Specular Highlight Detection from Endoscopic Images for Shape Reconstruction

Abstract

Endoscopy provides a convenient way to access the inner structures of various organs. The endoscopic images provide an immediate observation and help diagnosis and therapy. Shape reconstruction from endoscopic images further provides real scale factor for image-guided navigation. However, specular highlights, bright patches of light appearing on the imaged surface, mask the real image texture and result in erroneous reconstruction. Therefore, the detection of specular highlights is essential for accurate reconstruction. In this study, we divide the images into homogeneous regions by color quantization and spatial segmentation. Then, a thresholding technique based on histogram of the pixel intensity values is used. Finally, we check the gray level consistency for each region to avoid over segmentation. The experimental results show that the proposed method can achieve successfully detection.