Image retrieval based on salient points in compressed domain
基于压缩域显著点的图像检索方法

Compressed-domain image analysis and processing has been an active area in the fields of multimedia research.A fast image retrieval method based on salient points from DCT(Discrete Cosine Transform) compressed domain was presented in this paper,which direct computes the robust salient points from none-zero DCT coefficients without full decompression,so that a lot of computational cost was saved.Experimental results show that the image features obtained based on salient points are suited for image retrieval because of their powerful abilities to characterize the image.