used to assess the performance of iKFCM in comparison with other fuzzy clustering methods. The experimental results show that the proposed iKFCM method achieves a better segmentation performance than other fuzzy clustering methods.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"37 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":"116603674","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}
Jun Fujiki, Yumi Usami, H. Hino, S. Akaho, N. Murata
{"title":"Estimation of a rotationally symmetric mirror shape from a frontal image of the mirror","authors":"Jun Fujiki, Yumi Usami, H. Hino, S. Akaho, N. Murata","doi":"10.1109/IVCNZ.2010.6148829","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148829","url":null,"abstract":"In structure from motion problems, mirror shape reconstruction from mirror image is very interesting. In this paper, we propose a method to estimate the shape of a rotationally symmetric mirror by calibrating a mirror image which has radially symmetric distortion. In the proposed method, the shape of mirror is represented by the set of solution of a differential equation, which is derived from distortion function computed by the calibration of radially symmetric distortion of an image on a rotationally symmetric mirror. The differential equation and the boundary condition are simplified under the assumption that the image on mirror is taken by orthographic projection camera. The experimental result for a real image is presented to demonstrate the performance of our reconstruction method, and the method is applied for reconstruction of the shape of the mirror painted on the Jan van Eyck's Arnolfini Wedding which had drawn in the 15th century.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"58 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":"124500864","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}
{"title":"Enhanced image saliency model based on blur identification","authors":"Rizwan A. Khan, H. Konik, É. Dinet","doi":"10.1109/IVCNZ.2010.6148833","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148833","url":null,"abstract":"Detection of visual saliency is of great interest for a lot of computer vision applications in particular for content-based image retrieval. The work presented in this paper is devoted to develop an algorithm of saliency detection that performs adequately in predicting human fixations for stimuli containing blur and sharp regions. This work is based on an experimental study on the effect of blurriness on visual attention when observers see images with no prior knowledge in free viewing conditions. A ground-truth has been derived from this experimental study to test the saliency model we developed.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130204135","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}
{"title":"Evaluation of the effectiveness of head tracking for view and avatar control in virtual environments","authors":"Stefan Marks, John A. Windsor, Burkhard Wünsche","doi":"10.1109/IVCNZ.2010.6148801","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148801","url":null,"abstract":"Virtual environments (VE) are gaining in popularity and are increasingly used for teamwork training purposes, e.g., for medical teams. We have identified two shortcomings of modern VEs: First, nonverbal communication channels are essential for teamwork but are not supported well. Second, view control in VEs is usually done manually, requiring the user to learn the controls before being able to effectively use them. We address those two shortcomings by using an inexpensive webcam to track the user's head. The rotational movement is used to control the head movement of the user's avatar, thereby conveying head gestures and adding a nonverbal communication channel. The translational movement is used to control the view of the VE in an intuitive way. Our paper presents the results of a user study designed to investigate how well users were able to use our system's advantages.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130962723","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}
{"title":"Combining online feature selection with adaptive shape estimation","authors":"Adam Gatt, S. Wong, D. Kearney","doi":"10.1109/IVCNZ.2010.6148841","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148841","url":null,"abstract":"The online selection of features is widely cited to provide benefits in video tracking applications where the foreground (object) and background (clutter) models must to adapt to changes in the scene. It is commonplace amongst researchers in the field to assume a rectangular bounding box between foreground and background that is known a priori and is invariant during the tracking process. In many important tracking scenarios these assumptions do not hold. Recent work has shown that online feature selection is critically dependant on the selection of the boundary between the foreground and background. In this paper we present a tracking system that uses highly accurate shape estimates generated by the Shape Estimating Filter algorithm, which probabilistically estimates object shape using both top-down and bottom-up Bayesian methods. We show that the use of these shape estimations for object modelling improves feature selection over a simple bounding box scheme.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"51 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120815369","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}
{"title":"Pigmented skin lesion segmentation on macroscopic images","authors":"P. G. Cavalcanti, Yessenia Yari, J. Scharcanski","doi":"10.1109/IVCNZ.2010.6148845","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148845","url":null,"abstract":"Several pigmented skin lesion segmentation methods have been proposed for dermoscopy images, however skin lesion segmentation on macroscopic images have not received much attention. Despite the fact that dermoscopy is a very specialized technique, in some practical situations, patients do not have a fast access to an specialist. In this situations, pre-screening systems can be used to evaluate a suspect skin lesion by a non-specialist, and lesion segmentation is very important for the success of such systems. This paper proposes a new method for segmenting pigmented skin lesions on macroscopic images acquired with standard cameras. Our method is simpler than comparable methods proposed for dermoscopy, and our experiments based on publicly available datasets of pigmented skin lesion images show promising results. Our approach can achieve an average segmentation error of 24.85%, which is better than the accuracy of comparable methods available in the literature (even for illumination corrected images).","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127291620","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}
{"title":"UACI: Uncertain associative classifier for object class identification in images","authors":"L. Manikonda, A. Mangalampalli, Vikram Pudi","doi":"10.1109/IVCNZ.2010.6148859","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148859","url":null,"abstract":"Uncertainty is inherently present in many real-world domains like images. Analyses of such uncertain data using traditional certain-data-oriented techniques do not achieve best possible accuracy. UACI introduces the concept of representing images in the form of a probabilistic or uncertain model using interest points in images. This model is an uncertain-data-based adaptation of Bag of Words, with each image not only represented by the visual words that it contains, but also their respective probabilities of occurrence in the image. UACI uses an Associative Classification approach to leverage latent frequent patterns in images for the identification of object classes. Unlike most image classifiers, which rely on positive and negative class sets (generally very vague) for training, UACI uses only positive class images for training. We empirically compare UACI with three other state-of-the-art image classifiers, and show that UACI performs much better than the other classifying approaches.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115015706","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}
{"title":"Real-time aerial image mosaicing","authors":"T. Botterill, S. Mills, R. Green","doi":"10.1109/IVCNZ.2010.6148850","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148850","url":null,"abstract":"This paper describes a scheme for seamlessly stitching together images captured from an aerial platform, in real-time, in order to provide an operator with a larger field-of-view. Both recent images, and images from earlier in a flight are used. To obtain real-time performance several of the latest computer vision techniques are applied: firstly the Bag-of-Words image representation allows overlapping images to be found efficiently, and provides cheap wide-baseline correspondences between them. Secondly the BaySAC robust estimation framework allows images to be registered efficiently from a prior motion model combined with large numbers of potential matches between cheap image patch descriptors. Thirdly an efficient seam-placement algorithm allows the rendering of a visually attractive mosaic. Results are presented on a sequence of high-resolution images captured from a microlight.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115182834","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}
K. M. Yi, S. Kim, Hawook Jeong, Songhwai Oh, J. Choi
{"title":"Non-rigid object tracking with elastic structure of local patches and hierarchical sampling","authors":"K. M. Yi, S. Kim, Hawook Jeong, Songhwai Oh, J. Choi","doi":"10.1109/IVCNZ.2010.6148831","DOIUrl":"https://doi.org/10.1109/IVCNZ.2010.6148831","url":null,"abstract":"To solve the problem of real-time object tracking under partial occlusions and non-rigid deformations, we propose a tracking method based on sequential Bayesian inference. The proposed method is mainly consisted of two parts: (1) modeling the target object using elastic structure of local patches for robust performance; and (2) efficient hierarchical sampling method to obtain an acceptable solution in real-time. The elastic structure of local patches allows the proposed method to handle partial occlusions and non-rigid deformations through the relationship among neighboring patches. The proposed hierarchical sampling method generate samples from the region where the posterior is concentrated to reduce computation time. The method is extensively tested on a number of challenging image sequences with occlusion and non-rigid deformation, demonstrating its real-time capability and robustness under di#erent situations.","PeriodicalId":209059,"journal":{"name":"2010 25th International Conference of Image and Vision Computing New Zealand","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123897372","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}