Document analysis and recognition system

Fu Chang; Trai Fu Chiu; Tzren Ru Chou; Min Ching Lee; Ya Ching Lu; Tsuey Yuh Shuai; Tzu Ming Tan; Jian Jon Wu; Chu Sing Young

Document analysis and recognition system

Fu Chang^*, Trai Fu Chiu, Tzren Ru Chou, Min Ching Lee, Ya Ching Lu, Tsuey Yuh Shuai, Tzu Ming Tan, Jian Jon Wu, Chu Sing Young

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

This article describes our research results in constructing a system that analyzes and recognizes printed Chinese documents. Emphasis is placed upon the interactions between different functional modules of our system that are necessary and important to the overall system performance. In particular, the interplay between image and document processing is seen as useful for removing spurious black spots in the background and white holes within character interiors. We also show that the interplay between feature analysis and character recognition enhances the generalization and discrimination power in recognizing characters. Our system holds above 98% recognition rate products. In some extreme cases, 25% better recognition rate has been seen. Our system is also able to treat many cases impossible for other systems.

Original language	English
Pages	736-739
Number of pages	4
Publication status	Published - 1997
Externally published	Yes
Event	Proceedings of the 1997 4th International Conference on Document Analysis and Recognition, ICDAR. Part 2 (of 2) - Ulm, Ger Duration: 1997 Aug 18 → 1997 Aug 20

Other

Other	Proceedings of the 1997 4th International Conference on Document Analysis and Recognition, ICDAR. Part 2 (of 2)
City	Ulm, Ger
Period	1997/08/18 → 1997/08/20

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

@conference{8a6a056ebceb4b66b19326fff17bcce2,

title = "Document analysis and recognition system",

abstract = "This article describes our research results in constructing a system that analyzes and recognizes printed Chinese documents. Emphasis is placed upon the interactions between different functional modules of our system that are necessary and important to the overall system performance. In particular, the interplay between image and document processing is seen as useful for removing spurious black spots in the background and white holes within character interiors. We also show that the interplay between feature analysis and character recognition enhances the generalization and discrimination power in recognizing characters. Our system holds above 98% recognition rate products. In some extreme cases, 25% better recognition rate has been seen. Our system is also able to treat many cases impossible for other systems.",

author = "Fu Chang and Chiu, {Trai Fu} and Chou, {Tzren Ru} and Lee, {Min Ching} and Lu, {Ya Ching} and Shuai, {Tsuey Yuh} and Tan, {Tzu Ming} and Wu, {Jian Jon} and Young, {Chu Sing}",

year = "1997",

language = "English",

pages = "736--739",

note = "Proceedings of the 1997 4th International Conference on Document Analysis and Recognition, ICDAR. Part 2 (of 2) ; Conference date: 18-08-1997 Through 20-08-1997",

}

TY - CONF

T1 - Document analysis and recognition system

AU - Chang, Fu

AU - Chiu, Trai Fu

AU - Chou, Tzren Ru

AU - Lee, Min Ching

AU - Lu, Ya Ching

AU - Shuai, Tsuey Yuh

AU - Tan, Tzu Ming

AU - Wu, Jian Jon

AU - Young, Chu Sing

PY - 1997

Y1 - 1997

N2 - This article describes our research results in constructing a system that analyzes and recognizes printed Chinese documents. Emphasis is placed upon the interactions between different functional modules of our system that are necessary and important to the overall system performance. In particular, the interplay between image and document processing is seen as useful for removing spurious black spots in the background and white holes within character interiors. We also show that the interplay between feature analysis and character recognition enhances the generalization and discrimination power in recognizing characters. Our system holds above 98% recognition rate products. In some extreme cases, 25% better recognition rate has been seen. Our system is also able to treat many cases impossible for other systems.

AB - This article describes our research results in constructing a system that analyzes and recognizes printed Chinese documents. Emphasis is placed upon the interactions between different functional modules of our system that are necessary and important to the overall system performance. In particular, the interplay between image and document processing is seen as useful for removing spurious black spots in the background and white holes within character interiors. We also show that the interplay between feature analysis and character recognition enhances the generalization and discrimination power in recognizing characters. Our system holds above 98% recognition rate products. In some extreme cases, 25% better recognition rate has been seen. Our system is also able to treat many cases impossible for other systems.

UR - http://www.scopus.com/inward/record.url?scp=0030676851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030676851&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030676851

SP - 736

EP - 739

T2 - Proceedings of the 1997 4th International Conference on Document Analysis and Recognition, ICDAR. Part 2 (of 2)

Y2 - 18 August 1997 through 20 August 1997

ER -

Document analysis and recognition system

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this