•  
  •  
 

Abstract

Improving the accuracy level of face recognition system is still an open research area where it consists of certain limitations to attain maximum accuracy. In earlier days, several algorithms are developed using machine learning and deep learning models, but still, they need improvement in terms of accuracy. For that purpose, in this article a novel CNN model called the optimized multi cascaded CNN (OPT-MTC-CNN) in the artificial intelligence system is developed, which helps to overcome the accuracy issues in face recognition system. The algorithms that are incorporated in this model are Fully Convolutional Network (FCN), Convolutional Neural Network (CNN), and Improved Non-Maximum Suppression (INMS). The implementation of this idea is performed in python, and the parameters that are calculated for its performance analysis are accuracy, precision, recall and f1-score. Additionally, certain parameters are measured to improve the network efficiency, such as specificity and sensitivity. The earlier methods that are utilized to perform the comparative analysis are CNN with Siamese network, pretrained CNN and Faster R-CNN. From the final obtained results, it gets proven that the proposed work attained 99% specificity, 98% sensitivity and 99.8% accuracy, which are better when compared with these earlier baseline methods.

Keywords

Artificial intelligence, Convolutional neural network, Deep learning, Face recognition, Machine learning

Subject Area

Computer Science

Article Type

Article

First Page

3513

Last Page

3529

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS