Supervised Tissue Classification from Color Images for a Complete Wound Assessment Tool

This work is part of the ESCALE project dedicated to the design of a complete 3D and color wound assessment tool using a simple free handled digital camera. The first part was concerned with the computation of a 3D model for wound measurements using uncalibrated vision techniques. This paper presents the second part which deals with color classification of wound tissues, a prior step before to combine shape and color analysis in a single tool for real tissue surface measurements. As direct pixel classification proved to be inefficient for tissue wound labeling, we have adopted an original approach based on unsupervised segmentation prior to classification, to improve the robustness of the labeling step by considering spatial continuity and homogeneity. A ground truth is first provided by merging the images collected and labeled by clinicians. Then, color and texture tissue descriptors are extracted on labeled regions of this learning database to design a SVM region classifier, achieving 88% success overlap score. Finally, we apply unsupervised color region segmentation on test images and classify the regions. Compared to the ground truth, segmentation driven classification and clinician labeling achieve similar performance, around 75 % for granulation and 60 % for slough.