Feature Based Image Retrieval System using Zernike Moments and Daubechies Wavelet Transform

In image processing research field, image retrieval is extensively used in various application. Increasing need of the image retrieval, it is quiet most exciting research field. In image retrieval system, features are the most significant process used for indexing, retrieving and classifying the images. For computer systems, automatic indexing, storing and retrieving larger image collections effectively are a critical task. Nowadays several retrieval systems were implemented to overcome these issues but still there is a lack of speed and accuracy during image retrieval process. First, address the various issues on performance degradation of image retrieval then analyze and compare the methods and results in previous work. Second, discover the effective approach to be used to increase the accuracy of retrieval system significantly. This work provides a framework based on low level features extraction using Daubechies Wavelet Transform (DWT) and Zernike moments. Based on that features images are retrieved by using the distance measure. Zernike moments constitute a powerful shape descriptor due to its strength and narrative capability. Experimental results shows that our scheme provides significant improvement on retrieval accuracy compared to existing system based on the combination of both the color and edge features by using Discrete Wavelet Transform. In this paper, wang's image dataset is used for experiments.