Open AccessIterative deep learning for improved segmentation of endoscopic images
Author(s) -
Sharib Ali,
Nikhil Kumar Tomar
Publication year - 2021
Publication title -
nordic machine intelligence
Language(s) - English
Resource type - Journals
ISSN - 2703-9196
DOI - 10.5617/nmi.9137
Subject(s) - segmentation , thresholding , artificial intelligence , computer science , inference , image segmentation , iterative learning control , computer vision , scale space segmentation , iterative method , pattern recognition (psychology) , image (mathematics) , algorithm , control (management)
Iterative segmentation is a unique way to prune the segmentation maps initialized by faster inference techniques or even unsupervised traditional thresholding methods. We used our previous feedback attention-based method for this work and demonstrate that with optimal iterative procedure our method can reach competitive accuracies in endoscopic imaging. For this work, we have applied this segmentation strategy for polyps and instruments.