Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
In colleges, universities, organizations, schools, and offices, identifying known and unknown faces is difficult sometimes for applications such as marking attendance in an auditorium with several students, during workshops, and many other applications, The main goal of this project is to identify known and unknown faces from a group image faster and accurately. For making such a system known faces are trained which then differentiates from unknown faces, for training the faces three main parameters i.e., Face recognition, Face detection and facial feature extraction should be done accurately and very fast and here in this paper it is done using the new emerging technique INSIGHTFACE.
It is a new emerging machine learning/deep learning approach, it avoids the hinderances like high processing time, large sample data collection for training, and low accuracy due to again and again training of machine learning modelling which are reported in traditional techniques like SVM, Neural networks and CNN.
For training known faces a hypothetical college MNCT is assumed in this dissertation where 6 persons are trained, one as a principal, two teachers and three students, The project is prepared in python version 3.10 with jupyter notebook, the project was successfully able to differentiate between known and unknown faces.
the complete facial analysis was done using Insight face, the extracted features of these trained person were stored in REDIS database system. And for detection of known face between multiple peoples consisting of known and unknown faces machine learning search algorithms are applied. The results obtained have 100 % accuracy, the faces are detected clearly even for a image which was having less resolution, during training of images insight face uses 10 to 11 samples only which are 10 to 15 times less compared to traditional techniques which reduces the processing time also.
Keywords:
Face Recognition, Insight Face, Redis Key words: Face Recognition, Insight Face, Redis
Cite Article:
"Recognition of Known faces between multiple Unknowns with high Accuracy", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.8, Issue 6, page no.764 - 774, June-2023, Available :http://www.ijrti.org/papers/IJRTI2306116.pdf
Downloads:
000205117
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator