Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
A fast classification based method for fractal image encoding
Image and Vision Computing
Study on huber fractal image compression
IEEE Transactions on Image Processing
DCT based simple classification scheme for fractal image compression
Image and Vision Computing
A Hybrid Fast Fractal Image Encoding
TAAI '10 Proceedings of the 2010 International Conference on Technologies and Applications of Artificial Intelligence
Hi-index | 0.00 |
Fractal block coding method is based on a large amount of self-similarity which is exhibited in the image. In encoding phase of fractal block coding method, each range block will find its best matching domain block in domain pool by a search scheme. However, fractal block encoding consumes a lot of time in searching the best matching domain block. If the number of domain blocks can be trimmed down, the searches can speedup. In this regard, we proposed three elaborative designed factors for the fitness function in particle swarm optimization (PSO) and used this PSO to indentify the significant domain blocks. Consequently, our proposed method would reduce the number of domain blocks based on the result of optimization and achieve the goal of speeding up the search. This paper compared the search complexity of fractal block coding method and the proposed method based on the number of search. The search complexity of the proposed method is much improved than that of the fractal block coding method. The experimental results also indicate that the proposed method can markedly reduce the number of search in encoding phase and the quality of image after encode is acceptable to human eyes.