Innovative Convolutional Neural Network Approach to Enhance Real-Time Face Recognition Accuracy

This paper introduces an innovative facial recognition criminal detection system at the forefront of technology. Its primary goal is to identify suspects in real time, using cutting-edge algorithms and live camera technology. By combining these advanced features, the system significantly enhances security measures and helps combat criminal activities. Facial recognition has become a prominent tool in security, revolutionizing surveillance for threat detection. The user-friendly desktop application offers a wide range of features, including viewing crime statistics and uploading suspect images. With an impressive accuracy rate of 99.38%, the system excels at identifying potential criminals, thanks to its integration with live camera sensors by employing dlib’s Python library along with Histogram of Oriented Gradients (HOG), Euclidean distance, cosine similarity, and other preprocessing steps. Administrators benefit from additional privileges, such as direct management of the suspect database, user account control, and system monitoring. An admin dashboard provides efficient oversight of suspects, approval requests, and user management, enabling effective decision-making.