Improved Scene Text Recognition Using Fuzzy Based Method

Scene Text Recognition plays a major role in finding vital and valuable information from the scene. Text recognition involves detection, localization, tracking, extraction, enhancement and recognition of the text from the given image. However these text characters are difficult to be detected and recognized due to their deviation of size, font, style, orientation, alignment, contrast, varying color, textured background. Several techniques have been developed for efficient extraction of the text from an image. Among these techniques most efficient one is Scene Text Recognition utilizing Structure-Guided Character Detection and Linguistic Knowledge. Since the character models make utilization of both the local appearance and global structure information, the detection results are more reliable. However this method cannot detect text of varying font size. To overcome this drawback we have incorporate a fuzzy based segmentation.