High-order image subsampling using feedforward artificial neural networks

IEEE Transactions on Image Processing

Volumn 10, Issue 3, 2001, Pages 427-435

  Dumitras, Adriana ^a,b   Kossentini, Faouzi ^a,c  

^a IEEE   (United States)

^b AT AND T LABS RESEARCH   (United States)

^c UNIVERSITY OF BRITISH COLUMBIA   (Canada)

Author keywords

Feedforward neural network; High order subsampling; Pruning; Tridiagonally symmetrical

Indexed keywords

FEEDFORWARD ARTIFICIAL NEURAL NETWORKS; HIGH ORDER IMAGE SUBSAMPLING; HIGH SPEED PERFORMANCE TRADEOFFS; PRUNING; TRIDIAGONALLY SYMMETRICAL;

ALGORITHMS; EDGE DETECTION; FEATURE EXTRACTION; FEEDFORWARD NEURAL NETWORKS; IMAGE QUALITY; PATTERN MATCHING; PERFORMANCE; TREES (MATHEMATICS);

IMAGE PROCESSING;

EID: 0035279127     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/83.908518     Document Type: Article

References (20)

1. Feedforward neural network design with tridiagonal symmetry constraints
2. Image filtering using multiresolution representations
3. Multistage sampling structure conversion of video signals
4. A comparison of design methods for 2-D FIR orthogonal perfect reconstruction filter banks
5. Fast and high performance image subsampling using feedforward neural networks
6. Feedforward neural network design with application to image subsampling
7. The analysis and design of multidimensional FIR perfect reconstruction filter banks for arbitrary sampling lattices
8. The commutativity of up/downsampling in two dimensions
9. Optimal brain damage
10. The effects of a visual fidelity criterion on the encoding of images
11. Evaluation of contrast sensitivity functions for the formulation of quality measures incorporated in halftoning algorithms
12. Image quality assessment based on a degradation model