{"title":"Principles Emerging from the Design of Visual Search Algorithms for Practical Inspection Tasks","authors":"E. R. Davies","doi":"10.1109/IMVIP.2008.27","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.27","url":null,"abstract":"This paper is targeted at the design of inspection algorithms involving fast visual search for features, products, and the artefacts that accompany them. The work is based on a number of cereal grain inspection tasks that have presented important problems relating to robustness, sensitivity, accuracy and speed of operation. Techniques covered include multi-level thresholding, morphological operators, mask design, multi-stage processing, and sampling procedures. While in some sense these techniques are simple, they are not trivial to apply, because of the difficulty of specifying algorithms in applications where the image data to be analysed is highly variable, fuzzy, and voluminous. Indeed the difficulty of describing the data sufficiently precisely is both here and in general a highly inhibiting obstacle on the path to specifying and producing optimal algorithms. Nevertheless, it has proved possible to identify a number of generic principles underlying the design of visual search algorithms.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125273180","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 Multi-part Models for Mean-Shift Tracking","authors":"D. Caulfield, K. Dawson-Howe","doi":"10.1109/IMVIP.2008.14","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.14","url":null,"abstract":"Mean-shift tracking is a data-driven technique for tracking objects through a video sequence. We propose an innovation to mean-shift tracking that combines the background exclusion constraint with multi-part appearance models. The former constraint prevents the tracker from moving to regions where no foreground objects are present, while the multi-part nature of the models enforces a spatial structure on the tracked object. We also use a simple formula to determine the scale of the object in each video frame, and note the importance of setting an appropriate convergence condition. An evaluation of our proposed tracker and several existing trackers is performed using a ground truth dataset. We demonstrate that our innovation yields more accurate tracking than existing mean-shift techniques.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114145870","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 Visualization of Cardiac Catheterization Procedures Based on a New Algorithm for Reconstructions from Planar Cross Sections Using the Unconstrained 3D Delaunay Triangulation","authors":"Yingliang Ma, K. Rhode, R. Razavi, K. Saetzler","doi":"10.1109/IMVIP.2008.10","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.10","url":null,"abstract":"Real-time visualization plays an important role in medical imaging applications such as image-guided surgery, surgical simulation and medical education. For the real-time visualization and the simultaneous overlay of 3D triangulated objects onto live recordings of patient data gathered with fast imaging devices (e.g. from the beating heart) it is essential that the number of triangles used for displaying the meshes are reasonably low. For this purpose, we developed a novel, optimized surface reconstruction algorithm for planar cross sections based on the non-constrained 3D Delaunay triangulation using pre-computed contour data. The proposed method generates 50% fewer triangles for the cardiac images used in our application domain in comparison to standard reconstruction methods from planar cross sections. Besides reducing the number of triangles, our method eliminates 'stair-case' artifacts that can occur between consecutive cross sections for non-uniformly sampled input image data often found in biomedical imaging applications.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129791298","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}
J. Burke, P. Morrow, M. McNeill, S. McDonough, D. Charles
{"title":"Vision Based Games for Upper-Limb Stroke Rehabilitation","authors":"J. Burke, P. Morrow, M. McNeill, S. McDonough, D. Charles","doi":"10.1109/IMVIP.2008.16","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.16","url":null,"abstract":"Recent studies have shown the potential benefits of applying technology to stroke rehabilitation. Traditional rehabilitation tasks are often mundane, and can lead to a lack of patient motivation, resulting in little or no independent patient exercise taking place. We describe a low-cost visual tracking system suitable for upper limb stroke rehabilitation in the home which does not require expensive or special equipment and which can be operated entirely independently by the patient. We look at past applications of imaging to stroke rehabilitation, and also game design theory and how it can be applied to stroke rehabilitation. We then describe two small prototype games which implement colour/object segmentation and motion detection to form the basis of our home rehabilitation system.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132561891","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":"Biometric Identification Using Motion History Images of a Speaker's Lip Movements","authors":"Alfredo Grunwald de la Cuesta, Jianguo Zhang","doi":"10.1109/IMVIP.2008.13","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.13","url":null,"abstract":"This paper describes a new simple, but effective, approach to speaker verification using video sequences of lip movements. We use motion history images (MHI) to provide a biometric template of a spoken word for each speaker. Class-dependent correlation filters are then created by a weighted optimization of training MHI samples. Feature extraction is performed by correlating a test MHI against each correlation filter. A Bayesian classifier is deployed for classification. We carry out an extensive performance evaluation of our approach with respect to the number of training samples and different words. Results clearly show the efficacy of our method.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132590438","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":"Where is It? Object Reacquisition in Surveillance Video","authors":"F. Campbell-West, Hongbin Wang, P. Miller","doi":"10.1109/IMVIP.2008.23","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.23","url":null,"abstract":"We investigate the novel use of online PCA as a means of learning an object representation for track reacquisition following relatively long periods of track loss. A new Bayesian formulation for object verification is presented and correct track reacquisition is demonstrated for vehicles in ground- and air-based video. Video based object verification in airborne video is a new area, which uniquely positions this work.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131502430","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 Investigation into Optical Flow Computation on FPGA Hardware","authors":"T. Browne, J. Condell, G. Prasad, T. McGinnity","doi":"10.1109/IMVIP.2008.11","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.11","url":null,"abstract":"Motion estimation (or optical flow estimation) is an interesting problem in computer vision. However this task is computationally intensive for conventional processors. In this work an investigation into an FPGA-based hardware architecture for real-time motion estimation is carried out. The algorithm used in this paper is a gradient based inverse finite element method for optical flow computation. It carries out the motion estimation by calculating the gradient, Laplacian, and subsequently the velocities of each pixel in a parallel design which aids in the speed of the computation. The algorithm has been benchmarked against many of the well known algorithms cited within the field. A literature review is carried out and the algorithm is discussed. An FPGA design is presented. Preliminary simulation results are shown and discussed.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114720848","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":"Comparing Cornerness Measures for Interest Point Detection","authors":"D. Kerr, S. Coleman, B. Scotney","doi":"10.1109/IMVIP.2008.28","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.28","url":null,"abstract":"Interest point detection is used in many computer vision applications that require fast and efficient feature matching. For tasks such as robot localisation and navigation, the use of interest points for matching is preferred over edges or other, larger, features. Recently, finite-element based methods have been used to develop gradient operators for edge and interest point detection. We extend this work to alternative corner detection measures and provide a comparative evaluation of some different techniques.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126977849","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":"Multicues Face Detection in Complex Background for Frontal Faces","authors":"A. Pal","doi":"10.1109/IMVIP.2008.32","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.32","url":null,"abstract":"Face recognition (FR) systems are increasingly gaining more importance. Face detection and tracking in a complex scene forms the first step in building a practical FR system. In this paper a hybrid algorithm to detect face(s) in color images is introduced. The algorithm uses color histogram for skin (in the HSV color space) in conjunction with shape information and facial feature detection to quickly locate faces in a given image.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131256041","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":"Multi-scale Feature Extraction in a Sub-pixel Virtual Hexagonal Environment","authors":"B. Gardiner, S. Coleman, B. Scotney","doi":"10.1109/IMVIP.2008.29","DOIUrl":"https://doi.org/10.1109/IMVIP.2008.29","url":null,"abstract":"The area of hexagonal image representation has been explored for several decades based on the hexagonal structure's many advantages over conventional rectangular image grids. Due to existing image capture and display hardware being produced for rectangular structures only, most research to date has focused on developing an efficient software approach to mimic hexagonal grid structures. Only recently has the area of hexagonal image processing been investigated, where techniques such as rotation, scaling and edge detection have been implemented. In this paper, we present an approach to the development of multi-scale hexagonal gradient operators using the finite element framework. We apply these operators in a sub-pixel virtual hexagonal environment and provide both visual and quantitative results when comparing with standard rectangular image processing techniques.","PeriodicalId":280649,"journal":{"name":"2008 International Machine Vision and Image Processing Conference","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131319248","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}