Date of Graduation


Document Type


Degree Name

Bachelor of Science

Degree Level



Computer Science and Computer Engineering


Gauch, John

Committee Member/Reader

Gauch, Susan

Committee Member/Second Reader

Panda, Brajendra


Colonoscopy images contain specular highlights that occur as a result of the tiny camera on the colonoscope being perpendicular to the image location. These specular highlights may prevent the Gastroenterologist from having a full picture of the patient’s condition and potentially giving an early diagnosis. The purpose of my honors research is to remove the specular highlights from these colonoscopy images.

The process to achieve the above objective involves two steps. The first step would require locating the specular highlights in the image through image segmentation. For this purpose, information from nearby x and y pixels may be utilized. The second step consists of using image restoration to fill in the specular regions. The removal of these specular highlights refines the colonoscopy image and allows useful information to be deduced by the physician.


Image Processing, Image Segmentation, Region Growing, Background Subtraction, Image Restoration, Colonoscopy Images

Included in

Engineering Commons