摘要:

AbstractIf the multiple‐valued digital system can be extended to an ultrahigher‐valued digital system, the potential advantages of high information density and simple hardware algorithms by direct multiple‐valued coding of the processed data will be obtained. This paper presents a highly parallel ultra‐higher‐valued logic network composed of bio‐devices based on specificity of enzymes, i.e., the high‐level, multiple‐valued discrimination function. First, the multiple‐valued coding of varieties of organic molecules is presented, regarding the molecules as logic values. Then, basic bio‐devices are defined which can switch the molecular logic values. It is shown that any multiple‐valued logic function can be constructed in two‐stage structure by the proposed bio‐devices. Finally, the systematic synthesis method of the network is presented aiming at the minimization of the network. Since one of the most distinctive features of the proposed system is that there is no physical order relation among the logic values, the simplification of logic networks without a constraint due to the adjacency of the logic

ISSN:0882-1666    

DOI:10.1002/scj.4690210901

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

年代:1990

数据来源: WILEY

摘要:

AbstractThis paper proposes a neural network model, which performs deterministic, parallel pattern matching. The pattern is recognized by matching an input pattern containing noise and a template constructed through learning. In this paper, it is assumed that no feature detection has already been accomplished. We consider a circuit structure which merely compares a template with the noisy feature distribution pattern that appears at the output of the feature detector. This pattern matching method is based on our previous work using neural networks to determine the correspondence between stereo images. The input from the left eye, for example, corresponds to the feature distribution pattern, and the input from the right eye corresponds to the template. The difference in the positions of features in the template and the input pattern corresponds to the binocular parallax. The proposed model is composed of a pattern matching layer, a minimum distance detection layer (which selects the template close to the input feature distribution pattern, and feeds it back to the pattern matching layer for pattern matching) and the recognition layer which classifies the matched template. The results of our computer simulation indicated that perfect matching was achieved for inputs having feature distribution patterns corresponding to those used during learning. Since sequences of labels or character strings can be considered to be feature distribution patterns, the proposed network can be applied to a wide range of problems related to pattern matching.

ISSN:0882-1666    

DOI:10.1002/scj.4690210902

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

年代:1990

数据来源: WILEY

摘要:

AbstractIt is not easy to extract significant information from image data concerning the motion and the structure of an object, but this technique is indispensable to the future development of video coding and recognition of a moving object. The block matching method [1] is employed widely as a motion detection method in the motion‐compensated interframe coding. However, it has a problem in that the motion is estimated by the prediction error power minimization condition, which may lead to an instability in accurate motion detection. This paper proposes a new block matching method that has the following features: the motion is estimated and detected by stepwise switching from larger block size to smaller block size; by this scheme, the motion detection accuracy and the spatial resolution can be improved, and the processing complexity can also be reduced without degrading the detection accurac

ISSN:0882-1666    

DOI:10.1002/scj.4690210903

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

年代:1990

数据来源: WILEY

摘要:

AbstractOne of the serious problems in developing an optical character reader (OCR) is designing a dictionary of handprinted characters which requires a tremendous amount of character data for training. This paper considers training by artificially distorted characters instead of handprinted ones in the design of a dictionary. The feasibility and the usefulness of the scheme are examined. In the experiment, 26 alphabetical characters are employed. The characteristic loci proposed by Glucksman are used as the features, and the nearest‐neighbor method is used in the classification. The recognition result of test data indicated that the dictionary designed by artificially distorted characters has almost the same performance as the dictionary designed by handprinted characters. The correct recognition rates are 98.6 percent for the former and 98.9 percent for the latter. By the training where a part of the handprinted characters are replaced by the artificially distorted characters, a performance exceeding that of the training using only handprinted characters is realized, with the correct recognition rate of 99.2 percent. Thus, it is verified that the proposed method is a useful substitute to the method by collecting handprinted characters. It is shown also that by observing the distorted characters in the feature space, the stability of the features against distortion can be evaluate

ISSN:0882-1666    

DOI:10.1002/scj.4690210904

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

年代:1990

数据来源: WILEY

摘要:

AbstractThis paper describes a construction of a new CAI model for language education employing a machine translation system. The model includes the machine translation and the error correction mechanisms. By the machine translation mechanism, the system can receive the input from the student and return the translation or instruct the syntax. When an incorrect sentence is given from the student, the machine utilizes the error‐correction mechanism to analyze the sentence and instruct how the error is produced. The curriculum for the CAI system is placed outside the system as a dedicated text, and the user is free to choose the test. Based on such a model, the authors have developed a CAI system (English CAI) to teach English to the junior high school student. The system is actually operated in an educational situation. A field test is demonstrated in which the mechanisms for machine translation and error‐correction functioned effectively as a means to answer questions, providing a good assistance to learn

ISSN:0882-1666    

DOI:10.1002/scj.4690210905

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

年代:1990

数据来源: WILEY

摘要:

AbstractAs an example of character recognition from overlapping data, this paper presents the recognition of Ishihara's color vision test chart, where a color character composed of color dots is embedded in a background composed of color dots. The histogram is constructed on the normalized tri‐color coordinate, and the representative color is determined as the maximal point of the histogram. The distance pattern is constructed based on the representative colors, and the shape skeleton is extracted by the DP matching between the distance pattern and the category dictionary. The line width and the final position are determined by an examination based on the variance criterion. It is shown that the DP matching is useful in the hypothesis testing for the object, where both the background and the character are multivalued color texture

ISSN:0882-1666    

DOI:10.1002/scj.4690210906

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

年代:1990

数据来源: WILEY

摘要:

AbstractPhoneme or syllable spotting if reliably achieved provides a good solution to the spoken word and/or continuous speech recognition problem. We would like to extend the encouraging performance of TDNN to word/continuous speech recognition. We show techniques for spotting Japanese phonemes/CV‐syllables in input speech based on TDNNs. We constructed the TDNN which can discriminate a single phoneme or CV‐syllable. Phoneme and syllable spotting experiments show excellent results, including phoneme and syllable spotting rates of 92 percent and 96.7 percent, respectively. These spotting techniques are proved to be a step toward continuous speech recognit

ISSN:0882-1666    

DOI:10.1002/scj.4690210907

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

年代:1990

数据来源: WILEY

摘要:

AbstractThis paper proposes a method of constructing a multilayered neural network, using the multiple logistic model (MLM). The model is a nonlinear multivariate analysis considering the output logistic function of each unit, which is used in the back‐propagation method (BP). The idea can be applied directly to the determination of the multilayered neural network structure. The model can also be utilized as a systematic method to introduce such information as pattern distribution into the neural network structure. Considering the speaker‐independent vowel recognition as the problem, this paper compares the results by the proposed method (MLM), the construction by the linear multiple regression analysis (MRA), the learning by BP with the weight being defined at random as the initial value, and the learning by BP with the initial weight determined by MLM or MRA. It is seen as a result that the recognition rate is the best when BP is applied after introducing the speaker distribution information by the proposed method. It is seen also that the computation time is reduced compared with the BP, with the initial weight being defined at ran

ISSN:0882-1666    

DOI:10.1002/scj.4690210908

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

年代:1990

数据来源: WILEY

摘要:

AbstractThis paper describes a new syllable recognition method using the integrated neural network (INN). In this method, the recognition targets are partitioned into several groups. INN consists of a control network and several subnetworks. The control network identifies to which group the input speech belongs, and the subnetworks recognize the syllables within each group. Using INN, even if the recognition scope is large, or even if there are few training samples, the network can recognize syllables with higher recognition accuracy than conventional back‐propagation networks. Furthermore, new vocabulary entries can easily be added to an INN by adding new subnetworks corresponding to the new groups. Using the grouping method based on the manner of the articulation of consonants, the recognition accuracy is 96.2 percent for INN, compared with 95.8 percent for the conventional network architecture. This higher accuracy is obtained with 40 percent lower training costs. Using the grouping method based on the hidden layer activation patterns of a network which has learned to recognize all syllables, the accuracy is 96.0 percen

ISSN:0882-1666    

DOI:10.1002/scj.4690210909

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

年代:1990

数据来源: WILEY

摘要:

AbstractA new defect detection algorithm that compares grayscale images of actual patterns and an automatic visual inspection system implementing this algorithm have been developed. The objective is to detect defects reliably down to 0.3 μm in LSI photoresist patterns on a silicon wafer. To detect defects reliably while remaining uninfluenced by tiny differences between two images of satisfactory patterns, the images are matched in local windows by perturbing one image in thex‐yplane and in the brightness direction against the other image. The resulting unmatched regions are recognized as defects. One unique feature of the algorithm is its utilization of polarity changes in the subtracted images during the perturbation for deleting tiny differences between two images. All processing can be done in real time by local, one‐pass operators. The developed automatic visual inspection system has achieved a 100 percent detection rate for defects down to 0.

ISSN:0882-1666    

DOI:10.1002/scj.4690210910

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

年代:1990

数据来源: WILEY