数字内容技术与服务研究中心知识库

The whole process of text detection in scene images always contain three steps: character candidate detection, false character candidate removal, words extraction. However some errors appear in each step and influence the performance of text detection. According to the disadvantages of each step, we propose the compensation methods to solve these problems. Firstly, a filter based on color of stroke named Stroke Color Transform is used to ensure the integrality of characters and remove some false character candidates. Secondly, a classifier is trained based on gradient features is adopted to remove false character candidates. Thirdly, an extractor based on color of consecutive character named Character Color Transform is employed to extract undetected characters. The proposed technique is test on the two public datasets i.e. ICDAR2011 dataset, ICDAR2013 dataset, the experimental results show that our approach outperforms the state-of-the-art methods.