Text area localization under complex-background using wavelet decomposition

In this paper, we propose a novel approach to determine the positions of text areas in images with complex background using wavelet decomposition and pseudo-motion of images. In our method, a fixed image is translated and provides a sequence of moving images-the pseudomotion sequence of image. In fact, we can consider the translation of an image to be a motion of eyeshot. When an image is translated, its wavelet coefficients will oscillate. From this property, we can locate the text areas in complex-background images. Experiments were conducted to demonstrate the performance of the method In the experiments, we detect the text areas of several different types of characters in images with multi-gray level complex backgrounds