Programs
- M. Tech. in Automotive Engineering -
- Clinical Fellowship in Laboratory Genetics & Genomics - Fellowship
Publication Type : Conference Paper
Publisher : Proceedings of the 2017 IEEE International Conference on Communication and Signal Processing,
Source : Proceedings of the 2017 IEEE International Conference on Communication and Signal Processing, ICCSP 2017, Institute of Electrical and Electronics Engineers Inc., Volume 2018-January, p.952-958 (2017)
ISBN : 9781509038008
Keywords : Automatic approaches, Face profiles, Faces Side Poses, Gaussian distribution, Gaussian Mixture Model, Image segmentation, Image thresholding, Level set algorithm, Segmentation methods, Thresholding
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science
Year : 2018
Abstract : Amongst an array of research topics, image segmentation is the most challenging one. This along with image thresholding are the fundamental problems that arise in image processing. There are 2 main methods in image segmentation. They are automatic and manual. In the automatic method, we do not require any person to operate on the segmentation, whereas in the manual very minimal user interaction is required. It is proven that the interactive or the manual approach gives a better result than the automatic approach. This paper focuses on the comparisons and the implementations of the segmentation methods and their analysis. It also gives insights whether automatic or manual methods are better. The algorithms that we used here are modified Level Set algorithm, Gaussian Mixture model, Support Vector Machine. Finally, all the results are obtained and are compared and contrasted.
Cite this Research Publication : A. Arjun and Dr. Tripty Singh, “Analysis of image segmentation methods on Amrita's Indian side face profile database”, in Proceedings of the 2017 IEEE International Conference on Communication and Signal Processing, ICCSP 2017, 2017, vol. 2018-January, pp. 952-958.