Academic Journal of Computing & Information Science, 2023, 6(13); doi: 10.25236/AJCIS.2023.061328.
Jiaxi Guo, Chuansheng Wu
University of Science and Technology Liaoning, Anshan, Liaoning, China
This paper introduces a deep learning model training approach and a text detection method that harnesses the power of artificial intelligence, particularly in the fields of computer vision and deep learning. This method is well-suited for applications in optical character recognition (OCR) and other related scenarios. We detail the training process of the deep learning model for text detection, which involves the utilization of both single character segmentation and text line segmentation sub-networks. The trained model can effectively identify text areas in an image, and the prediction of single character segmentation and text line segmentation can be achieved simultaneously. By combining both text segmentation methods, we enhance the overall accuracy of text area detection.
Deep Learning, Text Detection, Model Training
Jiaxi Guo, Chuansheng Wu. Research on Deep Learning Based Methods for Text Detection. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 13: 208-218. https://doi.org/10.25236/AJCIS.2023.061328.
[1] Mnih, V. (Volodymyr), Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. A. (2013). Playing Atari with Deep Reinforcement Learning. CoRR, 89-90.
[2] Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., & Li, G. (2019). Scene Text Detection with Supervised Pyramid Context Network. Proceedings of the AAAI Conference on Artificial Intelligence, 56-57.
[3] Liu, Y., Jin, L., Zhang, S., Luo, C., & Zhang, S. (2019). Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognition, 103-108.
[4] Liao, M., Shi, B., & Bai, X. (2018). TextBoxes++: A Single-Shot Oriented Scene Text Detector. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 23-25.
[5] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE transactions on pattern analysis and machine intelligence, 89-90.
[6] Toledo, R. Y., Caballero Mota, Y., & Martínez, L. (2018). A Recommender System for Programming Online Judges Using Fuzzy Information Modeling. Informatics, 77-78.
[7] Yera Toledo, R., Caballero Mota, Y., & Martínez, L. (2020). An e-Learning Collaborative Filtering Approach to Suggest Problems to Solve in Programming Online Judges. International Journal of Distance Education Technologies (IJDET), 66-67.
[8] Yera, R., & Martínez, L. (2017). A recommendation approach for programming online judges supported by data preprocessing techniques. Applied Intelligence, 54-56.
[9] De La Torre, J. (2009). DINA model and parameter estimation: A didactic. Journal of educational and behavioral statistics, 34(1), 115-130.
[10] Fan, X. (2012). Item Response Theory and Classical Test Theory: An Empirical Comparison of their Item/Person Statistics. Educational and Psychological Measurement, 67-68.