CNN architectures for constrained diffusion based locally adaptive image processing

International Journal of Circuit Theory and Applications

Volumn 30, Issue 2-3, 2002, Pages 313-348

  Rekeczky, Csaba ^a  

^a PÁZMÁNY PÉTER CATHOLIC UNIVERSITY   (Hungary)

Author keywords

Adaptive image segmentation; Cellular neural network; CNN Universal Machine; Constrained diffusion; Image reconstruction; ODE; PDE

Indexed keywords

ALGORITHMS; CONSTRAINT THEORY; EDGE DETECTION; GAUSSIAN NOISE (ELECTRONIC); IMAGE RECONSTRUCTION; IMAGE SEGMENTATION; LOW PASS FILTERS; MORPHOLOGY; ORDINARY DIFFERENTIAL EQUATIONS; PARTIAL DIFFERENTIAL EQUATIONS; VLSI CIRCUITS;

BACKGROUND ILLUMINATION;

CELLULAR NEURAL NETWORKS;

EID: 0036494544     PISSN: 00989886     EISSN: None     Source Type: Journal    
DOI: 10.1002/cta.202     Document Type: Article

References (58)

1. Cellular neural networks: Theory
2. Cellular neural networks: Applications
3. The CNN paradigm
4. The CNN universal machine: An analogic array computer
5. CNN universal chip in CMOS technology
6. A 0.8 μm CMOS 2-D programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage
7. A 16 × 16 cellular neural network universal chip: The first complete single-chip dynamic computer array with distributed memory and with grey-scale input-output
8. Minimum size 0.5 micron CMOS programmable 48 by 48 CNN test chip
9. A 64 × 64 CNN universal chip with analog and digital I/O
10. A 48 by 48 CNN chip operating with B/W images
11. Classes of analogic algorithms and their practical use in complex image processing tasks
12. Dynamic analogic algorithms for complex recognition task - A first step towards the bionic eyeglass
13. Spatial-logic algorithms using basic morphological analogic CNN operations
14. Rotation invariant detection of moving and standing objects using analogic cellular neural network algorithms based on ring-codes
15. Spatio-temporal non-linear filtering and endocardial boundary detection in echocardiography
16. Computing with front propagation: Active contour and skeleton models in continuous-time CNN
17. Intelligent image resolution enhancement by the CNN universal machine and its relevance to TV picture enhancement
18. Smart image scanning algorithms for the CNN universal machine
19. Morphology and autowave metric on CNN applied to bubble-debris classification
20. CNN-based difference-controlled adaptive non-linear image filters
21. CNN: A vision of complexity
22. The analogic cellular neural network as a Bionic Eye
23. Resistive grid image filtering: Input/output analysis via the CNN framework
24. Methods for image processing in cellular neural networks: A tutorial
25. Design of linear cellular neural networks for motion sensitive filtering
26. Implementation of binary and grey-scale morphology on the CNN universal machine
27. Order statistic filtering with cellular neural networks
28. Scale-space and edge detection using anisotropic diffusion
29. Theory of edge detection
30. Scale-space filtering
31. The structure of images
32. A computational approach to edge detection
33. Image selective smoothing and edge detection by non-linear diffusion
34. Biased anisotropic diffusion - A unified regularization and diffusion approach to edge detection
35. Non-linear anisotropic filtering of MRI data
36. Image selective smoothing and edge detection by non-linear diffusion. II
37. Propagation and its failure to coupled systems of discrete excitable cells
38. The effects of a visual fidelity criterion on the encoding of images
39. A non-linear model for the spatial characteristics of the human visual system
40. On the role of observer and a distorsion measure in image transmission
41. Subjective image fidelity metric base on bit allocation of the human visual system in the DCT domain
42. A survey of thresholding techniques
43. Comparing images using the hausdorff distance
44. A wave approach to pattern recognition (with application to optical character recognition)
45. Autowave principles for image processing
46. Markov random field image segmentation using cellular neural network
47. A fast fixed point learning method to implement assocative memory on CNNs
48. A 0.5 μm CMOS CNN analog random access memory chip for massive image processing
49. The computational infrastructure of analogic CNN computing - Part I: The CNN-UM chip prototyping system