作者: S.-W. Ra , J.-K. Kim
DOI: 10.1109/82.257335
关键词:
摘要: A new fast search algorithm for vector quantization using the mean of image vectors is proposed. The codevectors are sorted according to their component means, and codevector having minimum Euclidean-distance a given input starts with one mean-distance it, making use our observation that two close each other in most real images. then made terminate as soon simple yet novel test reports any remaining codebook should have larger Euclidean distance. Simulations show number calculations can be reduced low fourth achievable by an known partial distance method. >