Home // PATTERNS 2017, The Ninth International Conferences on Pervasive Patterns and Applications // View article

Obtaining Shape from Endoscope Image Using Medical Suture with Two Light Sources

Authors:
Hiroyasu Usami
Yuji Iwahori
Boonserm Kijsirikul
Manas Kamal Bhuyan
Aili Wang
Kunio Kasugai

Keywords: Shape from Shading; Endoscope; Point Light Source; Perspective Projection; Camera Calibration; Reflectance Parameter.

Abstract:
Obtaining polyp size and shape is important for the medical diagnosis. In this paper, 3-D shape reconstruction of computer vision technology is introduced in the medical diagnosis for this purpose. Some approaches based on Shape from Shading have been proposed for polyp in endoscope image. Previous approaches need some parameters such as depth parameter Z from endoscope lens to the surface point and reflectance parameter C. In the endoscope image, it is important to obtain these parameters for accurate polyp shape recovery. This paper proposes a new approach for obtaining parameters Z and C from one endoscope image where a medical suture is taken. Medical suture is used to estimate the horizontal plane locally and observation model of medical suture is used with the horizontal plane. Two light endoscope observation system is assumed to improve the accuracy to recover the polyp shape based on the actual endoscope and experiments are demonstrated to validate the proposed approach.

Pages: 103 to 108

Copyright: Copyright (c) IARIA, 2017

Publication date: February 19, 2017

Published in: conference

ISSN: 2308-3557

ISBN: 978-1-61208-534-0

Location: Athens, Greece

Dates: from February 19, 2017 to February 23, 2017