Handwritten Multi-Scale Chinese Character Detector with Blended Region Attention Features and Light-Weighted Learning
Author:
Alnaasan Manar1, Kim Sungho1ORCID
Affiliation:
1. Department of Electronics Engineering, Yeungnam University, 280 Daehak-ro, Gyeongsan-si 38541, Republic of Korea
Abstract
Character-level detection in historical manuscripts is one of the challenging and valuable tasks in the computer vision field, related directly and effectively to the recognition task. Most of the existing techniques, though promising, seem not powerful and insufficiently accurate to locate characters precisely. In this paper, we present a novel algorithm called free-candidate multiscale Chinese character detection FC-MSCCD, which is based on lateral and fusion connections between multiple feature layers, to successfully predict Chinese characters of different sizes more accurately in old documents. Moreover, cheap training is exploited using cheaper parameters by incorporating a free-candidate detection technique. A bottom-up architecture with connections and concatenations between various dimension feature maps is employed to attain high-quality information that satisfies the positioning criteria of characters, and the implementation of a proposal-free algorithm presents a computation-friendly model. Owing to a lack of handwritten Chinese character datasets from old documents, experiments on newly collected benchmark train and validate FC-MSCCD to show that the proposed detection approach outperforms roughly all other SOTA detection algorithms
Funder
2023 Yeungnam University Research Grants NRF
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference34 articles.
1. Mubarok, A., and Nugroho, H. (2016, January 15–16). Handwritten character recognition using hierarchical graph matching. Proceedings of the 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Malang, Indonesia. 2. Zhu, Z.Y., Yin, F., and Wang, D.H. (2020, January 8–10). Attention Combination of Sequence Models for Handwritten Chinese Text Recognition. Proceedings of the 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), Dortmund, Germany. 3. Wang, Z.X., Wang, Q.F., Yin, F., and Liu, C.L. (2020, January 8–10). Weakly Supervised Learning for Over-Segmentation Based Handwritten Chinese Text Recognition. Proceedings of the 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), Dortmund, Germany. 4. Droby, A., Barakat, B.K., Madi, B., Alaasam, R., and El-Sana, J. (2020, January 8–10). Unsupervised Deep Learning for Handwritten Page Segmentation. Proceedings of the 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), Dortmund, Germany. 5. Ryu, J., and Kim, S. (2018, January 17–20). Chinese Character Detection Using Modified Single Shot Multibox Detector. Proceedings of the 2018 18th International Conference on Control, Automation and Systems (ICCAS), PyeongChang, Korea.
|
|