Study on Shape Recognition Based on Contour

Wei Zhang

doi:10.4028/www.scientific.net/AMM.644-650.4240

Paper Titles

Preprocessing for Interference Fringe of Spherical Object Wave
p.4225

An Improved Blind Image Restoration Based on Bi-Spectral Reconstruction
p.4229

CT Images Segmentation Based on Dynamic Relative Fuzzy Region Growing Algorithm
p.4233

Mix-Mode S Parameters Analysis of Crosstalk for Twisted Differential Line on PCB
p.4237

Study on Shape Recognition Based on Contour
p.4240

High Time Resolution Scanning Imaging Technique Research Based on Area CCD
p.4244

Modified Ocean Clutter Cancellation Algorithm in Sky-Wave Radar
p.4249

Parameter Estimation of Polynomial Phase Signal by Unscented Kalman Filtering
p.4253

Design Method of H.264/AVC Video Watermarking Based on Intra Prediction Coding
p.4257

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650Study on Shape Recognition Based on Contour

Study on Shape Recognition Based on Contour

Abstract:

Shape is the inherence characteristic of an object in the image, and it is the important character used for the object recognition. So it is significant for object recognition based on shape. This paper presents a contour-based method of feature extraction and shape recognition. First the object contour is translated into a 1-D contour curve. Secondly the curve is smoothed to restrain the noise. The number of peaks of the curve is achieved as well as the areas which contained between adjacent peak-valley, then the latter is followed by Discrete Fourier Transformation (DFT). Then two kinds of features ate extracted which are invariant to translation, scaling and rotation transformations. By using the features, a two-stake recursive algorithm for recognition is proposed. Experimental results show that this method is simple and efficient.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

4240-4243

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.4240

Citation:

Cite this paper

Online since:

September 2014

Authors:

Wei Zhang*

Keywords:

Contour, Feature Extraction, Occluded Shape, Shape Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Efstathios, Hadjidemetriou, Michael D. Grossberg, Shree, Multiresolution Histograms and Their Use for Recognition, IEEE Trans, PAMI, vol. 26, No. 7, (2004).

Google Scholar

[2] Thuy Tuong Nguyen, Xuan Dai Pham, Dongkyun Kim, Jae Wook Jeon. A test framework for the accuracy of line detection by Hough Transforms. 6th IEEE International Conference on Industrial Informatics, 2008, 1528-1533.

DOI: 10.1109/indin.2008.4618347

Google Scholar

[3] Thuy Tuong Nguyen, Xuan Dai Pham, JaeWook Jeon. An improvement of the Standard Hough Transform to detect line segments. IEEE International Conference on Industrial Technology, 2008, 1-6.

DOI: 10.1109/icit.2008.4608701

Google Scholar

[4] Heitz G, Elidan G, Packer B, Koller D. Shape-based object localization for descriptive classification [J]. International Journal of Computer Vision, 2009, 84(1): 40-62.

DOI: 10.1007/s11263-009-0228-y

Google Scholar

[5] Moosmann F, Nowak E, Jurie F. Randomized clustering forests for image classification [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(9): 1632-1646.

DOI: 10.1109/tpami.2007.70822

Google Scholar