Journal
SIGNAL PROCESSING
Volume 143, Issue -, Pages 346-353Publisher
ELSEVIER
DOI: 10.1016/j.sigpro.2017.07.009
Keywords
Image segmentation; Auto-encoders; Unsupervised learning; Hierarchical clustering
Categories
Funding
- National Natural Science Foundation of China [61622205, 61472110]
- Zhejiang Provincial Natural Science Foundation of China [LR15F020002]
Ask authors/readers for more resources
For decades, image segmentation is a hot research direction in computer vision because of its extensive and practical applications. In this work, we propose a method of image segmentation based on auto encoders and hierarchical clustering algorithm, aiming at dealing with the segmentation problem in an unsupervised way. More specifically, this proposed method consists of two stages: training and segmenting. In training stage, we divide sample images into non-overlapped patches and extract deep-level feature representations from the patches using Stacked Denoising Auto-encoder (SDA), then we perform unsupervised and hierarchical K-means clustering on these feature representations and build an indexing tree structure. In segmenting stage, we achieve segmentation of an arbitrary image based on the indexing tree structure. This unsupervised methodology is demonstrated to be an improvement over traditional unsupervised segmentation methods owing to the introduction of sample images. Experimental evaluations on several benchmark datasets indicate that our algorithm outperforms several other methods in both time efficiency and accuracy. (C) 2017 Published by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available