Segmentation of specular reflections is an essential step in endoscopic image analysis; it affects all further processing steps\r\nincluding segmentation, classification, and registration tasks. The dichromatic reflectance model, which is often used for specular\r\nreflection modeling, is made for dielectric materials and not for human tissue.Hence, most recent segmentation approaches rely on\r\nthresholding techniques. In this work, we first demonstrate the limited accuracy that can be achieved by thresholding techniques\r\nand propose a hybridmethod which is based on closed contours and thresholding. The method has been evaluated on 269 specular\r\nreflections in 49 images which were taken from27 real laparoscopic interventions. Our method improves the average sensitivity by\r\n16% compared to the state-of-the-art thresholding methods.
Loading....