Text Locating and Verification Algorithm for Scene Images Based on Gray-Scale Connected-Component Analysis

Abstract

〈Summary〉 Text information in natural images is formally different from that in the images captured by traditional scanners. A text locating algorithm for natural color images is presented. The apparent non-text regions are removed by two-step processing of the grayscale version of the original image, leaving the possible text regions. The first deletion is based on connected-component (CC) analysis of strokes. The second step uses a rulesoriented verification process for improving the performance.