TY  - JOUR
AU  - Li, Yuejie
AU  - Li, Shijun
AU  - Luo, Zhendong
PY  - 2026
DA  - 2026/09/27
TI  - Text Localization and Recognition of Chinese Characters in Natural Scenes Based on Improved Faster Region-Based Convolutional Neural Network
JO  - ICCK Transactions on Emerging Topics in Artificial Intelligence
T2  - ICCK Transactions on Emerging Topics in Artificial Intelligence
JF  - ICCK Transactions on Emerging Topics in Artificial Intelligence
VL  - 3
IS  - 3
SP  - 202
EP  - 217
DO  - 10.62762/TETAI.2026.620822
UR  - https://www.icck.org/article/abs/TETAI.2026.620822
KW  - text localization and recognition
KW  - deep learning
KW  - faster region-based convolutional neural network
KW  - long short-term memory
AB  - To solve the problems faced by Chinese character recognition, such as complex shapes and diverse structures, this paper adopts the Visual Geometry Group 16 (VGG-16) model for feature extraction and introduces a two-layer bidirectional Long Short-Term Memory (LSTM) network. It improves the Faster Region-based Convolutional Neural Network (Faster R-CNN) by using a Region Proposal Network (RPN) to extract candidate boxes and adjust the positions of candidate regions. The improved model, namely Faster BLSTM-CNN, is tested through three types of experiments: validation of feature extraction effectiveness, comparative analysis of the algorithm before and after improvement, and comparison with traditional recognition algorithms. Finally, an experimental comparison combining text recognition and localization is conducted. On the ReCTS and MSRA-TD500 datasets, the proposed Faster BLSTM-CNN achieves excellent performance in Chinese character localization and recognition: in natural scenes (ReCTS dataset), its total image identification rate (TIIR) reaches 81.54%, recognition precision rate is 88.14%, and inference speed is 86 ms per image. Compared with the end-to-end benchmark algorithms DETR+CRNN-RMC and CTPN+CRNN-RMC, it improves the recognition precision rate by up to 7.54%, the TIIR by up to 10.04%, and the inference speed by up to 21%. These gains are mainly attributed to the two-layer bidirectional LSTM for contextual feature modeling and the element-wise addition fusion strategy that avoids dimension explosion.
SN  - 3068-6652
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Li2026Text,
  author = {Yuejie Li and Shijun Li and Zhendong Luo},
  title = {Text Localization and Recognition of Chinese Characters in Natural Scenes Based on Improved Faster Region-Based Convolutional Neural Network},
  journal = {ICCK Transactions on Emerging Topics in Artificial Intelligence},
  year = {2026},
  volume = {3},
  number = {3},
  pages = {202-217},
  doi = {10.62762/TETAI.2026.620822},
  url = {https://www.icck.org/article/abs/TETAI.2026.620822},
  abstract = {To solve the problems faced by Chinese character recognition, such as complex shapes and diverse structures, this paper adopts the Visual Geometry Group 16 (VGG-16) model for feature extraction and introduces a two-layer bidirectional Long Short-Term Memory (LSTM) network. It improves the Faster Region-based Convolutional Neural Network (Faster R-CNN) by using a Region Proposal Network (RPN) to extract candidate boxes and adjust the positions of candidate regions. The improved model, namely Faster BLSTM-CNN, is tested through three types of experiments: validation of feature extraction effectiveness, comparative analysis of the algorithm before and after improvement, and comparison with traditional recognition algorithms. Finally, an experimental comparison combining text recognition and localization is conducted. On the ReCTS and MSRA-TD500 datasets, the proposed Faster BLSTM-CNN achieves excellent performance in Chinese character localization and recognition: in natural scenes (ReCTS dataset), its total image identification rate (TIIR) reaches 81.54\%, recognition precision rate is 88.14\%, and inference speed is 86 ms per image. Compared with the end-to-end benchmark algorithms DETR+CRNN-RMC and CTPN+CRNN-RMC, it improves the recognition precision rate by up to 7.54\%, the TIIR by up to 10.04\%, and the inference speed by up to 21\%. These gains are mainly attributed to the two-layer bidirectional LSTM for contextual feature modeling and the element-wise addition fusion strategy that avoids dimension explosion.},
  keywords = {text localization and recognition, deep learning, faster region-based convolutional neural network, long short-term memory},
  issn = {3068-6652},
  publisher = {Institute of Central Computation and Knowledge}
}