Parallel Image Component Labeling With Watershed Transformation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Artificial Life
Stigmergy, self-organization, and sorting in collective robotics
Artificial Life
Future Generation Computer Systems - Special issue on cellular automata: promise in computational science
Future Generation Computer Systems
Random walk approach to image enhancement
Signal Processing - Special section on digital signal processing for multimedia communications and services
Computing in nonlinear media and automata collectives
Computing in nonlinear media and automata collectives
Designing Evolware by Cellular Programming
ICES '96 Proceedings of the First International Conference on Evolvable Systems: From Biology to Hardware
Genetic Programming for Feature Detection and Image Segmentation
Selected Papers from AISB Workshop on Evolutionary Computing
A Multi-Agent System to Segment Living Cells
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Skeletonization: An Electrostatic Field-Based Approach
Skeletonization: An Electrostatic Field-Based Approach
A Shortest Path Search Algorithm Using an Excitable Digital Reaction-Diffusion System
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
An evolutionary autonomous agents approach to image featureextraction
IEEE Transactions on Evolutionary Computation
Special issue on Nature-inspired systems for parallel, asynchronous and decentralised environments
Multiagent and Grid Systems - Special Issue on Nature inspired systems for parallel, asynchronous and decentralised environments
A Distributed and Collective Approach for Curved Object-Based Range Image Segmentation
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
A new distributed approach for range image segmentation
CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
| Hi-index | 0.00 |
A multi-agent framework inspired by natural and physical systems is presented for data discovery and image enhancement. The input image is represented as a topographic landscape upon which a large population of independent simple, reactive, mobile agents resides. The local landscape configuration presents stimuli to each agent, influencing agent behaviour and resulting in changes in agent orientation and movement. Individual agents deposit a trail as they move and leave specific marks in response to stimuli above a certain threshold. The parallel interactions of the agent population and the image landscape result in emergent patterns of trails and marks being generated, corresponding to global (population level) perception of the original image. The emergent patterns exhibit image feature extraction and represent an indirect processing of the input image. External environmental pressures may be applied to the emergent patterns to further amplify the feature extraction. The framework represents a decentralised approach to image enhancement which is extensible. Different types of agent may be developed to perform different image processing functions, or other problems whose definition and solution may be represented as spatial patterns. Results including binary image processing, greyscale enhancement, colour image processing and related spatial processing problems are presented.