Authors: BaiBo

Description: Using gradient local correlation, we can characterize the density of pairwise edges and stroke width consistency to get a text confidence map. Based on the text confidence map, the regions with high confidence are segmented into connected components (CCs) based on a fast semi-supervised method. Then, CCs are classified to text CCs and non-text CCs by SVM, and text CCs with similar color and stroke width are grouped into text lines, which are in turn partitioned into final result.