A Transfer Learning-Based Intelligent Judiciary System for Public Safety

With the increasing prevalence of criminal activities, there is a growing need for effective crime detection methods leveraging modern technologies, such as artificial intelligence (AI), the Internet of Things (IoT), and cloud computing. In this paper, we propose a transfer learning (TL)-based solution for criminal face detection using convolutional neural networks (CNNs) to improve public safety. Leveraging pre-trained CNN models, we fine-tune them on a dataset comprising images of known criminals and non-criminals. The proposed framework aims to mitigate the challenges associated with training CNNs from scratch, such as data scarcity and computational inefficien-cies. Experimental results demonstrate the effectiveness of the proposed framework in accurately identifying criminal faces, showcasing its potential for enhancing law enforcement efforts. We achieved the highest accuracy of 97% with the TL scheme.