Feature Adaptive Co-Segmentation by Complexity Awareness

In this paper, we propose a novel feature adaptive co-segmentation method that can learn adaptive features of different image groups for accurate common objects segmentation. We also propose image complexity awareness for adaptive feature learning. In the proposed method, the original images are fir...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 22; no. 12; pp. 4809 - 4824
Main Authors: Meng, Fanman, Li, Hongliang, Ngan, King Ngi, Zeng, Liaoyuan, Wu, Qingbo
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.12.2013
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adaptation models
Algorithms
Applied sciences
Complexity
Complexity theory
Cosegmentation
Detection, estimation, filtering, equalization, prediction
distance metric learning
Exact sciences and technology
Feature extraction
Fitness
Image color analysis
image complexity analysis
Image detection
Image processing
Image segmentation
Information, signal and communications theory
Measurement
Object detection
Pattern recognition
Segmentation
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
State of the art
Studies
Telecommunications and information theory
State of the art
Image processing
distance metric learning
Error rate
image complexity analysis
Unsupervised classification
Pattern recognition
Shape detection
Algorithm
Signal classification
Adaptive method
Optimization
Remote teaching
Learning
Image segmentation
Image analysis
Accuracy
Least squares method
Object detection
Cosegmentation
Metric
Edge detection
Target detection
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a novel feature adaptive co-segmentation method that can learn adaptive features of different image groups for accurate common objects segmentation. We also propose image complexity awareness for adaptive feature learning. In the proposed method, the original images are first ranked according to the image complexities that are measured by superpixel changing cue and object detection cue. Then, the unsupervised segments of the simple images are used to learn the adaptive features, which are achieved using an expectation-minimization algorithm combining l 1-regularized least squares optimization with the consideration of the confidence of the simple image segmentation accuracies and the fitness of the learned model. The error rate of the final co-segmentation is tested by the experiments on different image groups and verified to be lower than the existing state-of-the-art co-segmentation methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2013.2278461