Chinese Character Boxes: Single Shot Detector Network for Chinese Character Detection
Source abstract
Abstract
This paper proposes a deep learning-based Chinese character detection network which is important for character recognition and translation. Detecting the correct character area is an important part of recognition and translation. Previous studies have focused on methods using projection through image pre-processing and recognition methods based on segmentation and methods using hand-crafted features such as analyzing and using features. Unfortunately, the results are vulnerable to noise. Recently, recognition or translation systems based on deep learning were dealt with as a single step from detection to translation but they failed to consider the inaccurate localization problem that arises in detectors. This paper proposes a Chinese character boxes (CCB) network that deals with a method to detect the character area more accurately using the single-shot multibox detector (SSD) as the baseline and called CCB-SSD. The proposed CCB-SSD network has a single prediction layer structure in which unnecessary layers are removed from the feature-pyramid structure. The augmentation method for training is introduced and the problem caused by the use of default boxes is solved by using the proposed non-maximum suppression (NMS). The experimental results revealed a 96.1% detection rate and 0.89 performance against the false positives per character (FPPC) which is the proposed false positive index for the character data-set and caoshu data-set used in this paper. This method showed better performance than the conventional SSD with 69.4% and 6.57 FPPC.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Image Processing and 3D Reconstruction · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronic Engineering, Yeungnam University, 280 Daehak-ro, Gyeongsan-si, Gyeongsangbuk-do 38541, Korea
Funding
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) · This work was also supported by the 2018 Yeungnam University Research Grants.
References (35)
Show source-provided references
1. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 8–16). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
2. Text-Line and Character Segmentation for Offline Recognition of Handwritten Japanese Text
3. Optical character recognition for cursive handwriting10.1109/TPAMI.2002.1008386 ↗
4. Roy, A., Bhowmik, T.K., Parui, S.K., and Roy, U. (2005, January 6–8). A novel approach to skew detection and character segmentation for handwritten Bangla words. Proceedings of the 2005 Digital Image Computing: Techniques and Applications (DICTA’05), Queensland, Australia.10.1109/DICTA.2005.6 ↗
5. Tse, J., Jones, C., Curtis, D., and Yfantis, E. (2007, January 13–15). An OCR-independent character segmentation using shortest-path in grayscale document images. Proceedings of the Sixth International Conference on Machine Learning and Applications (ICMLA 2007), Cincinnati, OH, USA.10.1109/ICMLA.2007.21 ↗
6. Yoon, Y., Ban, K.D., Yoon, H., and Kim, J. (2012, January 17–19). Blob detection and filtering for character segmentation of license plates. Proceedings of the 2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP), Banff, AB, Canada.10.1109/MMSP.2012.6343467 ↗
7. Subramanian, K., Natarajan, P., Decerbo, M., and Castanon, D. (2007, January 23–26). Character-stroke detection for text-localization and extraction. Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), Parana, Brazil.10.1109/ICDAR.2007.4378671 ↗
8. Uchida, S., Shigeyoshi, Y., Kunishige, Y., and Yaokai, F. (2011, January 18–21). A keypoint-based approach toward scenery character detection. Proceedings of the 2011 International Conference on Document Analysis and Recognition (ICDAR), Beijing, China.10.1109/ICDAR.2011.168 ↗
9. Kunishige, Y., Yaokai, F., and Uchida, S. (2011, January 18–21). Scenery character detection with environmental context. Proceedings of the 2011 International Conference on Document Analysis and Recognition (ICDAR), Beijing, China.10.1109/ICDAR.2011.212 ↗
10. Chen, H., Tsai, S.S., Schroth, G., Chen, D.M., Grzeszczuk, R., and Girod, B. (2011, January 11–14). Robust text detection in natural images with edge-enhanced maximally stable extremal regions. Proceedings of the 2011 18th IEEE International Conference on Image Processing (ICIP), Brussels, Belgium.10.1109/ICIP.2011.6116200 ↗
11. Yi, C., Yang, X., and Tian, Y. (2013, January 25–28). Feature representations for scene text character recognition: A comparative study. Proceedings of the 2013 12th International Conference on Document Analysis and Recognition (ICDAR), Washington, DC, USA.10.1109/ICDAR.2013.185 ↗
12. Huang, R., Shivakumara, P., and Uchida, S. (2013, January 25–28). Scene character detection by an edge-ray filter. Proceedings of the 2013 12th International Conference on Document Analysis and Recognition (ICDAR), Washington, DC, USA.10.1109/ICDAR.2013.99 ↗
13. A novel text detection system based on character and link energies
14. Sung, M.C., Jun, B., Cho, H., and Kim, D. (2015, January 23–26). Scene text detection with robust character candidate extraction method. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.10.1109/ICDAR.2015.7333797 ↗
15. Zhao, Y.X., and Chou, C.H. (2016). Feature Selection Method Based on Neighborhood Relationships: Applications in EEG Signal Identification and Chinese Character Recognition. Sensors, 16.10.3390/s16060871 ↗
16. Wang, K., Babenko, B., and Belongie, S. (2011, January 6–13). End-to-end scene text recognition. Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain.
17. Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S., and Zhang, Z. (2013, January 23–28). Scene text recognition using part-based tree-structured character detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.381 ↗
18. Scene Text Recognition Using Structure-Guided Character Detection and Linguistic Knowledge10.1109/TCSVT.2014.2302522 ↗
19. Tsai, C. (2016). Recognizing Handwritten Japanese Characters Using Deep Convolutional Neural Networks, Stanford University. Technical Report.
20. Maidana, R.G., dos Santos, J.M., Granada, R.L., de Morais Amory, A., and Barros, R.C. (2017, January 2–5). Deep Neural Networks for Handwritten Chinese Character Recognition. Proceedings of the 2017 Brazilian Conference on Intelligent Systems (BRACIS), Uberlandia, Brazil.10.1109/BRACIS.2017.24 ↗
21. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA.
22. Simonyan, K., and Zisserman, A. (arXiv, 2014). Very deep convolutional networks for large-scale image recognition, arXiv.
23. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
24. Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10590-1_53 ↗
25. Reading text in the wild with convolutional neural networks10.1007/s11263-015-0823-z ↗
26. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
27. Zitnick, C.L., and Dollár, P. (2014, January 6–12). Edge boxes: Locating object proposals from edges. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10602-1_26 ↗
28. Fast feature pyramids for object detection10.1109/TPAMI.2014.2300479 ↗
29. Liao, M., Shi, B., Bai, X., Wang, X., and Liu, W. (2017, January 4–9). TextBoxes: A Fast Text Detector with a Single Deep Neural Network. Proceedings of the AAAI, San Francisco, CA, USA.10.1609/aaai.v31i1.11196 ↗
30. Bušta, M., Neumann, L., and Matas, J. (2017, January 22–29). Deep textspotter: An end-to-end trainable scene text localization and recognition framework. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.242 ↗
31. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (CVPR 2017), Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
32. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, MIT Press.
33. Jeong, J., Park, H., and Kwak, N. (2017, January 4–7). Enhancement of SSD by concatenating feature maps for object detection. Proceedings of the British Machine Vision Conference (BMVC), London, UK.10.5244/C.31.76 ↗
34. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
35. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 13–16). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.123 ↗