Co-Salient Object Detection From Multiple Images

In this paper, we propose a novel method to discover co-salient objects from a group of images, which is modeled as a linear fusion of an intra-image saliency (IaIS) map and an inter-image saliency (IrIS) map. The first term is to measure the salient objects from each image using multiscale segmenta...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on multimedia Vol. 15; no. 8; pp. 1896 - 1909
Main Authors Li, Hongliang, Meng, Fanman, Ngan, King Ngi
Format Journal Article
LanguageEnglish
Published New York, NY IEEE 01.12.2013
Institute of Electrical and Electronics Engineers
Subjects
Applied sciences
Artificial intelligence
Attention model
co-saliency
Computer science; control theory; systems
Data processing. List processing. Character string processing
Exact sciences and technology
Information retrieval. Graph
Memory organisation. Data processing
minimum spanning tree
Pattern recognition. Digital image processing. Computational geometry
similarity
Software
Theoretical computing
Attention model
Computer vision
Image processing
Hierarchical classification
Image content
minimum spanning tree
Minimal spanning tree
Linear programming
Object recognition
Modeling
Linear model
Multiple image
Image segmentation
Voting
Image matching
Multiscale method
similarity
Object detection
Stimulus salience
Image sensor
Cooccurrence analysis
co-saliency
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel method to discover co-salient objects from a group of images, which is modeled as a linear fusion of an intra-image saliency (IaIS) map and an inter-image saliency (IrIS) map. The first term is to measure the salient objects from each image using multiscale segmentation voting. The second term is designed to detect the co-salient objects from a group of images. To compute the IrIS map, we perform the pairwise similarity ranking based on an image pyramid representation. A minimum spanning tree is then constructed to determine the image matching order. For each region in an image, we design three types of visual descriptors, which are extracted from the local appearance, e.g., color, color co-occurrence and shape properties. The final region matching problem between the images is formulated as an assignment problem that can be optimized by linear programming. Experimental evaluation on a number of images demonstrates the good performance of the proposed method on co-salient object detection.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2013.2271476