A different image content-based retrievals using OCR techniques

Abstract

It is very difficult to retrieve image from large no of database which contain some message on it. The OCR techniques are becoming very efficient techniques for external and fast retrievals. The OCR technique search image based on data or text written on image. It search image or message contain in the image OCR the mechanical or electronic conversion of images of typed, handwritten or printed text, whether from scanned document, a scene-photo. For that Tesseract will use. After recognizing text from image by OCR, it will store that message in any file. After that we used Boyer-Moore string search algorithm, for searching string stored in file.