Image retrieval method based on color and edge features
Zhibin Zhang · Journal of Computer Applications · 2012
In order to improve the effectiveness and efficiency of the Content-Based Image Retrieval(CBIR),in this paper,a new method was proposed.Both color feature and edge feature were used in this method.At first,RGB image was departed into several sub-images.Then,color feature and edge feature were extracted from every sub-image,where edge feature was acquired by utilizing the Moment Preserving(MP) edge detection.Combining the above two features,an effective and efficient image retrieval method was obtained.The experimental results show that the proposed method has higher precision and faster speed than Cheng's two methods.Compared with Cheng's two methods,retrieval time of the method proposed in this paper is its 10% and 3%,and retrieval precision has been improved by 20%.