摘要:

AbstractA number of methods for constructing fault‐tolerant parallel processors using one dimensional linear cellular automaton model have already been proposed. When the methods are used, however, a large amount of hardware is required to realize the connections among processing elements for executing a given algorithm, and for reconfiguring the processor quickly when faults occur in the processor. Moreover, these processors require long communication distances between processing elements so that the method is difficult to be used for large scale processors. In this paper, a method for constructing parallel processors based on a two dimensional cellular automaton model is proposed to alleviate the problems. In the processor based on this model, processing elements are connected in two dimension and the average communication distance can be reduced and a higher fault‐tolerance due to the increase in the number of communication paths from 2 t

ISSN:0882-1666    

DOI:10.1002/scj.4690250601

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractVarious methods of generating dataflow diagrams use an algebraic transformation system for a given input‐output relationship. These methods require mutual transformations between the input‐output relationship and algebraic expressions, and also a consistency check between the generated dataflow diagram and input‐output relationship. This paper proposes a deterministic algorithm that uniquely generates a unique dataflow diagram with a minimal number of processes from a given input‐output relat

ISSN:0882-1666    

DOI:10.1002/scj.4690250602

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractThis paper discusses the complexity from the viewpoint of the number of circuit elements for the slice functions and the homogeneous function, which belong to the class of monotonic logic functions. The slice function is one of those functions in which the circuit complexity is almost equal to the monotonic circuit complexity.Then‐inputk‐homogeneous function is considered as the first step, and it is shown that there exists a function with thek‐slice monotonic circuit complexity Ω(nCk/lognCk)and the monotonic circuit complexity ofu(>k) slice isO(nlogn). This property has already been shown by Wegener for the case of thek‐slice with the monotonic circuit complexity Ω(n‐1Ck‐1/logn‐1Ck‐1). The result in this paper is an improvement of his result, and is the optimal whenkis a constant.As the next step, a homogeneous function is shown where the monotonic circuit complexity is almost equal to the circuit complexity. As in the case of the slice function, if the lower bound ω(n(logn)2) for the monotonic circuit complexity for then‐input homogeneous function is shown, the same lower bound is shown for th

ISSN:0882-1666    

DOI:10.1002/scj.4690250603

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractFeed‐forward neural networks have been used for pattern recognition, because they have an ability to estimatea posterioriprobability. This paper investigates the ability to estimate thea posterioriprobability by using one‐dimensional Gaussian distributions, uniform distributions, their mixed distributions and real speech data, and applies the networks to speech recognition. Furthermore, the ability to estimate a probability density function of artificial data by using a vector quantization technique and neural networks and also to apply them to speech recognition also are investigated. Feed‐forward neural networks, radial basis function networks (RBF), Gaussian mixed distributions and multitemplate methods for speech recognition are compared. It is concluded that the vector quantization‐based RBF is the best in p

ISSN:0882-1666    

DOI:10.1002/scj.4690250604

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractMathematical morphology is one of the data processing methods that is extremely useful for image processing and has many applications, such as, noise elimination, shape description, texture analysis, and so on. The mathematical base of morphological processing is dilation and erosion which are described by set analysis and can be expressed in logical AND, OR notation.Localized parallel processing including morphological processing is not suitable to Neumann architecture because of the memory access bottleneck which makes it hard to achieve the high throughout data processing required in applications such as video image processing. Also the cytocomputer aimed at fast image processing has a drawback in that it can handle only very small structuring elements.In this paper, first, an algorithm is presented which accelerates morphological image processing. Next, the algorithm to design a specialized hardware which processes the real‐time video image is implemented and finally, an application of this specialized hardware for medical use is describe

ISSN:0882-1666    

DOI:10.1002/scj.4690250605

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractThis paper recovers 3D shapes from contours for graphics display in a 3D virtual environment. In this method, a continuous sequence of images is taken as an object rotates, and smooth convex shape is estimated instantaneously from its contour and contour movement. Shapes also are analyzed that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that is not exposed as contour yields a non‐smoothness in the tracked contour movement. An unknown region is obtained for further investigation using other visual cues. The entire process from silhouettes to a 3D model is based on local computation; which is promising for producing shapes in real time. The direct goal is to establish 3D graphics models of human faces for the growing needs of visual communications. Some good results have been obtaine

ISSN:0882-1666    

DOI:10.1002/scj.4690250606

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractIn recent years, attention has been given to coding based on the structurally extracted component and the three dimensional object model. However, it has a problem in that the content of the processing and the required model are fairly complex compared to the conventional waveform coding.From such a viewpoint, the authors considered the one‐dimensionalmultipulse model, which was proposed as an analysis/synthesis technique for speech, and have been investigating the method using the model which can easily extract the structure of the image and provide the coding.In this paper, the multipulse model is regarded as a stochastic model. A method is proposed, where the number of pulses required to represent the features of the image is determined automatically using Akaike's information criterion and a similar criterion (called modified AIC).As the first step, the modified AIC for the multipulse model is derived, and the sequential computation procedure is shown. Then the relation between the penalty coefficient of the modified AIC and the optimal number of pulses is described, and a method is shown based on that result where the traditional information criterion is utilized selectively based on the constraint for the compression ratio of the number of pulses.Finally, the modified AIC for the multipulse model is applied to the hierarchical coding from the two‐tone image to the gray‐level image, and the usefulness is demonstrated. It is expected that the proposed method will be applied to the image coding, image feature extraction and speech feature extra

ISSN:0882-1666    

DOI:10.1002/scj.4690250607

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractA neural network with maximum detectors divides a space which hasn‐dimensionsRninto piece‐wise‐linear regions. However, there have been very limited theoretical researches concerning what kind of piecewise‐linear region divisions can be realized by a neural network, that is, concerning the formation capability of piecewise‐linear discriminate regions by a neural network.In this paper, this problem is considered theoretically. The concept of ak‐dividual region is introduced and then it is proved that a division can be realized by a piecewise‐linear machine if and only if it

ISSN:0882-1666    

DOI:10.1002/scj.4690250608

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractThis paper proposes an image magnification method “IM‐GPDCT,” which is an iterative application of the Gerchberg‐Papoulis (GP) algorithm with the discrete cosine transform (DCT), and its performance is evaluated. Conventional image magnification by interpolation has a problem in that degradation of image quality is inevitable since essentially it is impossible to restore the spatial high‐frequency components which are lost in the observation process. For this point, IM‐GPDCT improves image quality of a magnified image by utilizing a concept to restore the spatial high‐frequency components which are lost in the observation.IM‐GPDCT uses the GP algorithm as the basic principle for extending the frequency band. The spatial high‐frequency components are restored during the forward and inverse iterative transform process for the image by DCT, using two constraints that the spatial extent of an image is finite, and correct information is already known for the low‐frequency components. The proposed method is compared to three conventional interpolation methods from the viewpoints of a restoration error and image quality. Restoration error performance results show that IM‐GPDCT outperforms the interpolation methods from the viewpoint of the restoration error. Simulation results show also that the presented method improves the image quality of the magnified image by obtaining image sharpness, nonjagged edges and reproduction of

ISSN:0882-1666    

DOI:10.1002/scj.4690250609

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY

摘要:

AbstractThe prototype sign language translation system described herein interprets Japanese sign language to verbal Japanese language. Since sign language has a unique morphology and syntax, the sign language translation system requires linguistic translation after recognition of the input symbols. One of the main difficulties in translation is a result of the insufficiency of syntactic markers in the input information.In Japanese sign language, input is represented as a sequence of important words. In our method, semantic dependency analysis based on case frame grammar is carried out to complement the lack of information such as postpositions. Then, rule‐based rephrasing is executed to obtain natural verbal language. This scheme contributes both flexibility and ease of maintenance to the translation system. A prototype sign language translation system was implemented and tested using 123 sentences extracted from a sign language textbook. Experimental results indicate that 76 percent of the sentences can be translated correctly if they have no recognition error in input sentence. However, if a recognition error occurs, the experiment indicates that the translation will become highly ambiguous. Therefore, the capability for rejecting incorrect sentences is very important, along with the capability for translating correct input sentences. Future issues include incorporation of unused information, such as facial expression, spatial information and contexts in sign language to improve translation accurac

ISSN:0882-1666    

DOI:10.1002/scj.4690250610

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1994

数据来源: WILEY