A robust approach for recognition of text embedded in natural scenes

In this paper, we propose a robust approach for recognition of text embedded in natural scenes. Instead of using binary information as most other OCR systems do, we extract features from intensity of an image directly. We utilize a local intensity normalization method to effectively handle lighting variations. We then employ Gabor transform to obtain local features, and use the linear discriminant analysis (LDA) for selection and classification of features. The proposed method has been applied to a Chinese sign recognition task. The system can recognize a vocabulary of 3755 level I Chinese characters in the Chinese national standard character set GB2312-80 with various print fonts. We tested the system on 1630 test characters in sign images captured from the natural scenes, and the recognition accuracy was 92.46%. We have integrated the system into our automatic Chinese sign translation system.