Part Recognition Based on Maximum Mutual Information

Sen Ge; Da Gui Huang

doi:10.4028/www.scientific.net/KEM.407-408.234

Paper Titles

Automatic Process Learning to Restore Omitted 2D Drawings
p.216

A Tool-Path Interpolation Algorithm Based on Unfolding-Bending Parametric Curves
p.220

A Collaborative Design and Analysis Environment for Flexible Fixture
p.225

Collaborative Manufacturing Unit Selection Using a Sorting Adaptive Genetic Algorithm in Networked Environment
p.230

Part Recognition Based on Maximum Mutual Information
p.234

Application of Virtual Manufacturing to Impeller Five-Axis High Speed Machining
p.239

Template-Based Process Planning System for Special Bearing
p.243

Development of Advanced NC Geometric Cutting Simulator
p.248

Development of Novel NC Machining System for Non-Circular Shafts
p.252

HomeKey Engineering MaterialsKey Engineering Materials Vols. 407-408Part Recognition Based on Maximum Mutual...

Part Recognition Based on Maximum Mutual Information

Abstract:

A new approach to the problem of part recognition is proposed by using maximum mutual information. The method applies entropy to measure image feature, combined with color information and local shape information, and uses mutual information as a new matching criterion between the images for image recognition. This method solves the problem that histogram algorithm can not represent the spatial information. This method not only has the feature of translation invariant, but also avoids image segmentation which may lead to a complex calculation, so it can be realized easily. The result shows that proposed approach is accuracy, stability, and reliability in the processing of machine part image recognition.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 407-408)

Pages:

234-238

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.407-408.234

Citation:

Cite this paper

Online since:

February 2009

Authors:

Sen Ge, Da Gui Huang

Keywords:

Entropy, Image Recognition, Machine Part Image, Mutual Information (MI)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] D. Xu, Y. P. Jiang, and H. Zheng: China Mechanical Engineering, Vol. 8(1997), No. 5, pp.69-71.

Google Scholar

[2] S. Li, T. G. Zhuang, and H. Cheng: Journal of Shanghai JiaoTong University, Vol. 35(2001), No. 5, pp.694-698.

Google Scholar

[3] M. Kunaver and J.F. Tasic: EUROCON 2005, Vol. 1(2005), pp.183-186.

Google Scholar

[4] M. B. Skouson, Q. Guo, Z. -P. Liang: IEEE Transactions on Medical Imaging, Vol. 20(2001), No. 8, pp.843-846.

Google Scholar

[5] F. Maes, A. Collignon, G. Marchal, and P. Suetens: IEEE Transactions on Medical Imaging, Vol. 16(1997), No. 2, pp.187-198.

DOI: 10.1109/42.563664

Google Scholar

[6] J. P. W. Pluim, J. B. A. Maintz, M. A. Viergever: IEEE Transactions on Medical Imaging, Vol. 22(2003), No. 8, pp.986-1004.

DOI: 10.1109/tmi.2003.815867

Google Scholar

[7] H. Xie, L. E. Pierce, F. T. Ulaby: Proceedings of International Geoscience and Remote Sensing Symposium 2003, Vol. 6, 21-25 (2003), pp.4028-4031.

Google Scholar

[8] S. Q. Luo and X. Li: Journal of Image and Graphics, Vol. 5(A)(2000), No. 7, pp.551-558.

Google Scholar

[9] I(a, a) I(a, b) I(a, c) -200 -150 -100 -50 0 50 100 150 200 Translation (pixel) 5 4 3 2 1 0 MI value.

Google Scholar