Learn More
Sparse representation has been proved to be very efficient in machine learning and image processing. Traditional image sparse representation formulates an image into a one dimensional (1D) vector which is then represented by a sparse linear combination of the basis atoms from a dictionary. This 1D representation ignores the local spatial correlation inside(More)
The conventional sparse model relies on data representation in the form of vectors. It represents the vector-valued or vectorized one dimensional (1D) version of an signal as a highly sparse linear combination of basis atoms from a large dictionary. The 1D modeling, though simple, ignores the inherent structure and breaks the local correlation inside(More)
In this paper, a new multiple description image coding scheme using directional lifting transform is proposed. The basic idea is to divide an image into two descriptions with quincunx segmentation. The traditional spatial domain multiple description image coding techniques usually result in the very low coding efficiency. To tackle this problem, we propose(More)
Sparse representation provides a new method of generating a super-resolution image from a single low resolution input image. An over-complete base for sparse representation is an essential part of such methods. However discovering the over-complete base with efficient representation from a large amount of image patches is a difficult problem. We make(More)
In this paper, a new low cost texture-synthesis based video coding scheme is presented for H.264/AVC, which is well-suited for a specific class of stochastic texture like water, and cloud, etc. We give a solution to two key problems that bother the application of texture synthesis in video coding for a long time. One is the synthesis cost of the decoder,(More)
Screen contents with complex structure contain random combination of texts, graphics and camera-captured images, which makes them difficult to be compressed efficiently by traditional video codecs. In this paper, we propose a 2-D dictionary based scheme to exploit the repeated patterns on screen content. In the proposed scheme, the current block is(More)
We demonstrated in this paper the shape-controlled synthesis of ZnIn2S4, CuInS2, and CuInSe2 nano- and microstructures through a facile solution-based route. One-dimensional ZnIn2S4 nanotubes and nanoribbons were synthesized by a solvothermal method with pyridine as the solvent, while ZnIn2S4 solid or hollow microspheres were hydrothermally prepared in the(More)