Identifying People’s Faces in Smart Banking Systems Using Artificial Neural Networks

Abstract Due to the exponential rise of ICT technologies, the digital banking industry has made tremendous advancements in user-friendly, effective, and quick financial transactions. Numerous new banking services, products, and business opportunities have resulted as a result. Smart facial authentication is a cutting-edge technology used in mobile banking. Users can utilize this technology to verify their identification by using the facial recognition feature of the camera on their mobile device. This method makes use of complex algorithms that can analyze a person’s face and extract the distinctive characteristics that can be seen there. The attributes of the images of distinct persons are then categorized using learning algorithms and the K-means clustering method. An artificial neural network (ANN), adaptive neural fuzzy inference system (ANFIS), and decision tree (DT) computer system are used to authenticate persons. In this inquiry, the face is used. Additionally, the Wild Horse Optimizer (WHO) method has been used to enhance the precision and optimization of machine learning systems by weighting cluster features. Fuzzy logic is used to make decisions about authentication based on the results of machine learning algorithms. The best feature from a broad dataset is selected using a technique based on evolutionary algorithms. The simulation findings for diverse users have a precision of about 99.78% for user authentication of test samples. Notably, the suggested method reduced the FAR, FRR, and ERR errors by 0.23, 1.13, and 1.1, respectively. It has been proven that using people’s image data may enhance the quality of everyday cameras, and it is anticipated that this work will be applied to mobile banking applications to ensure the verification of rightful owners.