Author: Sangita Wamane
Abstract: The rapid growth of video data leads to an urgent demand for efficient and true content-based browsing and retrieving systems. In response to such needs, various video content analysis schemes using one or a combination of image, audio, and text information in videos have been proposed to parse, index, or abstract massive amount of data text in video is a very compact and accurate clue for video indexing and summarization. Most video text detection and extraction methods hold assumptions on text color, background contrast, and font style. Moreover, few methods can handle multilingual text well since different languages may have quite different appearances. In this paper, an efficient overlay text detection and extraction method is implemented which deals with complex backgrounds. Based on our observation that there exist transient colors between inserted text and its adjacent background. It is robust with respect to font size, style text, color, orientation and noise and can be used in a large variety of application fields such as mobile robot navigation vehicle license detection and recognition, object identification , document retrieving, etc. System is implemented using ARM 7 microcontroller. Extracted text is finally displayed on LCD.
Keywords: Optical character recognition (OCR), overlay text, transition map, video summarization, video information retrieval.
Full Issue
| View or download the full issue | PDF 1-14 |