Ανίχνευση Κειμένου Σε Εικόνες Και Βίντεο

Abstract

The tremendous increase of multimedia content created new challenges in research areas related to multimedia categorization, retrieval and indexing. Text embedded in images and videos constitutes valuable source of high level semantics often essential for their fast and accurate description. The goal of a multimedia text extraction and recognition system is filling the gap between the already existing and mature technology of Optical Character Recognition and the new needs for textual information retrieval created by the spread of digital multimedia. If the transition from the arbitrary and complex multimedia text to a document-like, structured, binary text image is successful, then the existing techniques for character segmentation and recognition can be used for the generation of ASCII characters. A text extraction system from multimedia usually consists of the following four stages: spatial text detection, temporal text detectiontracking (for videos), image binarization -segmentation, character recognition. 4.1Εντοπισμός περιοχής κειμένου ..