Abstract
A new, non-iterative post-processing approach is proposed for real-time reduction of blocking effects. The proposed approach has the merits of being fully compatible with the JPEG standard and requiring no additional transmission overhead. This is achieved by training feed-forward single-layer neural networks to restore classified block boundaries of JPEG-encoded images. Classification is based on the intensity distribution of the pixels on either sides of the block boundaries. This approach can be easily implemented and simulation results demonstrate the superiority of the proposed approach in terms of signal-to-noise ratio improvement and processing time as compared with various well-known post-processing approaches.
Original language | English |
---|---|
Pages (from-to) | 337-346 |
Number of pages | 10 |
Journal | Signal Processing |
Volume | 65 |
Issue number | 3 |
DOIs | |
Publication status | Published - 31 Mar 1998 |
Keywords
- Blocking effect
- Classification
- Frequency-sensitive competitive learning
- Image restoration
- JPEG
- Neural network
ASJC Scopus subject areas
- Control and Systems Engineering
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering