Assessment of Object Segmentation Techniques for Object Based Image Retrieval
Laxmidevi Noolvi1, Hema N2, M V Sudhamani3
1Laxmidevi Noolvi, Department of CSE, RNSIT, Bangalore (Karnataka), India.
2Hema N, ISE, RNSIT, Bangalore (Karnataka), India.
3Dr. M V Sudhamani, ISE, RNSIT, Bangalore (Karnataka), India.
Manuscript received on 06 December 2019 | Revised Manuscript received on 14 December 2019 | Manuscript Published on 31 December 2019 | PP: 544-549 | Volume-9 Issue-2S December 2019 | Retrieval Number: B10481292S19/2019©BEIESP | DOI: 10.35940/ijitee.B1048.1292S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Objects relates more to human perception than any other attributes of an image. Image segmentation is a significant image processing technique to get the objects from complex image background. This work assesses the techniques of segmentation from basic global thresholding, edge based methods up to the advanced techniques such as K-means, Active Contour Model (Snakes) segmentation approaches. Later, results are post processed with the help of morphological operations and make them suitable for object based image retrieval. It also provides the comparative analysis and empirical assessment of performance of the proposed modified segmentation approaches.
Keywords: OBIR, Image Segmentation, Active Contours, K-means Image Segmentation.
Scope of the Article: Information Retrieval