Automatic discrimination of text and non-text natural images

With the rapid growth of image and video data, there comes an interesting yet challenging problem: How to organize and utilize such large volume of data? Textual content in images and videos is an important source of information, which can be of great usefulness and assistance. Therefore, we investigate in this paper the problem of text image discrimination, which aims at distinguishing natural images with text from those without text. To tackle this problem, we propose a method that combines three mature techniques in this area, namely: MSER, CNN and BoW. To better evaluate the proposed algorithm, we also construct a large benchmark for text image discrimination, which includes natural images in a variety of scenarios. This algorithm has proven to be both effective and efficient, thus it can serve as a tool for mining valuable textual information from huge amount of image and video data.