Open AccessNon-interactive object extraction based on saliency detection
Author(s) -
Ting Pa,
Xuan Wang,
Shouxun Liu
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/612/3/032130
Subject(s) - segmentation , computer science , artificial intelligence , computer vision , object (grammar) , image segmentation , segmentation based object categorization , scale space segmentation , pattern recognition (psychology) , object detection , region growing
In traditional content-based image retrieval (CBIR), it is very important to segment the regions of interest for retrieval. In order to realize the non-interactive target region segmentation, this paper proposes the object segmentation based on significance region detection. The Grab Cut segmentation algorithm is initialized through the detection of the significance region, and the interactive operation is removed. The segmentation precision of the algorithm proposed in this paper is 89.51%.