Share Email Print

Proceedings Paper

Unsupervised multi-class co-segmentation via joint object detection and segmentation with energy minimization
Author(s): Lei Li; Xuan Fei; Zhuoli Dong; Dexian Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Multi-class co-segmentation is a challenging task because of the variety and complexity of the objects and images. To get more accurate object proposals is the key step for the existing co-segmentation methods to obtain better performance. In this paper, we propose a novel method to co-segment multiple regions from a group of images in an unsupervised way. The key idea is to discover unknown object proposals for each image via joint object detection and object-level segmentation. First, object proposals of each image are generated by object-like windows (or boxes) and object-level segmentation using graph cuts, and two Gaussian mixture models (GMMs) are employed to characterize the object proposals for all images and single image, respectively. Then, a weighted graph for each image is constructed on super-pixel level, and multi-label graph cuts with global and local energy is employed to obtain the final co-segmentation results. In contrast to previous methods, our method could obtain the object proposals with high objectness by object-level segmentation. Experimental results demonstrate the good performance of the proposed method on the multi-class co-segmentation.

Paper Details

Date Published: 14 December 2015
PDF: 8 pages
Proc. SPIE 9812, MIPPR 2015: Automatic Target Recognition and Navigation, 981214 (14 December 2015); doi: 10.1117/12.2210737
Show Author Affiliations
Lei Li, Henan Univ. of Technology (China)
Xuan Fei, Henan Univ. of Technology (China)
Zhuoli Dong, Henan Univ. of Technology (China)
Dexian Zhang, Henan Univ. of Technology (China)

Published in SPIE Proceedings Vol. 9812:
MIPPR 2015: Automatic Target Recognition and Navigation
Nong Sang; Xinjian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top