Efficient image concept indexing by harmonic & arithmetic profiles entropy

Authors:
Herve Glotin;Zhong-Qiu Zhao;Stephane Ayache
Affiliations:
Systems and Information Sciences Lab., UMR, CNRS and Univ. Sud-Toulon Var, France;Systems and Information Sciences Lab., UMR, CNRS and Univ. Sud-Toulon Var, France and Computer and Information School, Hefei Univ. of Technology, China;Fundamental Computer Science Lab., UMR, CNRS and Univ. Marseille, France
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 5
Cited 2

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Content based image retrieval and information theroy: a general approach

Journal of the American Society for Information Science and Technology - Visual based retrieval systems and web mining
Saliency maps and attention selection in scale and spatial coordinates: an information theoretic approach

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Evaluation campaigns and TRECVid

MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Visual affinity propagation improves sub-topics diversity without loss of precision in web photo retrieval

CLEF'08 Proceedings of the 9th Cross-language evaluation forum conference on Evaluating systems for multilingual and multimodal information access

A matrix modular SVM robust to imbalanced data for efficient visual concept detection

Proceedings of the international conference on Multimedia information retrieval
A fast visual word frequency - inverse image frequency for detector of rare concepts

CLEF'09 Proceedings of the 10th international conference on Cross-language evaluation forum: multimedia experiments

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose new efficient visual features called Profile Entropy Features (PEF), giving information on the structure of the image content, and defined as the entropy of the distribution of a projection of the pixels. We analyse two simple projection operators (arithmetic or harmonic mean), and two orientations (horizontal and vertical). PEF are fast to compute (10 images per sec. on a PentiumIV) and of small dimension. Moreover, we show on High Level Feature task in TrecVid2008 that PEF performs in average better than the features of the state of the art (usual color features, edge direction, Gabor, and Local Binary Pattern). Moreover, we show on another international image retrieval campaign, the Visual Concept Detection of ImageCLEF2008, that the arithmetic and harmonic projections give complementary informations, yielding to the third best rank system in the official run of this campaign. Other properties of the PEF are discussed.