Abstract
In this paper, we propose an affine transform based vector quantization (ATVQ) technique for image coding applications. Vector quantization (VQ) is intrinsically superior to predictive coding, transform coding, and other suboptimal and ad hoc procedures. The limitation of VQ is the very large codebook that must be generated and stored. The proposed affine transform based vector quantization technique addresses this problem. The image to be coded is partitioned into disjoint square blocks. Each block is regarded as a vector and is encoded by searching through a set of affine transforms and a codebook of templates. The transform-template pair that can reconstruct an approximate input vector with minimum distortion is selected. The parameters and the index of the affine transform and the index of the template constitute the codeword of the input vector. In decoding, the image vector is reconstructed by applying the inverse of the affine tranform on the template. We present a clustering procedure to design the codebook that comprises the representative input vectors. The clustering is based on two criteria: a vector is placed in a cluster if it is nearer to the cluster centre than the other cluster centres and two vectors are grouped together if one is an affine transformed version of the other. ATVQ can reconstuct more input vectors without any distortion than conventional VQ can reconstruct, using the same codebook. Simulation results show that the technique performs well using a universal codebook. This technique is also suitable for progressive image transmission as its performance is good at very low bit rates.
Original language | English (US) |
---|---|
Pages (from-to) | 1639-1648 |
Number of pages | 10 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 2094 |
DOIs | |
State | Published - 1993 |
Externally published | Yes |
Event | Visual Communications and Image Processing 1993 - Cambridge, MA, United States Duration: Nov 7 1993 → Nov 7 1993 |
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering