JPEG image retrieval based on salient points
Zhang Wenyin · 2005
A new JPEG image retrieval method based on salient points extracted from DCT compressed domain is proposed in this paper. Using a small part of significant DCT coefficients, we provide a robust self-adaptive salient point extraction algorithm which is very robust to noise, rotation, translation and scale and most of common image processing such as lighting, darkening, blurring, compressing and so on. Based on salient points, three local image features, color histogram, LBP histogram and shape invariant moments are computed to represent local properties of the image for retrieval. Our system reduces the amount of data to be processed and only needs to do partial decompression, so it can accelerate the work of image retrieval. The experimental results also demonstrate it improves performance both in retrieval efficiency and effectiveness.