An Automatic Extraction Algorithm for Captions in Video Images
Jiao U-cheng · Systems engineering and electronics · 2003
The automatic video annotation is a key module of the video indexing and retrieval system, and the extraction and location of captions are important steps for video annotation. An automatic extraction algorithm for video caption by combining the wavelet transform and the fuzzy clustering neural network is presented. This algorithm is especially applicable to extracting and locating of Chinese captions. The experimental results show that the proposed algorithm can achieve an accuracy of about 92% in caption detection and location.