Text detection based on wavelet transform
Jie He, Fei Gao, Qing Nie · China-Ireland International Conference on Information and Communications Technologies (CIICT 2008) · 2008
In this paper, an algorithm is proposed which can automatically detect text embedded in images and video frames in different sizes, fonts and colors .It is performed by these steps: Firstly, it performed wavelet transform in different color channels; Secondly, a sliding window is moved over the transformed images, estimate feature vector of each window; then the k-means algorithm is chosen to classify the image into text candidates and background. Finally, the detected text candidates undergo the connected-component-based analysis to refine their location.