Image retrieval based on improved Canny edge detection algorithm

The edge detection algorithm is the key problem of image processing. The tradition Canny edge detection algorithm is analyzed and evaluated. In order to avoid the influence of defects coming from Canny algorithm, an improved Canny edge detection algorithm is proposed in this paper. The algorithm takes use of Gaussian filter to eliminate the noise. It calculated preserving the more edge information while filtering the noise. And the algorithm could be applied in image retrieval. The simulation results show that the method not only can detect more detail of the edge, but also can improve the image retrieval performance.