Improved Feature Point Pair Purification Algorithm Based on SIFT During Endoscope Image Stitching

Frontiers in Neurorobotics

Lirong Yin¹  Bo Yang²  Yan Liu²  Shan Liu²  Rongrong Hu²  Jiawei Tian²  Wenfeng Zheng² 

[1] Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA, United States;School of Automation, University of Electronic Science and Technology of China, Chengdu, China;

关键词: endoscope;    feature point matching;    image mosaic;    SIFT algorithm;    K-nearest;    RANSAC;   

DOI  :  10.3389/fnbot.2022.840594

来源: DOAJ

【 摘 要 】

Endoscopic imaging plays a very important role in the diagnosis and treatment of lesions. However, the imaging range of endoscopes is small, which may affect the doctors' judgment on the scope and details of lesions. Image mosaic technology can solve the problem well. In this paper, an improved feature-point pair purification algorithm based on SIFT (Scale invariant feature transform) is proposed. Firstly, the K-nearest neighbor-based feature point matching algorithm is used for rough matching. Then RANSAC (Random Sample Consensus) method is used for robustness tests to eliminate mismatched point pairs. The mismatching rate is greatly reduced by combining the two methods. Then, the image transformation matrix is estimated, and the image is determined. The seamless mosaic of endoscopic images is completed by matching the relationship. Finally, the proposed algorithm is verified by real endoscopic image and has a good effect.

【 授权许可】

Unknown