{"title":"Thinning in a distributed environment","authors":"P. Kwok","doi":"10.1109/ICPR.1990.118195","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118195","url":null,"abstract":"In the digitization of survey maps where the components are sparse but occupy large areas, a serial thinning algorithm implemented on a distributed environment can yield a better speedup than is possible with other forms of parallelism. A distributed algorithm based on contour generation is described. A component is divided into rectangular sections and assigned to different processors. A block-resume synchronization mechanism is examined. The different contour configurations at the border of a section are identified. The amount of communication between neighboring sections can be kept to a minimum by chain code representations. The proposed synchronization mechanism has been incorporated in the contour generation thinning algorithm and has been simulated on a Sun/4 workstation. For images such as contour maps, the extra overhead needed for synchronization is not significant.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130666497","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":"Time-recursive motion estimation using dynamical models for motion prediction","authors":"K. Karmann","doi":"10.1109/ICPR.1990.118109","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118109","url":null,"abstract":"The author describes a time-recursive method for motion estimation that utilizes dynamical models for object motion to predict the positions and motion parameters of all objects at future times. The predicted positions and motion vectors are used to reduce the search space of a segment matching step, which serves to measure the object displacements by comparing object positions in consecutive frames. The predicted positions and motion vectors are corrected by the use of the measured displacements during a measurement update step, in which corrected positions and motion vectors are computed. The method has been applied to several tracking problems (traffic monitoring and intrusion protection) and yielded excellent results during simulations on a general-purpose computer.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123529792","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":"Depth restoration from defocused images using simulated annealing","authors":"K. Prasad, R. Mammone","doi":"10.1109/ICPR.1990.118099","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118099","url":null,"abstract":"The recovery of depth from defocused images is formulated as a 3-D image restoration problem. A defocused image is modeled as the combinatorial outcome of the depths and intensities of the volume elements (voxels) of an opaque 3-D object. A large depth-of-field image is used to constrain the intensities of the voxels. The depths of voxels are estimated from a highly defocused image by using simulated annealing to solve a constrained optimization problem. It is concluded that the method provides a framework for high-resolution depth recovery from defocused images. The method is computationally-intensive; however, it is amenable to parallel processing and is well suited for small field-of-interest applications.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116222746","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":"Scale-space tree and its hierarchy","authors":"T. Wada, M. Sato","doi":"10.1109/ICPR.1990.119338","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119338","url":null,"abstract":"Scale-space filtering is a multiresolutional filtering method which expands a waveform to the set of waveforms in multiscale measurement. The intervals bounded by zero-crossings of expanded waveforms have a hierarchical structure, which can be represented by an interval tree. Another hierarchical description of the waveform, scale-space tree, is introduced as a natural description of the hierarchy. The difference hierarchy between the interval tree and the scale-space tree is discussed.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192067","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":"Detection of depth and orientation discontinuities in range images using mathematical morphology","authors":"P. Boulanger, F. Blais, Philip R. Cohen","doi":"10.1109/ICPR.1990.118205","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118205","url":null,"abstract":"A technique for the detection of depth and orientation discontinuities in range images is described. This method uses basic morphological operators to extract these discontinuities from a dense range map. The authors describe how to extract depth discontinuities using the morphological edge operator of J.S.J. Lee et al. (1987) and how to use a top-hat operator to localize the exact positions of these discontinuities. The detection of orientation discontinuities is then discussed in detail. The calculation of a good estimate of the surface normals using anisotropic filtering inhibited at depth discontinuities is demonstrated. Once these estimates of the normals are calculated, operations similar to those used in depth discontinuity detection are used to locate orientation discontinuities at abrupt variations of the surface normals. Experimental results demonstrate computation of the positions of these discontinuities at pixel precision as well as very efficient use of morphological operators to localize abrupt variations in a noisy image signal in less than 1 s using a Datacube image processor.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127562218","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":"The extended binary tree representation of binary image and its application to engineering drawing entry","authors":"Bin Yu, Xinggang Lin","doi":"10.1109/ICPR.1990.119339","DOIUrl":"https://doi.org/10.1109/ICPR.1990.119339","url":null,"abstract":"A kind of tree structure called extended binary tree (EBT) is presented to represent the line adjacency graph (LAG) in order to reduce the computational complexities of LAG-based algorithms in binary image processing. The traversal and the storage of the EBT are discussed. Applications of the structure in engineering drawing entry are shown.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"70 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128011623","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":"Future directions in computer vision and image understanding; ETL perspectives","authors":"K. Yamamoto","doi":"10.1109/ICPR.1990.118060","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118060","url":null,"abstract":"Research work dealing with some of the problems in computer vision (CV) and image understanding (IU) is described. Attention is given to progress in CV and IU involving active range finders, passive stereo sensing, 3D reconstruction, 3D scene analysis, dynamic scene analysis, automatic knowledge acquisition for model- and strategy-based systems, and autonomous vision systems.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"65 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128023826","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":"Simultaneous multiple optical flow estimation","authors":"M. Shizawa, K. Mase","doi":"10.1109/ICPR.1990.118111","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118111","url":null,"abstract":"The authors propose a simultaneous closed-form estimation method for multiple optical flow from image sequences in which each image point has multiple motions. This method only requires convolution for space-time filtering and low-dimensional eigensystem analysis as an optimization process. The authors propose a mixture flow model of a multiple flow and energy integral minimization as a model fitting method. It is shown that symmetry between component flows of the mixture flow can reduce the dimension of the eigensystem and make the optimization unimodal and stable. Successful experiments on double-flow estimation of random texture patterns and natural scene images are reported.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128035345","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":"Kernel classification rules in the presence of missing values","authors":"M. Pawlak, W. Siedlecki","doi":"10.1109/ICPR.1990.118190","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118190","url":null,"abstract":"The nonparametric kernel classification rule derived from incomplete data is studied. Methods of designing kernel decision rules possessing optimal asymptotic properties are proposed. Consistency and rates of convergence are examined. It is argued that the replacement methods using the regression approach can lead to the inconsistency of resulting decision rules. On the other hand, a method employing the concept of predictive density yields asymptotically optimal classification rules.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128105197","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":"Online recognizer for runon handprinted characters","authors":"T. Fujisaki, T. E. Chefalas, J. Kim, C. Tappert","doi":"10.1109/ICPR.1990.118144","DOIUrl":"https://doi.org/10.1109/ICPR.1990.118144","url":null,"abstract":"A recognize-then-segment recognizer of unconstrained handprinting is described with uses a unified tablet-display to provide a paperlike computer interface. Whereas most handwriting recognition systems segment and then recognize, this one recognizes and then finds the best segmentation. It classifies strokes, generates character hypotheses, and verifies hypotheses to estimate the optimal character sequence for each word of runon handwritten characters. Linguistic constraints can limit the choices. The system is implemented on an IBM workstation, accepts runon characters written on a tablet, and performs recognition in real time.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132055147","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}