ITM Web Conf.
Volume 44, 2022International Conference on Automation, Computing and Communication 2022 (ICACC-2022)
|Number of page(s)
|05 May 2022
Supervisory framework for threat detection withmultilayer processing in CNN
Ramrao Adik Institute Of Technology, Electronics and Telecommunication, Nerul, Navi Mumbai
Face recognition has received huge acknowledgement due to its various uses in Internet communication, security, access control, surveillance, PC entertainment and law enforcement. Conventional methods of recognition based on the ownerships of identity-cards or full knowledge such as a security number or password are not totally solid. Physical ID cards can be lost or forged, passwords can be hacked or forgotten but a face is undoubtedly connected to its owner. It cannot be stolen, borrowed or easily forged. Our current system has a lot of weaknesses wherever it is simply taken and merged. The focus of this paper is to help users for development of the security by utilizing face identification and recognition. The proposed framework principally comprises of subsystems specifically picture capture, face identification and detection, email alerts and metal detection. Furthermore, the improvement in Computer Vision through Deep Learning algorithms has been an impressive achievement, especially with the Convolutional Neural Network algorithm. A convolutional neural network is a feed-forward neural network that is by and large used to break down visual pictures by using grid-like topology. It is also called as ConvNet. The objects in a picture are distinguished and arranged using convolutional neural network. CNN detects various simple complex patterns in images and data in its different layers of Convolution Layer, Max Polling Layer and Fully Connected Layer .This field intends to allow and configure machines to see the world as people do, and utilize the information for doing tasks (such as Image Analysis, Image Recognition and Classification, etc).
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.