Script recognition in images with complex backgrounds

The extraction of textual information front images and videos is an important task for automatic content-based indexing and retrieval purposes. To extract text from images or videos coming from unknown international sources, it is necessary to know the script beforehand in order to employ suitable text segmentation and optical character recognition (OCR) methods. In this paper we present an approach for discriminating between Latin and Ideographic script. The proposed approach proceeds as follows: First, the text present in an image is localized. Then, a set of low-level features is extracted from the localized text image. Finally, based on the extracted features, the decision about the type of the script is made using a K-Nearest Neighbour classifier. Initial experimental results for a set of images containing text of different scripts demonstrate the good performance of the proposed solution.