Text Location on Complex Background Using DWT and Morphology Operation

Text location has wide applications, such as image retrieval, video retrieval, etc. However, it is not a trivial task because of the complexity of the background. In this paper, we propose a method for text location in complex background that is based on wavelet decomposition and mathematical morphology. Firstly, the input image is decomposed using wavelet. Then sub-image which corresponds to high frequency in vertical direction is binarised. Finally, prior knowledge is used to locate the text region. Experimental results show that the proposed method is fast and effective.