SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218)

14-14 Oct. 1998

Go

Filter Results

Displaying Results 1 - 25 of 147
  • 1998 IEEE International Conference on Systems, Man, and Cybernetics

    Publication Year: 1998, Page(s):0_2 - 0_56
    Request permission for reuse | PDF file iconPDF (4146 KB)
    Freely Available from IEEE
  • Application of machine speech recognition for real-time estimation of human cognitive process at man-machine interface

    Publication Year: 1998, Page(s):4127 - 4132 vol.5
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (667 KB)

    A real-time cognitive process estimation system has been developed, by employing machine speech recognition to estimate operators' thinking processes. The developed system consists of a user-interface, speech recognition subsystem, real-time cognitive process estimator, and nuclear power plant (NPP) simulator. The major point of the real-time estimator is that it equipped with the causal relation ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Agent navigation under linguistic instructions of a route using contextual information

    Publication Year: 1998, Page(s):4133 - 4138 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (689 KB)

    We propose a route planning algorithm for agent navigation under linguistic instructions of a route, aiming at man-agent flexible communication by a natural language. Instructions given to the agent describe a route in terms of landmarks like intersections, for example, "turn right at the second intersection". The contextual information in instructions of a route provides some constraints on the i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhancing speech recognition and speech understanding systems through non-phonetic cues

    Publication Year: 1998, Page(s):4139 - 4147 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (586 KB)

    Theoretical and practical techniques for the automatic extraction, representation and manipulation of information supplied by the body movements of a speaker are discussed. Since speech production and facial expressions have been shown to exhibit a synchronous relationship, optical information obtained from a camera trained on the speaker's face and body can prove useful in both correlating and di... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hybrid speech recognition model based on HMM and fuzzy PPM

    Publication Year: 1998, Page(s):4148 - 4153 vol.5
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    Hidden Markov model (HMM) is a robust statistical methodology for automatic speech recognition. It has been tested in a wide range of applications. A prediction approach traditionally applied for the text compression and coding. Prediction by partial matching (PPM) which is a finite-context statistical modeling technique and can predict the next characters based on the context has shown a great po... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech recognition based on lateral inhibition network auditory model

    Publication Year: 1998, Page(s):4154 - 4159 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (498 KB)

    This paper studies the robust speech recognition based on auditory model. The spectrum of auditory representation shows that the lateral inhibition network (LIN) can shape the spatial input patterns and highlight their edges and peaks. Also, it can make the speech recognition to be more robust to noise than the LPC cepstral (LPC-CEP) approach. Some preliminary experiments including speaker depende... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy-rough neural networks for vowel classification

    Publication Year: 1998, Page(s):4160 - 4165 vol.5
    Cited by:  Papers (7)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (809 KB)

    In many real life applications two patterns from the same cluster belong to different classes, and hence, classification based on mere similarity property is inadequate. This problem arises because the available features are not sufficient to discriminate the classes. It implies that the fuzzy clusters generated by the input features have rough uncertainty. This paper proposes a fuzzy-rough set ba... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible and robust matching scheme for character recognition to cope with variations in spatial interrelation among structural features

    Publication Year: 1998, Page(s):4166 - 4171 vol.5
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (546 KB)

    This paper presents a structural approach for classification of multi-font machine-printed or handwritten character samples. The issue of how to cope with variations that are found in the relative location of individual strokes of a character in the presence of variations in shape, size, orientation and spacing of the involved strokes is described in detail. The approach yields results closer to h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improvements on handwritten digit recognition by cooperation of modular neural networks

    Publication Year: 1998, Page(s):4172 - 4177 vol.5
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    In this paper modular neural networks are used to improve handwritten digit recognition. To evaluate the performance of modular networks, a comparison is made with a global neural network, on the same database. Two basic kind of modular networks are considered: 1) seven expert modular networks in which five of them are provided for digits 0, 1, 2, 5, 6, 7 and the rest for the pair of digits 3-8 an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new approach for the failure mode analysis of optical character recognition algorithms

    Publication Year: 1998, Page(s):4178 - 4183 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (525 KB)

    Concerns the imprecise method of OCR algorithm development and improvement. While trial-and-error techniques must be employed, the evaluation of the failed attempts is the most crucial, tedious, and error prone task. The paper presents a precise and efficient solution to this problem. The overlooked cause of the problem stems from the passive nature of the analysis performed. The proposed approach... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten character recognition by contour sequence moments and neural network

    Publication Year: 1998, Page(s):4184 - 4188 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (334 KB)

    Contour sequence moments (CSM) have been used in the classification of four closed planar shapes. Gupta et al. described a neural network approach for the classification of four closed planar shapes using a contour sequence. In this paper, a backpropagation neural network is used in the recognition of handwritten numerals (from 0 to 9) using contour sequence moments. Experimental results indicate ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A recognition-based Arabic optical character recognition system

    Publication Year: 1998, Page(s):4189 - 4194 vol.5
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (521 KB)

    Optical character recognition systems improve human-machine interaction and are widely used in many government and commercial departments. After forty years of intensive research, OCR systems for most scripts are well developed. However, not for Arabic script. Since Arabic is a popular script, Arabic OCR systems should have great commercial value. Thus a recognition-based Arabic OCR system is prop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using confusing characters to improve character recognition rate

    Publication Year: 1998, Page(s):4195 - 4200 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (575 KB)

    This paper proposes a confusion set analysis approach to increasing character recognition rate. In the training phase, top five candidates are outputted from an OCR system. Each candidate is assigned a weight in reversed-rank. If the reversed-rank sum of an output candidate is greater than a threshold, the input character is stored in the confusion set of the output candidate. In the recognition p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature selection for handwritten Chinese character recognition based on genetic algorithms

    Publication Year: 1998, Page(s):4201 - 4206 vol.5
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (402 KB)

    Feature selection is of great importance in recognition system design because it directly affects the overall performance of the recognition system. Feature selection can be considered as a problem of global combinatorial optimization. It is a very time-consuming task to search the most suitable features amongst a huge number of possible feature combinations, therefore, an effective and efficient ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contextual stochastic model for structural patterns

    Publication Year: 1998, Page(s):4207 - 4212 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (346 KB)

    The theory of contextual stochastic modeling of structurally complex and variant patterns like handwritten Chinese characters is presented. The key lies in capturing the contextual information of the strokes in the character image which is segmented into regions systematically. A model for a character captures the region-region and region-pixel stochastic relationship. An unknown image is recogniz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An extension of a fuzzy substroke extractor

    Publication Year: 1998, Page(s):4213 - 4216 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    In employing a structural approach to recognize handwritten Chinese characters (HCC), substroke is usually chosen as a feature set. Various types of ambiguities may arise during the substroke extraction. A fuzzy substroke extractor was previously (1990) proposed by the authors to handle a number of ambiguities caused by substroke touchings. The extractor then made use of the scoring information on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ambiguity handling of similar categories in handwritten Chinese character recognition

    Publication Year: 1998, Page(s):4217 - 4221 vol.5
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (265 KB)

    Chinese characters consist of thousands of categories, some of which have very similar structural characteristics. Ambiguity in recognition may thus arise. The authors previously (1990) proposed a technique for recognizing characters off-line based on their structural characteristics. Each input character is subject to various alternatives in stroke segmentation, and for each resulting stroke set,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiments on the use of corpus-based word BI-gram in Chinese word segmentation

    Publication Year: 1998, Page(s):4222 - 4227 vol.5
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    The first step of Chinese language processing is to segment a Chinese sentence into a sequence of words due to the fact that there is no original separation between adjacent words. An efficient corpus-based statistical method is adopted here to address such a problem. In this paper, some word BI-gram statistical measures derived from corpus are employed to remove the segmentation ambiguities. To s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neocognitron based handwriting recognition system performance tuning using genetic algorithm

    Publication Year: 1998, Page(s):4228 - 4233 vol.5
    Cited by:  Papers (5)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    Neural networks have been used to recognize handwritten characters such as Chinese, English or numerals. But their performance, i.e., the recognition rate, depends on a number of factors which may include the network architecture, feature selection, network parameter setting, learning strategy, learning sample selection, test pattern preprocessing, etc. These factors are important to network engin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neurofuzzy classification network and its application

    Publication Year: 1998, Page(s):4234 - 4239 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (551 KB)

    An important element of the automatic machining process control function is the online monitoring of cutting tool wear and fracture mechanisms. The paper presents an intelligent tool condition monitoring system. Cutting tool condition monitoring is a very complex process hence sensor fusion techniques and artificial intelligence based signal processing algorithms are employed. The tool condition m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Illumination invariant face recognition

    Publication Year: 1998, Page(s):4240 - 4245 vol.5
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (646 KB)

    Few of the face recognition methods reported in the literature are capable of recognising faces under varying illumination conditions. The paper discusses a method which can achieve a higher recognition rate than those obtained for existing methods. The novelty of this new method is the use of an embossing technique to process a face image before presenting it to a standard face recognition system... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A first approach to tactile texture recognition

    Publication Year: 1998, Page(s):4246 - 4250 vol.5
    Cited by:  Papers (22)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (544 KB)

    Tactile texture recognition seems to be a very important research area with various interesting applications which include medical, geological and autonomous mobile robotics; despite the great amount of tasks that biological beings solve using the sense of touch, not much work is done in this area (except for pressure-related sensing), and there are only a few papers in literature that uses dynami... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Defect detection in indirect layered manufacturing

    Publication Year: 1998, Page(s):4251 - 4256 vol.5
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (768 KB)

    Direct layered manufacturing (LM) is an additive manufacturing process where part is built layer by layer based on its CAD file. Indirect LM is a process where mold for a part is built by direct LM process. In this work we demonstrate a machine vision setup for surface voids detection which can be used for surface quality inspection of parts built by indirect LM and certain direct LM techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Assessing the robustness of neural network classifiers

    Publication Year: 1998, Page(s):4257 - 4263 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (725 KB)

    A preliminary report on the first phase of a multiyear experiment designed to assess the robustness of neural network classifiers compared to human experts involving the classification of terrain features is presented and discussed. The experiment includes a definition of the problem, description of the terrain data sets, preprocessing of the imagery, a variable reduction scheme involving genetic ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A variation and distortion tolerant structural pre-classifier for hierarchical character recognition

    Publication Year: 1998, Page(s):4264 - 4267 vol.5
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (276 KB)

    This paper presents a structural pre-classification approach to reduce the number of class models to be compared with a given sample during the main classification stage. This helps to increase the overall classification speed and to improve the recognition accuracy. The approach is based on preparing high-level coarse shape models of character classes permitting similar character-classes to merge... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.