Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture

Kojima, Yoshiyuki; Yamamoto, Hiroyuki; Kohda, Takehisa; Sakaue, S.; Maruno, S.; Shimeki, Y.; Kawakami, Kazuya; Mizutani, Mitsue

doi:10.1109/ijcnn.1993.714153

Cited by 5 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a small-sized input array, Nakanishi and Fukui (1993) propose a multilayered ANN using hierarchical feature types and their locations for training and recognition. Kojima et al (1993) describe a handwritten numeric character recognition system, the main classifier of which is a fuzzy vector quantizer, involving an improved version of the vector quantization algorithm. Features are extracted from the pre-processed input pattern, and used for training the network.…”

Section: Anns and Pattern Recognitionmentioning

confidence: 99%

Encoded pattern classification using constructive learning algorithms based on learning vector quantization

Murthy¹,

Venkatesh²

1998

Neural Networks

View full text Add to dashboard Cite

A novel encoding technique is proposed for the recognition of patterns using four different techniques for training artificial neural networks (ANNs) of the Kohonen type. Each template or model pattern is overlaid on a radial grid of appropriate size, and converted to a two-dimensional feature array which then acts as the training input to the ANN. The first technique employs Kohonen's self-organizing network, each neuron of which is assigned, after training, the label of the model pattern. It is found that a graphical plot of the labels of the neurons exhibits clusters (which means in effect that the feature array pertaining to distorted versions of the same pattern belongs to a specific cluster), thereby justifying the coding strategy used in this paper. When the new, unknown pattern is input to the network, it is classified to have the same label of the neuron whose corresponding model pattern is closest to the given pattern. In an attempt to reduce the computational time and the size of the network, and simultaneously improve accuracy in recognition, Kohonen's learning vector quantization (LVQ) algorithm is used to train the ANN. To further improve the network's performance and to realize a network of minimum size, two constructive learning algorithms, both based on LVQ, are proposed: (1) multi-step learning vector quantization (MLVQ), and (2) thermal multi-step learning vector quantization (TLVQ). When the proposed algorithms are applied to the classification of noiseless and noisy (and distorted) patterns, the results demonstrate that the pattern encoding strategy and the suggested training techniques for ANNs are efficient and robust. For lack of space, only the most essential results are presented here. For details, see Ganesh Murthy and Venkatesh (1996b).

show abstract

Section: Anns and Pattern Recognitionmentioning

confidence: 99%

Encoded pattern classification using constructive learning algorithms based on learning vector quantization

Murthy¹,

Venkatesh²

1998

Neural Networks

View full text Add to dashboard Cite

show abstract

Character recognition system with cooperation of pattern and symbolic processing

Niwa

Yamamoto

Kojima

et al. 1995

Systems & Computers in Japan

View full text Add to dashboard Cite

A newly developed character recognition method is proposed that can be applied to low quality printed documents. In this method, the cooperation of pattern processing with neural networks and symbolic processing with knowledge of language is adopted. If errors occur at one part, another part detects it and sends the error information to all parts. After successive iterations until no error is detected, a recognition result is obtained. A character recognition of 98.4 percent is obtained with this method. This rate is 2.8 percent higher than the result of a conventional method with no information exchange among processing parts.

show abstract

Structured neural networks for multi-font Chinese character recognition using a newly developed digital neural network chip with adaptive segmentation of quantizer neuron architecture (ASQA)

Kondo

Imagawa²,

Maruno³

Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop

View full text Add to dashboard Cite

Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture

Cited by 5 publications

References 2 publications

Encoded pattern classification using constructive learning algorithms based on learning vector quantization

Encoded pattern classification using constructive learning algorithms based on learning vector quantization

Character recognition system with cooperation of pattern and symbolic processing

Structured neural networks for multi-font Chinese character recognition using a newly developed digital neural network chip with adaptive segmentation of quantizer neuron architecture (ASQA)

Contact Info

Product

Resources

About