Applications of neural networks in handwritten digit recognition

Ching Tang Hsieh, Mu Chun Su, Shih Lii Yang, Kuang Ming Shen

Research output: Contribution to conferencePaperpeer-review

Abstract

This paper proposes a handwritten digit recognition system based on a HyperRectangular Composite Neural Network(HRCNN). This system consists of four parts : an input device, preprocessing, feature extraction, and a classifier. The input device is an image, scanner which can get several numerals simultaneously. Preprocessing involves image segmentation and normalization. The Localized Arc Patterns are used to extract the feature vectors from the normalized image. Then the feature vectors are used as the input of the HRCNN and we can obtain the result. The experiment shows a good result and thus we can use this system in a wide range of applications about handwritten digit recognition.

Original languageEnglish
Pages335-338
Number of pages4
StatePublished - 1997
Event7th International Symposium on IC Technology, Systems and Applications ISIC 97 - Singapore, Singapore
Duration: 10 Sep 199712 Sep 1997

Conference

Conference7th International Symposium on IC Technology, Systems and Applications ISIC 97
Country/TerritorySingapore
CitySingapore
Period10/09/9712/09/97

Fingerprint

Dive into the research topics of 'Applications of neural networks in handwritten digit recognition'. Together they form a unique fingerprint.

Cite this