SmartKYC

This Paper demonstrates an automated system to streamline the KYC (Know Your Customer) process using machine learning. It integrates document validation, image pre-processing, text extraction, automated form filling, face detection, liveliness detection, and verification. Tesseract, utilizing LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network), extracts text from smart driving licenses to auto-fill digital KYC forms, reducing manual entry errors. MTCNN (Multi-task Cascaded Convolutional Networks) handles face detection, OpenCV ensures liveliness, and FaceNet (Inception-ResNet-v1) verifies the selfie against the ID photo for security. Successful verification grants confirmation; otherwise, users resolve issues. The system achieved 86.43% training and 86.25% validation accuracy, improving efficiency, accuracy, and user experience.