Image Feature Extraction of Moment of Inertia Based on Otsu Threshold Segmentation

Qing Liu; Li Ming  Zhao; Li Jun Zhang

doi:10.4028/www.scientific.net/AMR.756-759.3157

Paper Titles

Prediction of Surface Ship's Residual Resistance Coefficient Using Neural Networks
p.3141

Modeling and Algorithm of Signal Coverage in Deep Space Communications
p.3145

Estimation of Failure Rate and its Applications
p.3149

Two Cascade Fault Models in Bayesian Networks
p.3153

Image Feature Extraction of Moment of Inertia Based on Otsu Threshold Segmentation
p.3157

New Convergence of Relaxed Parallel Multisplitting Method for the H-Matrix
p.3162

Data Sanitization Based on Weaken_Sensitive_Pattern Tree
p.3167

A Light-Weight Design Method for Vehicle with Welded Structure Based on Surrogate Model
p.3172

A Novel Unconstrained Criterion for Blind Equalization Based on the Property of Vector Norm
p.3177

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 756-759Image Feature Extraction of Moment of Inertia...

Image Feature Extraction of Moment of Inertia Based on Otsu Threshold Segmentation

Abstract:

In order to better extract image feature and recognition, a novel feature extraction algorithm of the binary image processing using Otsu combined with normalized moment of inertia (NMI) is put forward. Firstly, the image is processed into binary image and the target area is effectively segmented utilizing Otsu algorithm based on the criteria of maximal variance between-class , secondly, the NMI feature of the binary image is extracted, and finally, the extraction NMI feature is used in image recognition. Experimental results show that NMI feature of the binary image have the ability of anti-geometric distortions (translation, rotation and scaling, TRS), and anti-brightness distortions, the novel method have characteristics of simple extraction approach, little extraction parameter, easy implementation, and strong robustness.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 756-759)

Pages:

3157-3161

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.756-759.3157

Citation:

Cite this paper

Online since:

September 2013

Authors:

Qing Liu, Li Ming Zhao, Li Jun Zhang

Keywords:

Feature Extraction, Mage Segmentation, NMI Feature, Otsu Method

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Hosny, Khalid M. On the computational aspects of affine moment invariants for gray-scale images, Applied Mathematics and Computation, vol·195, pp.762-771, (2008).

DOI: 10.1016/j.amc.2007.05.025

Google Scholar

[2] Viangteeravat, Teeradache, Shirkhodaie, Amir. Multiple target vehicles detection and classification with low-rank matrix decomposition, Proc. IEEE Symp. International Conference on System of Systems Engineering. IEEE Press, 2007, pp.1-8.

DOI: 10.1109/sysose.2007.4304317

Google Scholar

[3] Wei Zhou, Jian Guan, Guohua Zhang. A Extracting Scheme for Targets of Interest in High Resolution Remote Sensing Imagery, Opto-Electronic Engineering, Vol. 38 pp.115-121, (2011).

Google Scholar

[4] Pin Xu, Gui Tong, Jing Qu. Face Detection in Video Based on AdaBoost Algorithm and Eye Location, Video Engineering, Vol. 35. pp.114-118, (2011).

Google Scholar

[5] Weng Muyun, He Mingyi. Image Feature Detection and Matching Based on SUSAN Method, Proceedings of the First International Conference on Innovative Computing, Information and Control. Washington, 2006, pp.322-325.

DOI: 10.1109/icicic.2006.96

Google Scholar