Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629452
L. Hess, B. Mayoh
This paper, describing a computer graphics tool for clinical vision, is the result of an effort to find out the potential of and possible improvements to a tool to help opticians. The software prototype, the computer binocular kit, generates customized stereo pairs. The results of this collaborative research project show that the eye cooperation ability of a patient can be trained by exercising the eye muscles with the Binocular Kit. However, we want to leave open the possibility of combining the data of patient's eye convergence with other measurements of perceived sharpness and disparity of stereo pairs.
{"title":"Computer binocular kit: the return","authors":"L. Hess, B. Mayoh","doi":"10.1109/CYBVIS.1996.629452","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629452","url":null,"abstract":"This paper, describing a computer graphics tool for clinical vision, is the result of an effort to find out the potential of and possible improvements to a tool to help opticians. The software prototype, the computer binocular kit, generates customized stereo pairs. The results of this collaborative research project show that the eye cooperation ability of a patient can be trained by exercising the eye muscles with the Binocular Kit. However, we want to leave open the possibility of combining the data of patient's eye convergence with other measurements of perceived sharpness and disparity of stereo pairs.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131175026","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629442
A.M.C. Machado, M. Campos
The development of adaptive systems must face the problem of recognition as a synergy of learning and knowledge. This paper presents a method for constructing influence diagrams from backpropagation neural networks, as a way of combining the main advantages of these methodologies. The basic concepts of influence diagrams and neural networks are discussed as a brief review. An algorithm to extract the conditional probabilities of the network is presented and illustrated by three pattern recognition examples. Although much of the a priori information from the sample set is lost during the training phase of the network, an influence diagram that behaves as the original knowledge source can be constructed.
{"title":"A connectionist approach for building influence diagrams","authors":"A.M.C. Machado, M. Campos","doi":"10.1109/CYBVIS.1996.629442","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629442","url":null,"abstract":"The development of adaptive systems must face the problem of recognition as a synergy of learning and knowledge. This paper presents a method for constructing influence diagrams from backpropagation neural networks, as a way of combining the main advantages of these methodologies. The basic concepts of influence diagrams and neural networks are discussed as a brief review. An algorithm to extract the conditional probabilities of the network is presented and illustrated by three pattern recognition examples. Although much of the a priori information from the sample set is lost during the training phase of the network, an influence diagram that behaves as the original knowledge source can be constructed.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134516959","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629435
J. Raynauld
The fact that our senses adapt is one of the most important characteristics of our sensory system. Since ambient light varies over such a large dynamic range, adaptation is an important aspect of vision in all species. In the vertebrate retina, Weber-Fechner adaptation can be observed at the level of the photoreceptor itself. Using the ergodicity theorem from statistical mechanics, it has been possible to analyze the adaptation properties of the compartment model of Lamb et al. (1981) and to predict the value of Io, the background intensity at which the sensitivity is reduced by one-half. It is simply equal to N, the number of compartments in the outer segment of rod and cones, divided by T, the time constant of biochemical process limiting the recovery of the response. For the cones, the number of compartments is set equal to the number of folds (disks) in the outer segment, for the rods, an empirical rule has been found. The decay of the photocurrent after a small flash has been used to estimate the time constant of the limiting process. The predictions for Io of rods and cones are generally in good agreement with experimental values obtained over the years.
{"title":"The adaptation properties of a compartment system","authors":"J. Raynauld","doi":"10.1109/CYBVIS.1996.629435","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629435","url":null,"abstract":"The fact that our senses adapt is one of the most important characteristics of our sensory system. Since ambient light varies over such a large dynamic range, adaptation is an important aspect of vision in all species. In the vertebrate retina, Weber-Fechner adaptation can be observed at the level of the photoreceptor itself. Using the ergodicity theorem from statistical mechanics, it has been possible to analyze the adaptation properties of the compartment model of Lamb et al. (1981) and to predict the value of Io, the background intensity at which the sensitivity is reduced by one-half. It is simply equal to N, the number of compartments in the outer segment of rod and cones, divided by T, the time constant of biochemical process limiting the recovery of the response. For the cones, the number of compartments is set equal to the number of folds (disks) in the outer segment, for the rods, an empirical rule has been found. The decay of the photocurrent after a small flash has been used to estimate the time constant of the limiting process. The predictions for Io of rods and cones are generally in good agreement with experimental values obtained over the years.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"471 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133405521","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629470
A. Araújo, R.M. Hadad
This work reports and illustrates the application of optimal filtering to enhance sketch contours on infrared photographs of wood paintings. Three approaches to edge detection by using optimal filtering-symmetric exponential filter of an infinitely large window size-were tested. Then one method was chosen to have a fine tuning of its parameters.
{"title":"Enhancement of sketch contours on paintings infrared photographs by optimal filtering","authors":"A. Araújo, R.M. Hadad","doi":"10.1109/CYBVIS.1996.629470","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629470","url":null,"abstract":"This work reports and illustrates the application of optimal filtering to enhance sketch contours on infrared photographs of wood paintings. Three approaches to edge detection by using optimal filtering-symmetric exponential filter of an infinitely large window size-were tested. Then one method was chosen to have a fine tuning of its parameters.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131769182","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629439
R. M. Cesar, R. C. Coelho, L. da Fontoura Costa
Experiments on the classification of neural cells by means of 2D shape analysis and pattern recognition procedures are described. Two types of the cat's retinal ganglion cells (/spl alpha/ and /spl beta/ cells) are characterized by a set of morphological and specific features, which are analyzed by feature-ordering techniques. The shape features include the fractal dimension, the normalized multiscale bending energy as well as standard measures such as the size of the soma and of the dendritic arborization. Several classification experiments using two statistical classifiers (k-nearest neighbor and maximum likelihood) were carried out based on the information provided by the a priori feature-ordering tests. Encouraging recognition results are reported.
{"title":"Automatic classification of retinal ganglion cells","authors":"R. M. Cesar, R. C. Coelho, L. da Fontoura Costa","doi":"10.1109/CYBVIS.1996.629439","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629439","url":null,"abstract":"Experiments on the classification of neural cells by means of 2D shape analysis and pattern recognition procedures are described. Two types of the cat's retinal ganglion cells (/spl alpha/ and /spl beta/ cells) are characterized by a set of morphological and specific features, which are analyzed by feature-ordering techniques. The shape features include the fractal dimension, the normalized multiscale bending energy as well as standard measures such as the size of the soma and of the dendritic arborization. Several classification experiments using two statistical classifiers (k-nearest neighbor and maximum likelihood) were carried out based on the information provided by the a priori feature-ordering tests. Encouraging recognition results are reported.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122063938","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629451
E.L.L. Rodrigues, V. O. Roda
This paper presents a real time architecture made of systolic modules for applications in the "early processing" level of computer vision systems. The purpose of the architecture is to determine dynamically the threshold by local edge evaluation. Systolic modules are proposed for the edge detection, for finding the histogram and for the evaluation of the edge quality which is used to determine dynamically the threshold.
{"title":"A systolic array approach to determine the image threshold by local edge evaluation","authors":"E.L.L. Rodrigues, V. O. Roda","doi":"10.1109/CYBVIS.1996.629451","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629451","url":null,"abstract":"This paper presents a real time architecture made of systolic modules for applications in the \"early processing\" level of computer vision systems. The purpose of the architecture is to determine dynamically the threshold by local edge evaluation. Systolic modules are proposed for the edge detection, for finding the histogram and for the evaluation of the edge quality which is used to determine dynamically the threshold.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812018","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629459
S. Fukusima
Two experiments were carried out to investigate the horizontal-vertical illusion using the psychophysical method of adjustment and the double staircase method. Results from both experiments indicated that the eye movement and the stimulus time exposure can affect the magnitude of the illusion, but they cannot affect the illusion pattern in function of the location of the stimuli in the visual fields and of the location of vertical line on the horizontal line. It is suggested that size perception involves specialization of the right and the left brain.
{"title":"What does the horizontal-vertical illusion show us about size perception?","authors":"S. Fukusima","doi":"10.1109/CYBVIS.1996.629459","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629459","url":null,"abstract":"Two experiments were carried out to investigate the horizontal-vertical illusion using the psychophysical method of adjustment and the double staircase method. Results from both experiments indicated that the eye movement and the stimulus time exposure can affect the magnitude of the illusion, but they cannot affect the illusion pattern in function of the location of the stimuli in the visual fields and of the location of vertical line on the horizontal line. It is suggested that size perception involves specialization of the right and the left brain.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127729651","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629432
J. Eklundh, P. Nordlund, T. Uhlin
We stress a systems approach for research in active vision. We also argue that design and analysis of seeing agents should be accompanied by experiments, requiring implementations, i.e. a constructive approach. In particular, we discuss two issues that we have worked with: use and integration of multiple cues and attention.
{"title":"Some problems in active vision","authors":"J. Eklundh, P. Nordlund, T. Uhlin","doi":"10.1109/CYBVIS.1996.629432","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629432","url":null,"abstract":"We stress a systems approach for research in active vision. We also argue that design and analysis of seeing agents should be accompanied by experiments, requiring implementations, i.e. a constructive approach. In particular, we discuss two issues that we have worked with: use and integration of multiple cues and attention.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117170869","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629456
V. Pessoa, M. Tavares, C. Tomaz
Research carried out by various investigators has indicated significant differences in color vision perception between Old World and New World monkeys. While the former seem evenly trichromatic, the New World monkeys show color vision polymorphism with at least 6 different phenotypes and an absence of trichromacy amongst the males of the Saimiri and Callithrix genera. We summarize the studies of color vision in New World monkeys, including our own data, showing inconsistencies in the outcomes of these experiments, the interspecific differences and the numerous non-tested species. The results are discussed according to the neurobiological hypothesis of male dichromatism in New World monkeys, to the hypothesis that the major function of color vision in primates is its role as an adaptation to feeding ecology as well as to aspects regarding primates evolution. In conclusion, the available data points to the necessity of further work on this problem including behavioral, electrophysiological and generical approaches-before definitive proofs are possible.
{"title":"Color vision in New World monkeys: di- and/or trichromaticity?","authors":"V. Pessoa, M. Tavares, C. Tomaz","doi":"10.1109/CYBVIS.1996.629456","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629456","url":null,"abstract":"Research carried out by various investigators has indicated significant differences in color vision perception between Old World and New World monkeys. While the former seem evenly trichromatic, the New World monkeys show color vision polymorphism with at least 6 different phenotypes and an absence of trichromacy amongst the males of the Saimiri and Callithrix genera. We summarize the studies of color vision in New World monkeys, including our own data, showing inconsistencies in the outcomes of these experiments, the interspecific differences and the numerous non-tested species. The results are discussed according to the neurobiological hypothesis of male dichromatism in New World monkeys, to the hypothesis that the major function of color vision in primates is its role as an adaptation to feeding ecology as well as to aspects regarding primates evolution. In conclusion, the available data points to the necessity of further work on this problem including behavioral, electrophysiological and generical approaches-before definitive proofs are possible.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115893412","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}
Pub Date : 1996-12-09DOI: 10.1109/CYBVIS.1996.629437
G. Perelmuter, Paula Pereira, M. Vellasco, M. Pacheco, E. Carrera
This article presents the structure of an "intelligent classifier" composed of three modules: 1) the preprocessor, responsible for the transformation of the raw image; 2) the characteristics extractor, implemented by a genetic algorithm, which is responsible for the selection of the most relevant coefficients; and 3) the classifier, implemented by a neural network. Generic algorithms have been used as a search technique for large sets of data and neural networks, due to their ability to extract information from complex sets of data, have been largely applied in computer vision for pattern classification. The complete image classification system is invariant to translation rotation and sizing of the analysed object.
{"title":"Classification of bidimensional images using artificial intelligence techniques","authors":"G. Perelmuter, Paula Pereira, M. Vellasco, M. Pacheco, E. Carrera","doi":"10.1109/CYBVIS.1996.629437","DOIUrl":"https://doi.org/10.1109/CYBVIS.1996.629437","url":null,"abstract":"This article presents the structure of an \"intelligent classifier\" composed of three modules: 1) the preprocessor, responsible for the transformation of the raw image; 2) the characteristics extractor, implemented by a genetic algorithm, which is responsible for the selection of the most relevant coefficients; and 3) the classifier, implemented by a neural network. Generic algorithms have been used as a search technique for large sets of data and neural networks, due to their ability to extract information from complex sets of data, have been largely applied in computer vision for pattern classification. The complete image classification system is invariant to translation rotation and sizing of the analysed object.","PeriodicalId":103287,"journal":{"name":"Proceedings II Workshop on Cybernetic Vision","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116467008","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：