Presentation 2000/2/22
An Adaptive Threshold Method for Gray Scale Document Images
Akira Murakata, Norikazu Onda, Shinji Ozawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Gray scale document image is less suitable for conventional binarization algorithm because of character struture when used for OCR. Digital camera image is difficult to binarize conventional binarization algorithm because of strong shading. Strong shading causes difficulty to decide threshold level, and character structure tend to make binarized character scratchy or blurred. This paper presents a model based adaptive binarization algorithm, which handles above problems. we assumed digitized binary image has not only two states (black and white) but also three states. They are Background, Transition and Character pixel. We attach importance to Transition pixels, and utilize gradient information from this area for first stage binarization. Finally, we examine the performance of this method on sets of character image for several types of fonts, and we found certain percentage of improvement in OCR results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Binarization / document image / digital camera / OCR
Paper # PRMU99-232
Date of Issue

Conference Information
Committee PRMU
Conference Date 2000/2/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Adaptive Threshold Method for Gray Scale Document Images
Sub Title (in English)
Keyword(1) Binarization
Keyword(2) document image
Keyword(3) digital camera
Keyword(4) OCR
1st Author's Name Akira Murakata
1st Author's Affiliation Faculty of Science and Technology, Keio University()
2nd Author's Name Norikazu Onda
2nd Author's Affiliation Faculty of Science and Technology, Keio University
3rd Author's Name Shinji Ozawa
3rd Author's Affiliation Faculty of Science and Technology, Keio University
Date 2000/2/22
Paper # PRMU99-232
Volume (vol) vol.99
Number (no) 649
Page pp.pp.-
#Pages 8
Date of Issue