Fast codebook search algorithms based on tree-structured vector quantization
Pattern Recognition Letters
Full-Searching-Equivalent Vector Quantization Using Two-Bounds Triangle Inequality
Fundamenta Informaticae
Efficient Fingercode Classification
IEICE - Transactions on Information and Systems
Accelerating VQ-based codeword search on the basis of partial search strategy
Computer Standards & Interfaces
Performance improvement of vector quantization by using threshold
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III
Hardware accelerator for vector quantization by using pruned look-up table
ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part IV
Full-Searching-Equivalent Vector Quantization Using Two-Bounds Triangle Inequality
Fundamenta Informaticae
| Hi-index | 0.00 |
For fast vector quantization (VQ) encoding, we present in this paper a new method to speed up the calculation of the squared Euclidean distance between two vectors. We call it the approximated look-up table (ALUT) method. This method considers the frequency of each squared number that occurs in the equation of squared Euclidean distances, and generates a more practical table to store squared numbers. ALUT makes use of this table and some simple operations to speed up the calculation of squared Euclidean distances. From the VQ simulation results, we see that ALUT saves memory and produces better image quality compared with some other methods. It is a suitable method for VLSI implementation