Enhancement of hand held device captured document images with phase preservation

Abstract

Enhancement of text information from the images captured by mobile camera is a very challenging task due to the high variation between the background and the foreground that contains shadows, poor contrast and non uniform illumination. In this paper, denoising along with binarization algorithm that uses phase congruency features is proposed to extract the text information from the document images. In the pre-processing step, the image is de-noised to preserve all features present in the document image. In the next step, the phase congruency map is obtained from the document image and it is combined with the image obtained in the pre-processing step. The post-processing step is to improve the quality of the texts by using morphological operations. Experimental results shows that the proposed method performs well in enhancing the document images captured using hand held devices.