Fusion of Multi-view Tissue Classification Based on Wound 3D Model
ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
Imaging technologies applied to chronic wounds: a survey
Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies
| Hi-index | 0.00 |
Abstract: This paper presents a methodology for the segmentation and analysis of the tissues in color images of leg ulcers. The segmentation is obtained through an automatic analysis made in the RGB and SI channels by changing from the RGB color space to the HSI color space. The aim is to determine which of the five channels have the characteristic that will make the segmentation process more efficient. After the analysis, the selected channel is segmented and used as a mask over the original image, allowing that only the inner tissues of the wound be analyzed. The analysis is done through pre-determined functions that attribute membership grade for each processed pixel as well as its level of engagement in a specified tissue class. The article also shows the results obtained from both the segmentation and analysis of tissues using the proposed method.