Combining SIFT and global features for web image classification

Authors:
Qimin Cheng;Yue Wen;Zheng-Jun Zha;Xihua Chen;Zhenfeng Shao
Affiliations:
The Department of Electronics and Information Engineering/Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China;Department of Automation, Tsinghua University, Beijing, China;School of Computing, National University of Singapore, Singpaore;The Department of Electronics and Information Engineering/Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China;State Key Laboratory for Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China
Venue:
PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
Year:
2012

Citing 16
Cited 0

Approximate nearest neighbors: towards removing the curse of dimensionality

STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Data Fusion for Sensory Information Processing Systems

Data Fusion for Sensory Information Processing Systems
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Locality-sensitive hashing scheme based on p-stable distributions

SCG '04 Proceedings of the twentieth annual symposium on Computational geometry
CSIFT: A SIFT Descriptor with Color Invariant Characteristics

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Discriminative cue integration for medical image annotation

Pattern Recognition Letters
Visual query suggestion

MM '09 Proceedings of the 17th ACM international conference on Multimedia
Unified video annotation via multigraph learning

IEEE Transactions on Circuits and Systems for Video Technology
A Robust Keypoints Matching Strategy for SIFT: An Application to Face Recognition

ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part I
Integrating ILSR to Bag-of-Visual Words Model Based on Sparse Codes of SIFT Features Representations

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Vocabulary Hierarchy Optimization and Transfer for Scalable Image Search

IEEE MultiMedia
An iris recognition approach with SIFT descriptors

ICIC'11 Proceedings of the 7th international conference on Advanced Intelligent Computing Theories and Applications: with aspects of artificial intelligence
Towards a Relevant and Diverse Search of Social Images

IEEE Transactions on Multimedia
Less is More: Efficient 3-D Object Retrieval With Query View Selection

IEEE Transactions on Multimedia
Interactive Video Indexing With Statistical Active Learning

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nowadays, web images are rapidly increasing with the development of internet technology. This situation leads to the difficulties on effective and efficient image retrieval from mass data under web environment. In this paper, we propose a web images classification method by integrating SIFT features of the images with global features. First, Locality Sensitive Hashing (LSH) is adopted for local feature extraction by embedding the SIFT feature vector. Then, other global features, such as color, texture or shape feature, are extracted. Support Vector Machine (SVM) is employed for image classification by using these two types of features respectively. The two classification results are integrated by decision-level fusion to get the final classification result. Experimental results on a web image dataset show that the proposed method is able to improve the performance of web images classification.