Color image segmentation applied to medical domain
IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Automatic detection system of cervical cancer cells using color intensity classification
Proceedings of the 15th WSEAS international conference on Computers
CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
Hi-index | 0.00 |
The National Cancer Institute has collected a large database of digitized 35mm slides ofthe uterine cervix, the idea being to build a system enabling to study the evolution of lesionsrelated to cervical cancer. In taking the first few steps towards this goal, the objective ofthis work is to develop and evaluate methodologies required for visual-based (i.e. content-based) indexing and retrieval that substantially improve information management of such a database. In this paper we model the properties of three tissue types using color andtexture features, and use these models for image segmentation. Statistical modeling andsegmentation tools are used for the task.