Oracle text positioning system based on improved YOLOv7-FC model
DOI:
https://doi.org/10.54097/ehss.v19i.11036Keywords:
Oracle bone inscriptions image, YOLOv7, Text positioning, Semantic segmentation, Object detection.Abstract
In recent years, how to use computer to efficiently and accurately recognize oracle characters on oracle rubbings has become the focus of research. Due to the severe damage caused by the natural environment and the characteristics of complex background and loud noise, the oracle bone rubbings are difficult to separate the foreground and back of the oracle bone inscriptions. Therefore, it will be the future research direction to eliminate the negative impact of complex background and accurately locate the Oracle bone inscriptions. This paper puts forward the YOLOv7-FC neural network model and realizes the specific application in the oracle topology data set, and presents the system of single oracle character positioning results.The experimental results show that on the HWOBC-A dataset, the mAP value of the YOLOv7-FC neural network model proposed in this paper reaches 0.937. Compared with the original YOLOv7 model, it has improved by 0.22, effectively balancing the relationship between running speed and average accuracy, and providing feasibility for Oracle text localization machine learning method.
Downloads
References
Wang Aimin, Zhong Luo, Ge Yanqiang, et al. Research on Key Technologies for Intelligent Conjugation of Oracle Bone Fragments [J]. Journal of Wuhan University of Technology, 2010 (20): 194 - 199.
Liu Fang, Li Huabiao, Ma Jin, et al. Research on Automatic Detection and Recognition of Oracle Rubbings Based on Mask R-CNN [J] Data Analysis and Knowledge Discovery, 2021 (12): 88 - 97.
Han Jiaohong. Research on ontology-based semantic retrieval model for oracle bone literature [J] Library Science Research, 2013 (07): 51 - 57.
Li Qingsheng, Wu Qinxia, Yang Yuxing, et al. Research on oracle bone script font dynamic description library and its font generation technology [J] Journal of Peking University (Natural Science Edition), 2013 (01): 61 - 67.
Li Dongqin, Wang Fang, Zhou Wanhuai, et al. Research on Text Detection Methods in Natural Scene Images [J] Journal of Chongqing University of Science and Technology (Natural Science Edition), 2016, 18 (06): 108 - 111.
Yi C, Tian Y L. Text string detection from natural scenes by structure-based partition and grouping [J]. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 2011 (9): 2594 - 2605.
Zhao, X, Lin, K.-H, Fu, Y, Hu, Y, Liu, Y, Huang, T. S. Text from Corners: A Novel Approach to Detect Text and Caption in Videos[J]. Image Processing, IEEE Transactions on, 2011, (3): 790 - 799.
Shivakumara P, Phan T Q, Tan C L. New Fourier-Statistical Features in RGB Space for Video Text Detection [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010 (11): 1520 - 1532.
Jung C,Liu Q, Kim J.A stroke filter and its application to text localization [J]. Pattern Recognition Letters, 2009 (2): 114 - 122.
Li B, Dai Q, Gao F, et al. HWOBC-A Handwriting Oracle Bone Character Recognition Database [J]. Journal of Physics Conference Series, 2020, 1651: 012050.
Li Qingsheng, Yang Yuxing, Wang Aimin A Graph Isomorphism Method for Oracle Bone Inscription Recognition [J] Computer Engineering and Applications, 2011, 47 (8): 3.
Guo Lei. Research on feature extraction algorithm for neatly written oracle bone rubbings [J]. Computer Applications and Software. 2014 (6): 4.
Shi Xiaosong, Huang Yongjie, Liu Yongge. A text localization method based on threshold segmentation and morphology for oracle bone rubbings [J]. Journal of Beijing University of Information Technology (Natural Science Edition), 2014 (06): 7 - 10.
Feng, G., Jing, X., & Yongge, L. (2015). Recognition of Fuzzy Characters on Oracle-Bone Inscriptions. IEEE International Conference on Computer & Information Technology Ubiquitous Computing & Communications Dependable. IEEE.
Chen Tingzhu, Wu Shaoteng, Wu Jiang, et al.Research on Encoding Based Oracle Recognition Technology [J]. Chinese Character Research, 2019 (1): 12.
Melnyk P, You Z, Li K. A high-performance CNN method for offline handwritten Chinese character recognition and visualization [J]. Soft Computing, 2019, 24 (8).
Zhang Yikang, Zhang Heng, Liu Yongge, et al. Oracle bone character recognition based on cross modal depth metric learning [J]. Journal of Automation, 2021 (4): 10.
Gaofeng, Liu Yongge, Han Shengwei. From "Digital Oracle Bone" to "Intelligent Oracle Bone" - A New Paradigm of "Yin Qiwen Yuan" Assisting Oracle Bone Research [J]. Oracle Bone Inscription and Yin Shang History, 2021 (00): 600 - 610.
Men Yi, Zhang Chongsheng. Artificial intelligence-based oracle bone recognition technology and font database construction [J]. Chinese Character Research, 2021 (1): 8.
Zhou X, Yao C, Wen H, et al. EAST: An Efficient and Accurate Scene Text Detector [J]. IEEE, 2017.
Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition [J]. Computer Science, 2014.
Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [J]. arXiv e-prints, 2022.
Ma N, Zhang X, Sun J. Funnel Activation for Visual Recognition [J]. 2020.
Li Y, Yao T, Pan Y, et al. Contextual Transformer Networks for Visual Recognition [J]. 2021.
Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection [J]. 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
