A Review On Hybrid Feature Based Object Mining And Tagging
DOI:
https://doi.org/10.26438/ijcse/v6i11.686689Keywords:
Image processing, Object recognition, object mining, object tagging, feature extraction, classification, SVMAbstract
Tag mining is important as far as image search engines/databases are concerned viz. Flicker, Picasa, Facebook...etc. Tag Mining is a difficult and highly relevant machine task. In this paper, we present a new approach to hybrid features based object mining and tagging that identifies the objects with higher accuracy from an occluded image. In existing system tag Mining with algorithms based on ‘Nearest neighbor classification’ have achieved considerable attention implementation point of view but at the cost of increasing computational complexity both during training and testing. It is very difficult to identify the object which is occluded in image. The objective of object tagging of image is to search over user contributed photo online which have accumulated rich human knowledge and billions of photos, then associate surrounding tags from those visually similar photos for the unlabeled image. For an unlabeled image, photos in the social media are extracted by the Feature based object tagging of image, the annotations associated with the images are expanded, and then each object group is classify. In this paper different features and classifier are compare with advantages and disadvantages.
References
[1] Hiteshree H. Lad, Mayuri A. Mehta “Analysis of Feature based Object Mining and Tagging Algorithm Considering Different Levels of Occlusion ” IEEE , 2017
[2] Adrian Llopart, Ole Ravn, Nils A. Andersen, Jong-Hwan Kim “Generalized framework for the parallel semantic segmentation of multiple objects and posterior manipulation” IEEE, 2017
[3] Ali Vashaee , Reza Jafari, Djemel Ziou, Mohammad Mehdi Rashidi “Rotation invariant HOG for object localization in web images ” Elsevier , 2016
[4] Amin Mohamed Ahsan , Dzulkifli Bin Mohamad “Machine learning technique for object detection based on SURF feature ” Int. J. Computational Vision and Robotics, 2017
[5] Zahid Mahmood, Mahammad Nazeer, Muhammad Arif, Imran Shahzad, Fahad Khan, Mazhar Ali “Boosting the Accuracy of AdaBoost for Object Detection and Recognition” International Conference on Frontiers of Information Technology ,2016
[6] Pawel Forczmanski, Andrzej Markiewicz “Two-stage approach to extracting visual objects from paper documents ” SPINGER, 2016
[7] Muhammad Sipan, Supeno Mardi Susiki , Eko Mulyanto Yuniarno “Image Block Matching Based on GLCM Texture Feature on Grayscale Image Auto Coloring” IEEE ,2017
[8] Nikhil Rasiwasia, Nuno Vasconcelos “Holistic Context Models for Visual Recognition” IEEE, 2012
[9] R.suresh , P. Dhivya and N.Bhuvana “Analysis on Image Mining Techniques” International Conference on Innovations in information Embedded and Communication Systems (ICIIECS) IEEE, 2017
[10] I.Khan, A.Khan and R.Shaikh “Object analysis in image mining” conf. Computing for sustainable global development (INDIACom) ,2015
[11] Jigisha M.Patel and Nikunj C. Gamit “A Review on Feature Extraction Techniques in Content Based Image Retrieval” IEEE, 2016
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
