Grouping and Summarizing Scene Images from Web Collections

Authors:
Heng Yang;Qing Wang
Affiliations:
School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, P.R. China 710072;School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, P.R. China 710072
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Year:
2009

Citing 9
Cited 0

An optimal algorithm for approximate nearest neighbor searching fixed dimensions

Journal of the ACM (JACM)
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Scalable Recognition with a Vocabulary Tree

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Robust multi-view feature matching from multiple unordered views

Pattern Recognition
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an efficient approach to group and summarize the large-scale image dataset gathered from the internet. Our method firstly employs the bag-of-visual-words model which has been successfully used in image retrieval applications to give the similarity between images and divides the large image collections into separated coarse groups. Next, in each group, we match the features between each pair of images by using an area ratio constraint which is an affine invariant. The number of matched features is taken as the new similarity between images, by which the initial grouping results are refined. Finally, one canonical image for one group is chosen as the summarization. The proposed approach is tested on two datasets consisting of thousands of images which are collected from the photo-sharing website. The experimental results demonstrate the efficiency and effectiveness of our method.