Call for Paper - Upcoming Issues

Intelligent Identity Verification and Digital Onboarding System Using Deep Learning and RPA

International Journal of Electrical and Electronics Engineering
© 2025 by SSRG - IJEEE Journal
Volume 12 Issue 11
Year of Publication : 2025
Authors : Vijay Thokal, Purushottam R Patil, Pawan R Bhaladhare
10.14445/23488379/IJEEE-V12I11P111
pdf
How to Cite?

Vijay Thokal, Purushottam R Patil, Pawan R Bhaladhare, "Intelligent Identity Verification and Digital Onboarding System Using Deep Learning and RPA," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 11, pp. 124-138, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I11P111

Abstract:

Onboarding in industries such as fintech, telecom, and e-governance is usually plagued with problems of identity fraud, delays through manual processing, and poor scalability. This work proposes a generic end-to-end AI-driven customer onboarding system that overcomes these limitations using face recognition, Optical Character Recognition (OCR), liveness detection, and intelligence in decision-making. The framework puts into use MTCNN for face detection, FaceNet for facial embeddings, and 3D-CNN for real-time liveness detection to avoid spoofing. Document text is obtained through Tesseract OCR and optimized through preprocessing. Principal Component Analysis (PCA) is then utilized to reduce feature dimensionality. Final onboarding decisions are made using a Random Forest classifier based on fused document and biometric features. Robotic Process Automation (RPA) is used to automate the execution of decisions. The system is tested on the MIDV-500 dataset, achieving 98.1% classification accuracy and a 97.1% F1-score. ROC analysis reveals strong performance, with Area Under the Curve (AUC) values of 0.976 for face verification and 0.952 for liveness detection, indicating high discriminative power. The system performs better than current models and provides high accuracy, fraud protection, and automation. The scalable, explainable solution is suitable for real-world applications where fast, secure, and compliant onboarding is necessary.

Keywords:

AI-based onboarding, MTCNN, Facial recognition, Liveness detection, OCR, Identity verification, Random Forest, Digital KYC.

References:

[1] Mohit Yadav et al., “Intelligent Robotic Process Automation (RPA) Development,” IGI Global Scientific Publishing, pp. 105-132, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Jing Zhang, “Student Apartment Access Control System based on MTCNN-FaceNet Algorithm,” International Journal of Computational Intelligence and Applications, vol. 24, no. 1, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Santosh Gore et al., “Recommendation of Contemporary Fashion Trends via AI-Enhanced Multimodal Search Engine and Blockchain Integration,” 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, pp. 1676-1682, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Santosh Gore et al., “A Machine Learning-Based Detection of IoT Cyberattacks in Smart City Application,” ICT Analysis and Applications, Singapore, pp. 73-81, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Manuel Beck, Phase 7 in the Sales Cycle: AI in Onboarding and Support, Artificial Intelligence in Sales, Wiesbaden, pp. 115-128, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Smita Khairnar et al., “Face Liveness Detection using Artificial Intelligence Techniques: A Systematic Literature Review and Future Directions,” Big Data and Cognitive Computing, vol. 7, no. 1, pp. 1-35, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] S. Balasubramaniam et al., “Artificial Intelligence‐Based Hyperautomation for Smart Factory Process Automation,” Hyperautomation for Next‐Generation Industries, pp. 55-89, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Megha Chhabra et al., “Improving Automated Latent Fingerprint Detection and Segmentation using Deep Convolutional Neural Network,” Neural Computing and Applications, vol. 35, no. 9, pp. 6471-6497, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Alexander Lavin et al., “Technology Readiness Levels for Machine Learning Systems,” Nature Communications, vol. 13, no. 1, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Shiv Shankar Kumar Yadav, and Gaurav Mishra, “Robotic Process Automation Applications Across Industries: An Exploration,” 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), Greater Noida, India, pp. 26-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] D.N. Harshavardhan Reddy Malapati, Sai Sravanth Reddy Panyam, and Sudha Dandapani, “Enhancing PAN Card Security with OCR Based Information Extraction and Face Recognition for Reliable Identity Verification,” 2025 International Conference on Data Science, Agents and Artificial Intelligence (ICDSAAI), Chennai, India, pp. 1-6, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Pranav Khare, and Shristi Srivastava, “Transforming KYC with AI: A Comprehensive Review of Artificial Intelligence-Based Identity Verification,” Journal of Emerging Technologies and Innovative Research, vol. 10, no. 12, pp. 525-531, 2023.
[Google Scholar] [Publisher Link]
[13] Istiaque Ahmed et al., “A Systematic Review on Blockchain-Enabled eKYC: Leveraging SSI and DID for Secure and Efficient Identity Verification,” IEEE Internet of Things Journal, vol. 12, no. 21, pp. 44381-44401, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Seyf Kazamel, Umut Kocasarı, and Ali Alıcı, “An End-to-End Computer Vision System for Structured Information Extraction from Turkish ID Card Images,” Computational Science and Its Applications - ICCSA 2025: 25th International Conference, Istanbul, Turkey, Springer, pp. 51-64, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Bektemyssova Gulnara, and Akhmer Yerassyl, “Using Image Processing and Optical Character Recognition to Recognise ID cards in the Online Process of Onboarding,” 2022 International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mihai Alin Lazăr, “The Impact of Digital Natives' Expectations on IT Onboarding Processes,” Annals of the University Dunarea De Jos of Galati: Fascicle: I, Economics and Applied Informatics, vol. 31, no. 1, pp. 146-153, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Erwin Yulianto, Teguh Murdianto, and Al-Amin Al-Amin, “The Role of Artificial Intelligence (AI) in Records and Document Management,” COSMOS: Journal of Education, Economics and Technology, vol. 1, no. 6, pp. 484-499, 2024.
[Google Scholar] [Publisher Link]
[18] Khalid M.O. Nahar et al., “Recognition of Arabic Air-Written Letters: Machine Learning, Convolutional Neural Networks, and Optical Character Recognition (OCR) Techniques,” Sensors, vol. 23, no. 23, pp. 1-24, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Abhishek Potdar, Parva Barbhaya, and Sangeeta Nagpure, “Face Recognition for Attendance System using CNN based Liveliness Detection,” 2022 International Conference on Advances in Computing, Communication and Materials (ICACCM), Dehradun, India, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Nico Surantha, and Boy Sugijakko, “Lightweight Face Recognition-Based Portable Attendance System with Liveness Detection,” Internet of Things, vol. 25, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] U. Ganesh Naidu et al., “Person Vein Identification using CNN,” Proceedings of Data Analytics and Management, Singapore, vol. 3, pp. 45-59, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Houding Zhang, and Zexian Yang, “Biometric Authentication and Correlation Analysis based on CNN‐SRU Hybrid Neural Network Model,” Computational Intelligence and Neuroscience, vol. 2023, no. 1, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Plaifah Laimeеk, and Waree Kongprawechnon, “High-Value Fruit Biometric Identification via Triplet-Loss Technique,” Ph.D. Thesis, Thammasat University, pp. 1-55, 2022.
[Google Scholar] [Publisher Link]
[24] Lamia Mosbah et al., “Adocrnet: A Deep Learning OCR for Arabic Documents Recognition,” IEEE Access, vol. 12, pp. 55620-55631, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Dewan Ahmed Muhtasim, Monirul Islam Pavel, and Siok Yee Tan, “A Patch-Based CNN Built on the VGG-16 Architecture for Real-Time Facial Liveness Detection,” Sustainability, vol. 14, no. 16, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Esraa Asem et al., “Biometric CNN Model for Verification based on Blockchain and Hyperparameter Optimization,” International Journal of Computational Intelligence Systems, vol. 17, no. 1, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Konthee, “MIDV-500 - Identity Document Dataset,” Kaggle, 2022. [Online]. Available: https://www.kaggle.com/datasets/kontheeboonmeeprakob/midv500