• Shreyas Yerole
• Rohini Hanchate
• Nazir Lalloti
• Piyush Mahajan

The Permanent Account Number (PAN) Card is an important document that serves as an identification tool for many more purposes like tax payment, verification medium in banks, companies and in other government services in India. However, with the increasing demand for PAN Cards, fraudulent activities involving fake PAN Cards have also increased. To address this issue, a system for detecting fake and real PAN Cards using Convolutional Neural Networks (CNN) is proposed. The proposed system uses a dataset of real and fake PAN Cards to train the CNN model, which can classify PAN Cards as real or fake with high accuracy. The model is designed to extract relevant features from the PAN Card images and use them to distinguish between real and fake ones. The proposed system has the potential to provide an efficient and reliable solution to the problem of detecting fake PAN Cards, which can help prevent tax fraud, duplication detail of other person etc. and improve the overall integrity of the tax system in India.

Machine Learning, Convolutional Neural Network, PAN card, Real, Fake

"Fraud Detection of PAN Card Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.h864-h871, May-2023, Available :http://www.jetir.org/papers/JETIR2305812.pdf

"Fraud Detection of PAN Card Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. pph864-h871, May-2023, Available at : http://www.jetir.org/papers/JETIR2305812.pdf