| With the rapid development of Internet and technologies of computer and multimedia, information of all kinds of images increases dramatically. An efficient approach to query these images becomes more and more important in the area of retrieval research. Content based image retrieval (CBIR) is one of the key technologies.In CBIR, image retrieval is discussed in the visible field, including semantics and visual characteristic of the multimedia information, such as color, texture, shape and etc. Extracting image color characteristics is studied in this paper. The main contributions of this dissertation are summarized as follows:1. Introduction of blocking wavelet transformation. The wavelet transformation can decompose the image to the sum of sub-image having different frequency. These sub-images separately represent the different structure of the image. The main structure information and the detail information of the image can be conveniently extracted. Simultaneously, the image's spatial characteristic can be represented by the blocking technology, which can be used to enhance the performance of the algorithm.2. Introduction of particle swarm optimization. The particle swarm optimization, a new community intelligence method, originates from the social psychology and the artificial life, and it is one of the most important tools to simulate the society interaction between individuals. It has quick convergence rate and strong versatility. Particle swarm optimization is used in this paper to improve blocking wavelet transform-based image retrieval. It has expedited the speed of the algorithm.3. Design and implementation of wavelet & PSO-based image retrieval. The wavelet & PSO-based image retrieval is proposed by combining blocking wavelet transformation and particle swarm optimization with color histogram-based image retrieval. This algorithm using blocking wavelet transformation and particle swarm optimization can get higher retrieval performance and quicker speed. |
PDF Full Text Request