Sonar Image Segmentation Based on an Improved Selection of Initial Contour of Active Contour Model

Jun Peng Wu; Hai Tao Guo

doi:10.4028/www.scientific.net/AMM.709.447

Paper Titles

Studies on the Removal of Tetracycline by a Kind of Nano-Sized Amorphous Carbon
p.426

Stress Analysis of All Ceramic Fixed Partial Denture by Finite Element Method
p.430

Penetration Force in Biopsy under Condition of Biomimetic Vibration
p.436

Preparation and the Release Rate Studies of a New Gel Type Slow-Release Solid Chlorine Dioxide
p.441

Sonar Image Segmentation Based on an Improved Selection of Initial Contour of Active Contour Model
p.447

A Test to Measure the Rate of Adsorption Deformation of Flexible Assembly Tooling
p.451

Comparison of Vibration Signal Analysis Methods for Effective Gear Fault Detection
p.456

Design of a Spherical Leak Detector for Submarine Oil Pipelines
p.460

The Application and Research of Terrestrial 3D Laser Scanning Technology in Tunnel Survey
p.465

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 709Sonar Image Segmentation Based on an Improved...

Sonar Image Segmentation Based on an Improved Selection of Initial Contour of Active Contour Model

Abstract:

The correct sonar image segmentation is an important foundation for underwater target recognition. Because the contour convergence of the active contour model depends on the selection of initial position, the active contour model is applied in sonar image segmentation. This paper proposed a selection method based on local standard deviation of image as the outline of initial contour. Due to the disturbance of noise, sonar image is usually affected in resolution and contrast. Firstly, sonar image is enhanced by top-hat and bottom-hat transformation in image morphology. Then after image enhancement, a suitable threshold value is chose for rough binarization and the standard deviation of target areas to calculate the local image. According to the size of standard deviation of different regions to determine the scope of the initial contour, sonar image segmentation is achieved by active contour algorithm.

You might also be interested in these eBooks

Designing and Researching of Machines and Technologies for Modern Manufacture

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 709)

Pages:

447-450

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.709.447

Citation:

Cite this paper

Online since:

December 2014

Authors:

Jun Peng Wu*, Hai Tao Guo

Keywords:

Active Contour, Grayscale, Image Segmentation, Image Standard Deviation

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Kass. M. , Witkin. M. Meier and Terzopoulos D.: Snakes: active contour models. International Journal of Computer Vision, 1987, pp.321-331.

DOI: 10.1007/bf00133570

Google Scholar

[2] Guangyu Liu, Hongyu Bian and Xiufen Ye. An Improved Spectral Clustering Sonar Image Segmentation Method. International Conference on Complex Medical Engineering, 2011, pp.474-477.

DOI: 10.1109/iccme.2011.5876787

Google Scholar

[3] Akansha Mehrotra, Krishna Kant Singh and Shraddha Tripathi. Blood Vessel Extraction for Retinal Images Using Morphological Operator and KCN Clustering. IEEE International Advance Computing Conference, 2014, pp.1142-1146.

DOI: 10.1109/iadcc.2014.6779487

Google Scholar

[4] Zhu Shihu. Function extension and application of morphological top-hat transformation and bottom-hat transformation. Computer Engineering and Applicaton, 2011, pp.190-192.

Google Scholar

[5] Li Liqin, Gao Huanwen and Zhou Xingxiang: Study on Initial Contour Selection of Snake Model. Computer Engineering and Application, 2004, pp.43-45.

Google Scholar