Fast Encoding Algorithm for Vector Quantization

In this paper, we present a new and fast encoding algorithm (FEA) for vector quantization. The magnitude (sum of the components of a vector) feature of the vectors is used in this algorithm to improve the efficiency of searching. Sorting of the magnitude values enhances the searching. As the values are sorted, the searching can be terminated in advance to reduce the time needed to locate the representative code vector. For a codebook of size M (M generally being 128/256/512/1024), M distortion calculations are performed. But in the proposed method, only 11 distortion computations are done irrespective of the size of the codebook. The time taken to locate the representative codevector is significantly reduced from 0.77 seconds to 0.07 seconds on an average. The experiments were carried over with codebooks of sizes 128, 256, 512 and 1024 with the standard images Lena, Boats, Cameraman and Bridge.