Video Compression Based on Orthonormal Matching Pursuits

Abstract- Video coding schemes based on matching pursuits Matching pursuit is a greedy algorithm that decomposes a have been shown to have better coding efficiency and perceptual signal into a linear combination of bases, but as the bases quality at low bit rates than DCT-based video coding schemes. are not independent, there are many ways to represent a Matching pursuit is a greedy algorithm that decomposes a signal into a linear combination of bases within an overcomplete dictio- signal. The algorithm selects the maximum basis to represent a nary. However, as the bases are not independent, the redundancy signal at each iteration; however, it can not guarantee optimal in linear combinations increases as the number of iterations linear combinations. In fact, since the bases are redundant, of matching pursuit increases. In this paper, we introduce as the number of iterations increases, the redundancy in an orthonormal matching pursuit algorithm that reduces the linear combinations also increases. To solve this problem, an redundancy between bases and represents a signal by a linear combination of bases more efficiently. Our proposed updated full orthogonal matching pursuit algorithm has been proposed to search matching pursuit algorithm has been shown to be effective reduce the redundancy between bases [2]. At each iteration, in both coding performance and computational complexity. Based the projection of bases on the selected orthogonal basis is on this algorithm, we present an orthonormal matching pursuit removed, but it does not normalize the orthogonal basis; there-video coding scheme that achieves a more efficient coding fore, the basis selection unfair. To ensure that all bases hav