A frame reduction system based on a color structural similarity (CSS) method and Bayer images analysis for capsule endoscopy

作者：

Highlights：

• A colour structural similarity (CSS) method combined color textures and structural features.

• Bayer images is an optimal approach, achieving significant reduction ratios, reduced computational time.

• Modified local binary pattern (LBP) method to extract more precise structural information.

• The quality of images produced by CSS method did not affect bleeding detection sensitivity when compared to the original images as confirmed by the specialist.

摘要

•A colour structural similarity (CSS) method combined color textures and structural features.•Bayer images is an optimal approach, achieving significant reduction ratios, reduced computational time.•Modified local binary pattern (LBP) method to extract more precise structural information.•The quality of images produced by CSS method did not affect bleeding detection sensitivity when compared to the original images as confirmed by the specialist.

论文关键词：Frame reduction,Capsule endoscopy,Abnormality detection,Structural similarity,Clinical assessment

论文评审过程：Received 20 July 2018, Revised 31 October 2018, Accepted 27 December 2018, Available online 29 December 2018, Version of Record 10 January 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2018.12.008