Text in images contains useful information which can be used to fully understand images .This paper proposes an unified method to segment a text region from images such as Scene text images , Caption text & Document images using Contourlet transform . Contourlets not only possess the main features of wavelets (namely, multiscale and time-frequency localization), but also offer a high degree of directionality and anisotropy. It decomposes the image into set of directional sub bands with texture details capture in different orientations at various scales. As the contourlet transform is not shift-invariant , non subsampled contourlet transform NSCT is used here to extract text regions from heterogeneous images. Proposed system is tested on various kind of images & shown promising result.

Caption text images, Directional filter bank, Laplacian Pyramid, Non subsampled Contourlet transform, Scene text images, Text region extraction