Search

Date Recognition of Handwritten Chinese Documents Based on Object Detection and Character Classification

Author(s)

Zhenyu Liu, Jie Zhang*

Affiliation(s)

School of Automation, Nanjing University of Science and Technology, Nanjing, China *Corresponding Author.

Abstract

With the increasing degree of informatization in human society, paper documents are increasingly stored and processed in the form of electronic documents. People often want to extract key information such as dates in the process of digitizing paper documents. However, for text images with severe linking, extracting key information is very difficult. This paper proposes a date recognition framework for handwritten Chinese documents. First, YOLOv9 is trained to detect dates in images. Then single characters are segmented according to the pixels and character edges of the date area. And finally, Support Vector Machine (SVM) and Convolutional Neural Network (CNN) are used to classify handwritten Arabic numerals and handwritten Chinese characters and recognize handwritten numerals. At the same time, the date area in the text is located and recognized according to the date writing habits in Chinese documents. The method in this paper was experimented on 150 different handwritten Chinese text images with dates, and the recognition accuracy of dates in images reached 91.3%. The method proposed in this paper effectively achieves the localization and recognition of dates in handwritten Chinese character documents.

Keywords

Handwritten Chinese Characters; Object Detection; Character Segmentation; SVM; CNN; Date Recognition

References

[1] Mori S, Suen C Y, Yamamoto K. Historical review of OCR research and development. Proceedings of the IEEE, 1992, 80(7): 1029-1058. [2] Zhang X Y, Bengio Y, Liu C L. Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark. Pattern Recognition, 2017, 61: 348-360. [3] Dai R, Liu C, Xiao B. Chinese character recognition: history, status and prospects. Frontiers of Computer Science in China, 2007, 1: 126-136. [4] Haifeng D, Siqi H. Natural scene text detection based on YOLO V2 network model journal of physics: conference series. IOP Publishing, 2020, 1634(1): 012013. [5] Chaitra Y L, Dinesh R, Jeevan M, et al. An impact of YOLOv5 on text detection and recognition system using Tesseract OCR in images/video frames. 2022 IEEE International Conference on Data Science and Information System (ICDSIS). IEEE, 2022: 1-6. [6] Gao X, Han S, Luo C. A detection and verification model based on SSD and encoder-decoder network for scene text detection. IEEE Access, 2019, 7: 71299-71310. [7] Laroca R, Severo E, Zanlorensi L A, et al. A robust real-time automatic license plate recognition based on the YOLO detector. 2018 international joint conference on neural networks (ijcnn). IEEE, 2018: 1-10. [8] Chen R C. Automatic License Plate Recognition via sliding-window darknet-YOLO deep learning. Image and Vision Computing, 2019, 87: 47-56. [9] Memon J, Sami M, Khan R A. Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR). IEEE access, 2020, 8: 142642-142668. [10] Nguyen T T H, Jatowt A, Coustaty M. Survey of post-OCR processing approaches. ACM Computing Surveys (CSUR), 2021, 54(6): 1-37. [11] Lopresti D. Optical character recognition errors and their effects on natural language processing. Proceedings of the second workshop on Analytics for Noisy Unstructured Text Data. 2008: 9-16. [12] Fujisawa H, Nakano Y, Kurino K. Segmentation methods for character recognition: from segmentation to document structure analysis. Proceedings of the IEEE, 1992, 80(7): 1079-1092. [13] Wang C Y, Yeh I H, Liao H Y M. Yolov9: Learning what you want to learn using programmable gradient information. arxiv preprint arxiv:2402.13616, 2024. [14] Liu Y. Sequence Recognition of Scene Text Based on CRNN and CTPN Models. Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering. 2022: 196-200. [15] Zhong Z, Jin L,Xie, Z. High performance offline handwritten chinese character recognition using googlenet, and directional feature maps. 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, 2015: 846-850. [16] Xiao X, Jin L, Yang Y. Building fast and compact convolutional neural networks for offline handwritten Chinese character recognition. Pattern Recognition, 2017, 72: 72-81. [17] Shi P, Lou Y, Xia R. Handwritten Chinese character recognition based on morphology and transfer learning. 2023 International Conference on Intelligent Perception and Computer Vision (CIPCV). IEEE, 2023. [18] Wang X, Zheng S, Zhang C. R-YOLO: A real-time text detector for natural scenes with arbitrary rotation. Sensors, 2021, 21(3): 888. [19] Shashidhar R, Manjunath A S, Kumar R S. Vehicle number plate detection and recognition using yolo-v3 and ocr method 2021 IEEE International Conference on Mobile. Networks and Wireless Communications (ICMNWC). IEEE, 2021: 1-5. [20] Li X, Zhang X, Yang B. Character segmentation in text line via convolutional neural network. 2017 4th International Conference on Systems and Informatics (ICSAI). IEEE, 2017: 1175-1180. [21] Wu X, Chen Q, Xiao Y. LCSegNet: An efficient semantic segmentation network for large-scale complex Chinese character recognition IEEE Transactions on Multimedia 23 (2020): 3427-3440. [22] Kohli M, Kumar S. Segmentation of handwritten words into characters. Multimedia Tools and Applications 2021, 80: 22121-22133. [23] An S, Lee M, Park S. An ensemble of simple convolutional neural network models for mnist digit recognition. arxiv preprint arxiv:2008.10400 2020. [24] Wei T C, Sheikh U U, Ab Rahman A A H. Improved optical character recognition with deep neural network. 2018 IEEE 14th international colloquium on signal processing & its applications (CSPA). IEEE, 2018: 245-249. [25] Parthiban R, Ezhilarasi R, Saravanan D. Optical character recognition for English handwritten text using recurrent neural network. 2020 International Conference on System, Computation, Automation and Networking (ICSCAN). IEEE, 2020: 1-5. [26] Rawls S, Cao H, Kumar S. Combining convolutional neural networks and lstms for segmentation-free ocr2017 14th IAPR international conference on document analysis and recognition (ICDAR). IEEE, 2017, 1: 155-160. [27] Garg N, Sharma N, Jain G. Handwriting Recognition System Using YOLO and CTC 2023 International Conference on Advanced Computing & Communication Technologies (ICACCTech). IEEE, 2023: 496-502. [28] Chen W, Sui L, Xu Z. Improved Zhang-Suen thinning algorithm in binary line drawing applications 2012 International Conference on Systems and Informatics (ICSAI2012). IEEE, 2012: 1947-1950. [29] Deng G, Cahill L W. An adaptive Gaussian filter for noise reduction and edge detection 1993 IEEE conference record nuclear science symposium and medical imaging conference. IEEE, 1993: 1615-1619.