Multilingual scene character recognition with co-occurrence of histogram of oriented gradients

Automatic machine reading of texts in scenes is largely restricted by the poor character recognition accuracy. In this paper, we extend the Histogram of Oriented Gradient (HOG) and propose two new feature descriptors: Cooccurrence HOG (Co-HOG) and Convolutional Co-HOG (ConvCo-HOG) for accurate recognition of scene texts of different languages. Compared with HOG which counts orientation frequency of each single pixel, the Co-HOG encodes more spatial contextual information by capturing the co-occurrence of orientation pairs of neighboring pixels. Additionally, ConvCo-HOG exhaustively extracts Co-HOG features from every possible image patches within a character image for more spatial information. The two features have been ∗Corresponding author. Tel: +65-65162784, Fax: +65-67794580 Email addresses: [email protected] (Shangxuan Tian ), [email protected] (Ujjwal Bhattacharya), [email protected] (Shijian Lu), [email protected] (Bolan Su), [email protected] (Chew Lim Tan) Preprint submitted to Pattern Recognition June 18, 2015 *Manuscript Click here to view linked References