B
Bor-Shenn Jeng
Researcher at National Central University
Publications - 12
Citations - 34
Bor-Shenn Jeng is an academic researcher from National Central University. The author has contributed to research in topics: Optical character recognition & Image segmentation. The author has an hindex of 4, co-authored 12 publications receiving 34 citations.
Papers
More filters
Journal ArticleDOI
Optimal segmentation of handwritten Chinese signatures using wavelet transforms
TL;DR: To segment an input signature curve at the inflection points, and to locate the inflec- tion points by detecting the zero-crossing points of the wavelet trans- forms of the input signature, is proposed.
Journal ArticleDOI
Optical Chinese Character Recognition Using Accumulated Stroke Features
TL;DR: An intelligent optical Chinese character recognition system using accumulated stroke features has been developed to solve the input problem of Chinese characters and results show that 99% of printed characters and 90% of constrained handwritten characters can be correctly recognized.
Proceedings ArticleDOI
On-line Chinese signature verification with mixture of experts
Nai-Jen Cheng,Chi-Jain Wen,Hon-Fai Yau,David Hwang Liu,Kuei Liu,Kun-Chi Cheng,Bor-Shenn Jeng +6 more
TL;DR: An on-line Chinese signature verification system based on mixture of experts to further improve the reliability of a Signature verification system with a personal-oriented feature decision is proposed.
Journal ArticleDOI
Tremor detection of handwritten Chinese signatures based on multiresolution decomposition using wavelet transforms
TL;DR: A tremor detection scheme for handwritten signature verification is proposed, which can extract the trembling features of handwritten signatures based on the multi-resolution property of a wavelet transform.
Proceedings ArticleDOI
Handwritten Chinese signature verification based on attributed string matching of stroke linkage order
Nai-Jen Cheng,Chi-Jain Wen,Hon-Fai Yau,Tsann-Shyong Liu,Kuei Liu,Kun-Chi Cheng,Bor-Shenn Jeng +6 more
TL;DR: This research proposes an attributed string matching approach based on the writing sequences of an input signature for Chinese signature verification to find a particular feature set that will exhibit small intraclass variance.