← Back to Publications List

Multi-Input Faster Region-Based Convolutional Neural Network(ConvNet) and Facial Landmark Feature-Based Crowd Recognition: A Deep Learning Approach

Students & Supervisors

Student Authors
Abdulla Mahamud Shejan
BSc in Electrical & Electronic Engineering, FE
Md. Mehedi Hasan Monna
BSc in Electrical & Electronic Engineering, FE
S G A Shezan
BSc in Electrical & Electronic Engineering, FE
Imtiaz Uddin
BSc in Electrical & Electronic Engineering, FE
Supervisors
Prof. Dr. Mohammad Nasir Uddin, Peng.
Professor, Head [graduate Program], FE

Abstract

In light of global health crises, such as the COVID-19 pandemic, the importance of touchless facial authentication systems has become evident. Traditional face recognition-based models face difficulties in dynamic environments where individuals are in motion and their facial features may change over time. This research proposes a method based on the Faster RCNN architecture, which achieves an accuracy of 98%, surpassing conventional models like LBPH (Local Binary Pattern Histogram), Eigen face, and Haar Cascade. By incorporating a Region Proposal Network (RPN) and utilizing inputs from various angles, with a demonstrated average accuracy of 94% in practical examinations. In nine standard cases, the system achieves an accuracy rate of 96%, showcasing its reliability in diverse scenarios. Furthermore, the model effectively addresses challenges posed by facial obstacles such as masks and sunglasses, exhibiting a commendable detection accuracy of 89%. By storing processed RPN for future recognition, the proposed model not only enhances accuracy but also improves detection speed.

Keywords

Training Face recognition Surveillance Software algorithms Software Feeds Servers

Publication Details

  • DOI: 10.1109/ICDCECE60827.2024.10549554
  • Type of Publication: Conference
  • Conference Name: IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE)
  • Date of Conference: 26/04/2024 - 27/04/2024
  • Venue: India
  • Organizer: IEEE
View on Publisher