Handwriting Text Recognition Based on Faster R-CNN

Handwriting text recognition is one of the emphases in computer vision. The traditional Optical Character Recognition (OCR) technology requires the text writing neatly and handwriting clearly, but in fact, the handwriting text always fail to meet such states. In this paper, a novel handwriting text recognition algorithm based on deep learning is presented to improve the problems. In this paper, the method based on an object detection algorithm (Faster R-CNN) finds a new dimension to study the problem. The algorithm sets two steps: First, preprocessing the handwriting character based on Faster RCNN, second, character recognition based on the Convolutional Neural Networks. The correctness of this method is better than the traditional OCR by the testing data. Experimental results show that the recognition algorithm in this paper is effective and illuminating.