SNOOPERTEXT: A MULTIRESOLUTION SYSTEM FOR TEXT DETECTION IN COMPLEX VISUAL SCENES

Text detection in natural images remains a very challeng-ing task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular il-lumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a mul-tiresolution algorithm able to manage large character size vari-ations. The segmented regions are then filtered out using shape-based classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results. Index Terms — Text detection, multiresolution, image seg-mentation, machine learning