Intrinsic layer based automatic specular reflection detection in endoscopic images.

Endoscopic images are used to observe the internal structure of the human body. Specular reflection (SR) images are mostly a consequence of the strong light and bright regions appearing on endoscopic images, which affects the performance of minimally invasive surgery. In this study, we propose a novel method for automatic SR detection based on intrinsic image layer separation (IILS). The proposed method consists of three steps. Initially, it involves the normalization of the image followed by the extraction of high gradient area, and the separation of SR is done on the basis of the color model. The image melding technique is utilized to reconstruct the reflected pixels. The experiments were conducted on 912 endoscopic images from CVC-EndoSceneStill. The results of accuracy, sensitivity, specificity, precision, Jaccard index, Dice coefficient, standard deviation, and pixel count difference show that the detection performance of the proposed method outperforms that of other state-of-the-art methods. The evaluation of the proposed IILS-based SR detection demonstrates that our method obtains better qualitative and quantitative assessments compared with other methods, which can be used as a promising preprocessing step for further analysis of endoscopic images.