Presentation | 2022-12-16 Training Kindai OCR with parallel textline images and self-attention feature distance-based loss Le Duc Anh, Kitamoto Asanobu, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The modern Japanese documents in late 19th and early 20th century are called Kindai documents and have great historic value for historians and experts in exploring social aspects, lifestyles, even weather in the previous era. It is time-consuming and labor-intensive work for making transcriptions for the documents. As the result, the training dataset is small and it is hard to enlarge the training dataset. In this research, we aim to enlarge small training set by parallel textline images. Parallel textline images contain a pair of original Kindai and current Japanese fonts. We propose a distance-based objective function to minimize the distance between the self-attention feature of parallel textline images. The experiments show that the proposed system improves 2.3% of CER to compare with a Transformer as a baseline Kindai OCR. Moreover, our proposed method provides a better discriminant of self-attention feature. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Kindai OCRself-attention feature distance-based lossparallel textline images |
Paper # | PRMU2022-56 |
Date of Issue | 2022-12-08 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2022/12/15(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Toyama International Conference Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Seiichi Uchida(Kyushu Univ.) |
Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) |
Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) |
Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Training Kindai OCR with parallel textline images and self-attention feature distance-based loss |
Sub Title (in English) | |
Keyword(1) | Kindai OCRself-attention feature distance-based lossparallel textline images |
1st Author's Name | Le Duc Anh |
1st Author's Affiliation | Center for Open Data in the Humanities(Center for Open Data in the Humanities) |
2nd Author's Name | Kitamoto Asanobu |
2nd Author's Affiliation | Center for Open Data in the Humanities(Center for Open Data in the Humanities) |
Date | 2022-12-16 |
Paper # | PRMU2022-56 |
Volume (vol) | vol.122 |
Number (no) | PRMU-314 |
Page | pp.pp.127-131(PRMU), |
#Pages | 5 |
Date of Issue | 2022-12-08 (PRMU) |