A new text location method in natural scene images based on color reduction and AdaBoost

摘要

A new text location method based on color reduction and Adaboost classifier is proposed in this paper, which is used in extracting the text region in natural scene images with complex background. Firstly, the images are segmented into several layers through adopting color reduction and mean shift image segmentation techniques. Then, in order to pick up the potential text region, each layer is processed using connected component analysis, text region identification and text region merging, etc. Finally, HOG (Histogram of Oriented Gradient) and LBP (Local Binary Pattern) features are extracted from the candidate text region, and an AdaBoost classifier is applied to classify text and non-text regions. A series of experiments on a natural scene images database have indicated that, our method can effectively improve the text location in natural scene images with complex background, showing the effectiveness of the proposed approach.