Text Localization and Extraction in Images Using Mathematical Morphology and OCR Techniques

In the digitalization of the world, it becomes more and more important to extract text from image. Because text data present in images contain useful information for automatic annotation, indexing and structuring of images. Furthermore, text printed on the cover of magazine, signs, indicators, billboards etc always mixes with photos and designs. This kind of texts in scene images may take much information and thus need to separate text string from scene image. Hence, the extraction of texts in scene images is a difficult as well as challenging task. Recently, mathematical morphology based algorithm finds applications to extract texts from scene images. In this paper we proposed a technique for text extraction from an image. The process uses morphology and OCR techniques. The first, feature extraction stage analyzes the set of isolated characters and selects a set of features that can be used to uniquely identify characters. The performance depends upon the calculation of F-score. RRC and reduced noise level. Due to insufficiency of a single threshold value, we have divided input images into different clusters depending on the size of texts.