Scene text detection with superpixels and hierarchical model

Scene text detection is a challenging task for the text-based information extraction systems. We present a novel scene text detection method for this task. The images are over-segmented into meaningful perceptron superpixels, and candidate connected components (CCs)are extracted by combining local contrast and color consistency. The non-text components are then pruned by a hierarchical model consisting of three stages in cascade. Experimental results show that our approach is better than other state-of-the-art methods.