Text detection in natural images based on multi-scale edge detetion and classification

In this paper, we present a robust method for text detection in color scene image. The algorithm is based on edge detection and connected-component. In our framework, firstly, multi-scale edge detection is achieved by Canny operator and an adaptive thresholding binary method. Secondly, the filtered edges are classified by the classifier trained by SVM combing HOG, LBP and several statistical features, including mean, standard deviation, energy, entropy, inertia, local homogeneity and correlation. Thirdly, k-means clustering algorithm and the binary gradient image are used to filter the candidate regions and re-detect the regions around the candidate text candidates. Finally, the texts are relocated accurately by projection analysis. Experiments on 2003 ICDAR text location competition test database show the effectiveness of the proposed method.