Using Point Descriptors for ReconstructingThree-Dimensional Wounds
Chronic Wounds, Points Descriptors, 3D reconstruction
Ulcer is the generic name given to any lesion in the cutaneous or mucosal tissue. These lesions culminate in a epithelial rupture, so that deeper tissues are exposed. The problem to be solved in the project in which this work is part of, refers to the development of efficient computational tools for the complete monitoring of wound and chronic treatment. This monitoring is of fundamental importance to determine the evolution of the patient's treatment. Thus, this work proposes to perform a quantitative analysis of the three-dimensional reconstructions obtained using Structure from Motion with the aid of 6 different point descriptors. The specific problem tackled is that of determining which descriptor(s) are more efficient and accurate for the three-dimensional reconstruction of chronic wounds, between the descriptors SIFT, SURF, ORB, BRIEF, FAST and DRINK. The main objective of this work is determining which point descriptors are more adequate for this task, when taking into account accuracy and computational cost-benefit.