Text Recognition Using Poisson Filtering and Edge Enhanced Maximally Stable Extremal Regions

Text recognition in imagery gives more meaningful information, which makes it a relevant area of interest in different fields like , content based image retrieval, navigation, blind people assistance, intelligent transportation systems, vehicle testing etc. Text detection from the scene image is a process by which text zones are segmented from non-textual ones and they are arranged in accordance with their correct order of reading. Diverse text patterns and variant background interferences are the challenges that affect the reliability of text character extraction. A novel system for text detection and recognition in images is proposed in this paper. The proposed method uses Fractional Poisson enhancement for removing Laplacian noise of the input image. Then Edge-enhanced Maximally Stable Extremal Regions (MSERs) is obtained from the pre-processed image. Region filtering is used to filter non-text regions and is then recognized by an Optical Character Recognition (OCR) system. The result of this algorithm outperforms other existing methods in terms of Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) measurements. The method is evaluated using the standard ICDAR dataset consisting mostly real time images.