Estimation of Ear Parameters Applicable to Otoplasty Surgery

Abstract

Analysis of facial color images is very important as a result of its numerous applications in facial surgeries. The development of different tools in the field of facial surgery analysis has helped surgeons before and after surgery. In this article, an Active Contour Model (ACM) based on Local Gaussian Distribution Fitting (LGDF) is introduced for the contour extraction of the ear area. The LGDF model is a region-based method in the Active Contour Model that unlike other models such as the Chan-Vese is not sensitive to intensity inhomogeneity of the image. After the contour extraction of the ear area, in the second step, with the four landmarks detection, ear parameters containing: length, width and external angle of ear were measured for analysis in the Otoplasty surgery. The proposed algorithm was evaluated on the AMI and Sahand University of Technology (SUT) databases. The proposed algorithm has an accuracy of %96.432, %97.423 and %85.546 in the AMI database and an accuracy of %98.381, %97.237 and %87.864 in the SUT database for the length, width and external angle of the ear parameters, respectively.