An Image Retrieval Algorithm Based on Block-Edge-Pattern Histogram
Kai Qiu · 2006
In this paper,we propose a new image retrieval algorithm based on block edge patterns.Block edge patterns are extracted respectively from each 8×8 block of image.Then a 3-D or 4-D histogram is constructed by utilizing block edge patterns to retrieve images inside image databases.Because the edge orientation of each block can be estimated in discrete cosine transform (DCT),it will reduce the complexity of evaluating edge orientation.In comparison with ex- isting representative techniques,the experimental results show the superiority of the proposed algorithm in terms of re trieval precision and processing speed.