Modular Face Recognition: A Customizable System
Jatin Katyal1, Poonkodi Mariappan2, Arun Nehru J3
1Jatin Katyal, Department of CSE, Faculty of Engineering and Technology, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
2Poonkodi Mariappan, Department of CSE, Faculty of Engineering and Technology, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
3Arun Nehru J, Department of CSE, Faculty of Engineering and Technology, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
Manuscript received on 22 April 2019 | Revised Manuscript received on 01 May 2019 | Manuscript Published on 07 May 2019 | PP: 83-85 | Volume-7 Issue-6S3 April 2019 | Retrieval Number: F1017376S19/2019©BEIESP
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: Facial Recognition is an emerging topic and has been in discussion for a long time now. It has much application in use and even more to be discovered. We propose a system where Machine Learning is used on stored extracted facial features and classifies test data into recognized classes. This requires detection of a face, normalization of detected faces, extraction of features, training on extracted features and classification as subtasks. The end result of this project is a modular and robust face recognition system, with multiple detectors, extractors, and classifiers to choose from. We are using a subset of Cal Tech dataset of facial images. We will be recording our results with some of the possible combinations and develop a real-time application as proof of concept.
Keywords: Recognition System Modular Data.
Scope of the Article: Pattern Recognition