Training cellular automata for image processing

Authors:
Paul L. Rosin
Affiliations:
Cardiff School of Computer Science, Cardiff University, Cardiff, UK
Venue:
SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
Year:
2005

Citing 10
Cited 4

New and efficient cellular algorithms for image processing

CVGIP: Image Understanding
Floating search methods in feature selection

Pattern Recognition Letters
Analyzing nonconvex 2D and 3D patterns

Computer Vision and Image Understanding
A fast parallel algorithm for thinning digital patterns

Communications of the ACM
Evolving two-dimensional cellular automata to perform density classification: a report on work in progress

Parallel Computing - Special issue on cellular automata: from modeling to applications
An Evaluation of Parallel Thinning Algorithms for Character Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Theory of Self-Reproducing Automata

Theory of Self-Reproducing Automata
Discovery by genetic programming of a cellular automata rule that is better than any known rule for the majority classification problem

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Parallel Image Processing by Memory-Augmented Cellular Automata

IEEE Transactions on Pattern Analysis and Machine Intelligence
Application of partition-based median type filters for suppressing noise in images

IEEE Transactions on Image Processing

Real-time disparity map computation module

Microprocessors & Microsystems
Evolutionary Cellular Automata Based-Approach for Edge Detection

WILF '07 Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory
An Approach to Searching for Two-Dimensional Cellular Automata for Recognition of Handwritten Digits

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
On solving edge detection by emergence

IEA/AIE'06 Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Experiments were carried out to investigate the possibility of training cellular automata to to perform processing. Currently, only binary images are considered, but the space of rule sets is still very large. Various objective functions were considered, and sequential floating forward search used to select good rule sets for a range of tasks, namely: noise filtering, thinning, and convex hulls. Several modifications to the standard CA formulation were made (the B-rule and 2-cycle CAs) which were found to improve performance.