Identification of an Object in an Image using Frame Differencing, Optical Flow and Support Vector Machine
Vikash Yadav1, Rati Shukla2, Vandana Dixit Kaushik3
1Vikash Yadav, Computer Science & Engineering Department, ABES Engineering College, Ghaziabad, (U.P), India.
2Rati Shukla, GIS Cell, MNNIT Allahabad, Prayag raj, (U.P), India.
3Vandana Dixit Kaushik, Computer Science & Engineering Department HBTU Kanpur, (U.P), India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 2938-2942 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7302068819/19©BEIESP
Open Access | Ethics and 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: The main aim of Identification of any object is to trace a region of interest from an image and locate its position and movement. This paper introduces a novel technique for object identification using frame differencing for background subtraction, optical flow for feature extraction and Support Vector Machine classifier for classification. Existing techniques are capable of identifying the object but unable to handle the situations of cluster of pixels in the given images. To overcome this drawback, new frameworks have been developed for object identification and have maximum accuracy. This framework is very helpful in surveillance system and security system.
Keyword: Optical flow, Position, SVM, Object classification.
Scope of the Article: Natural Language Processing and Machine Translation.