Development of digital image retrieval technique using autocorrelogram and wavelet based texture

In this paper, we present the development of a digital image retrieval technique using autocorrelogram and wavelet based texture feature. Autocorrelogram is a color feature that is able to incorporate the spatial correlation of alike color and is tolerant to large changes in appearance, color, contrast, and brightness. A wavelet transform is used to analyze the textures that are characterized by their energy distribution in each sub-band. We propose an integration of the autocorrelogram and wavelet based texture to improve the performance of the image retrieval system. Experimental results suggest that the proposed integration offers much better performance than using the features separately.