Artificial neural networks are used in a Dark Having to learn Biometric smart card in contrast to the Integrated Method
P. Shyamala Bharathi, G. Khiran Sai · 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) · 2022
Deep Learning based face recognition attendance system using novel robust 4-layer Convolutional Neural Network architecture is proposed for the face recognition problem, with a solution that is capable of handling facial images in comparison with Holistic Matching Method (HMM) classifier to enhance the efficiency of the system. The algorithms have been implemented and tested over a dataset which consists of 20 records as a dataset of 10 samples each with threshold value of 0.05% and confidence interval 95%. and the pretest power is 80 % with an error correction of 0.05. The Novel Robust 4-Layer CNN classifier gives 95.2% accuracy in the classification of face detection while the HMM gives 86.2% accuracy. There is a significant difference between the two groups p < 0.05. Conclusion:Novel robust 4-layer Convolutional Neural Network (CNN) architecture gives significantly better classification in terms of accuracy and precision compared to that of Holistic Matching Method method (HMM).