{"title":"Using high-level linguistic knowledge for Chinese speech recognition","authors":"Dongxin Xu, Peiji Zhu, Taiyi Huang, D. Chen","doi":"10.1109/ICPR.1988.28205","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28205","url":null,"abstract":"A linguistic processor using syntactic, semantic and vocabulary knowledge as constraints to improve the performance of a Chinese speech recognition system is described. The processor can accept not only sentences but also phrases and words as speech input. Some characteristics of Chinese are taken into account and a knowledge representation framework based on a case frame is developed. Affirmative, negative, interrogative and elliptical sentences, etc., can be represented easily in this framework. The parsing algorithm, having no direct relation to tasks, depends only on the knowledge-representation form. Consequently, it is convenient to change the task-domain by the aid of knowledge acquisition tools. The processor can also distinguish Chinese homonymic characters.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120946895","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":"Solving the stiff problem in computer vision by trade-off optimization","authors":"Chengzhi Huang, Yanda Li, Tong Chang","doi":"10.1109/ICPR.1988.28195","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28195","url":null,"abstract":"The effect of stiffness in a general solution of the linear inverse problem is discussed, and a method is proposed to deal with this problem. It uses tradeoff by tradeoff optimization between the resolution and variance of solution to keep them both small, by applying a group of optimal weights on the singular values of the operator. The reliability of the estimated motion parameters is improved significantly.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120948554","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":"Rotation-invariant operators applied to enhancement of fingerprints","authors":"P. Danielsson, Q. Ye","doi":"10.1109/ICPR.1988.28234","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28234","url":null,"abstract":"Rotation-invariant operators of order 0 and 2 are used first to detect and then to enhance lines. The enhancement procedure, suitable for fingerprints, is based on suppression of line responses with an orientation that creates a mismatch with the locally dominating direction of the fingerprint. The rotation-invariant operators also serve as basis functions. By construction they are mutually orthogonal and by proper normalization they form an orthonormal set. At the origin any pattern a(r, phi ) can be expanded or at least approximated by such a set of basis functions.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127482501","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 of object-oriented programming as the basis for an image processing and analysis system","authors":"J. Piper, D. Rutovitz","doi":"10.1109/ICPR.1988.28427","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28427","url":null,"abstract":"The ways are explored in which object-oriented programming is well adapted to image analysis, and attempt is made to assess the implications of its use. In particular, the possible transition from C to C++ of an existing image processing system called Woolz is examined. It is concluded that the system already closely follows the object-oriented paradigm, and that an efficient implementation in the C++ language using restricted removal of interobject privacy constraints, could be achieved.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125049167","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":"Computer architectures for image analysis","authors":"S. Levialdi","doi":"10.1109/ICPR.1988.28463","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28463","url":null,"abstract":"The author reviews a number of parallel-processing projects which use processing power, memory and input/output of image data for image analysis. The systems covered include ILLIAC, CLIP, MPP, the cytocomputer, SNAP, and PAPIA and II. Issues in parallelism reviewed include types of parallelism, types of operation, complexity of processing elements, and the different paradigms of human vision and their application and implementation.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125512997","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":"Multiresolution relaxation: experiments and evaluations","authors":"Dingding Zhang, Jian Liu, Faguang Wan","doi":"10.1109/ICPR.1988.28336","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28336","url":null,"abstract":"A multiresolution relaxation method for edge detection is proposed. Using multiresolution representations of the image hierarchical representation, it is possible to change the weighted coefficients by considering the values at the high level of the pyramid as a measure of the local edge features in the image. Satisfactory detection can then be obtained at all points, and the convergence speed of the relaxation process can be improved greatly. This method also has the advantage of obtaining compact border of objects in the images.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125556291","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":"Color-based panoramic representation of outdoor environment for a mobile robot","authors":"Z. Yu, M. Asada, S. Tsuji","doi":"10.1109/ICPR.1988.28364","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28364","url":null,"abstract":"A color-based panoramic representation is presented of outdoor scenes along routes of a mobile robot. A qualitative description, which is composed of a series of significant visual events called landmarks and their ranges and their ranges of distinctiveness, is generated from it. The mobile robot builds such a map and selects landmarks autonomously in its five moves along a certain route. When the robot is given a command to go along that route, it tries to pursue the memorized route by matching the landmarks with the incoming scenes. Retinex theory is used in matching of scenes in different weather conditions.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122429131","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":"A structural approach to online Chinese character recognition","authors":"Y. J. Liu, J. Tai","doi":"10.1109/ICPR.1988.28366","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28366","url":null,"abstract":"A fuzzy attributed finite-state grammar and corresponding automation are introduced for recognizing line segments and an ordering arrangement is provided according to intrinsic structural properties of Chinese characters. Arrangement is provided. As a result, an online Chinese character recognition system has been implemented. The system consists of a small input tablet interfaced with a IBM-PC/XT/AT which can recognize about seven thousand online handwritten Chinese characters, with some constraints.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122711385","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":"Adaptive size for operators in line image processing","authors":"Herve Jarosz, J. Crettez","doi":"10.1109/ICPR.1988.28368","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28368","url":null,"abstract":"The authors apply, for each pixel, operators of varying size. These adaptive-size operators can be obtained by selecting, in each location, the size of the operator which gives the best response according to a given criterion. A method is defined for computing a set of Laplacian operators of different sizes from local bicubic approximations. These different Laplacian operators make it possible to obtain a representation of the images, based on a visual model, constituted of a stack of responses. This representation is called the Laplacian multilayer representation. With this method a good segmentation of line images was obtained. An application to the detection of the median lines of the spectrum images is presented.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122766768","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":"Knowledge-based pattern recognition: a case study in acoustic-phonetic of speech","authors":"J. Haton","doi":"10.1109/ICPR.1988.28255","DOIUrl":"https://doi.org/10.1109/ICPR.1988.28255","url":null,"abstract":"The various approaches proposed to solve the difficult problem of acoustic phonetic decoding (PD) are briefly recalled, including the hidden Markov model (HMM), which appears to be particularly efficient. It is then proposed to consider PD as a knowledge-intensive process, and the issues involved in the knowledge-based approach to this problem are identified. The APHODEX (acoustic expert) phonetic decoding system is used to illustrate this approach. Results obtained show that the knowledge acquired from expert phoneticians can substantially improve the performances of PD systems. The incorporation of this knowledge into efficient operational models such as HMMs or neural networks represents a good basis for further developments in the field.<<ETX>>","PeriodicalId":314236,"journal":{"name":"[1988 Proceedings] 9th International Conference on Pattern Recognition","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122466139","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}