Computer Vision, Graphics, and Image Processing
Hierarchical Image Analysis Using Irregular Tessellations
IEEE Transactions on Pattern Analysis and Machine Intelligence
CVGIP: Image Understanding
Adaptive Image Segmentation With Distributed Behavior-Based Agents
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIGMA: A Knowledge-Based Aerial Image Understanding System
SIGMA: A Knowledge-Based Aerial Image Understanding System
Yet Another Survey on Image Segmentation: Region and Boundary Information Integration
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
An Architecture of Object Recognition System for Various Images Based on Multi-Agent
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Distributed Markovian segmentation: Application to MR brain scans
Pattern Recognition
MRF model-based approach for image segmentation using a chaotic multiagent system
WILF'05 Proceedings of the 6th international conference on Fuzzy Logic and Applications
Automated segmentation of human brain MR images using a multi-agent approach
Artificial Intelligence in Medicine
Hi-index | 0.10 |
Reliability of vision systems may be enhanced by a good integration of prior knowledge and the cooperation between various image processing approaches. But the design of such a vision system is a challenging problem: carrying out the integration of many descriptive and operational knowledge induces control problems and then requires a suitable underlying software architecture. Cooperative image-situated agents provide an interesting atomic abstraction to carry out and process knowledge in a modular adapted and distributed manner, in order to avoid anarchic behaviours, we propose to map an irregular pyramid on the agents' society. The pyramid organizes and constraints the agents' population in a structured society so global constraints can be guaranteed. Autonomous agents may implement local processing adaptation and sophisticated cooperative behaviours. After a presentation of this new methodological approach, we present an evaluation on a computed tomography breast image segmentation. The agents' pyramid is compared with classical segmentation approaches, then we propose a global analysis of the system through a set of measures compared to an opinion poll in human society.