Study on text information extraction algorithm of image in wavelet domain
Lei Zhu · Journal of Harbin University of Commerce · 2008
This paper studies text extraction models for images based on wavelet transforms,a text extraction algorithm for images in wavelet domain is proposed.For the algorithm,two-dimensional wavelet transform is used to the image firstly and slipping windows are set to scan high-frequency subband,through computing the wavelet texture feature of the image in slipping windows,k-means cluster algorithm is used to extract text area.The edge detection are put on the text area and original image respectively.According to the character of text area,the edge detection are located exactly.The text and background are segmented.The experimental result shows that the algorithm can extract texts information with different languages,fonts,size from the background image exactly.