원문정보
초록
영어
In present research, the image feature based on adaptive wavelet has been widely used in the content-based image retrieval field. However, there is a common problem in these methods, which is to describe different query images with the same wavelet basis. In order to improve the adaptability of the image retrieval technology, we design different image basis for different query images, to achieve characterizing the feature-changing of different image categories with the adjustable distance measure. We also use the approximate Taylor expansion to reduce the seeking time of the characterization image and the characterization derivative image. As the experimental results have shown that, the new image retrieval technology with high adaptability can improve the retrieval performance greatly.
목차
1. Introduction
2. Feature Extraction based on Given Wavelet Filter
3. Establishment of Characterization Image
3.1. Wavelet Filter Space
3.2. Characterization Image and Characterization Derivative Image
3.3. Approximate Characterization Image
3.4. Immutability of the Characterization Image and its Derivative
3.5. Building Steps of Characterization Image
4. Image Retrieval Process
5. Experimental Results and Analysis
6. Conclusion
Acknowledgements
References