SmartKYC

Authors

  • Narayan Poudel Department of Computer and Electronics Engineering, Kantipur Engineering College, Dhapakhel, Lalitpur, Nepal
  • Saugat Neupane Department of Computer and Electronics Engineering, Kantipur Engineering College, Dhapakhel, Lalitpur, Nepal
  • Smarika Shrestha Department of Computer and Electronics Engineering, Kantipur Engineering College, Dhapakhel, Lalitpur, Nepal
  • Subarna Shakya Department of Electronics and Computer Engineering, IOE Pulchowk Campus, Pulchowk, Lalitpur, Nepal
  • Suyasha Nepal Department of Computer and Electronics Engineering, Kantipur Engineering College, Dhapakhel, Lalitpur, Nepal

DOI:

https://doi.org/10.3126/injet.v2i2.78620

Keywords:

KYC, Text Extraction, Face Verification, Liveliness Detection, Machine Learning

Abstract

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.

Downloads

Download data is not yet available.
Abstract
157
PDF
125

Downloads

Published

2025-05-19

How to Cite

Poudel, N., Neupane, S., Shrestha, S., Shakya, S., & Nepal, S. (2025). SmartKYC. International Journal on Engineering Technology, 2(2), 215–229. https://doi.org/10.3126/injet.v2i2.78620

Issue

Vol. 2 No. 2 (2025)

Section

Articles

License

Copyright (c) 2025 International Journal on Engineering Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use.