Pan-Card Tampering Using

Computer Vision

Sriram R M - RA1811003040152
Department : B.Tech, CSE
Semester/ Year : VII / IV | SEC : C
Abstract
The purpose of this project is to detect tampering of PAN card with the help of
computer vision we are going to detect that whether the given image of PAN card is
original or tampered (fake).
This project will help different organization
in detecting whether the ID i.e. the PAN card
provided to them by their employees or
customers or anyone is original or not.
Existing System
Detecting tampered PAN card by extracting Permanent Account Number
from User uploaded image and checking with official department .
- Highly Time consuming processes , Limited to larger organisations only.
Detecting tampered PAN card using computer vision by only checking
Structural Similarity between the of original PAN card and the PAN card
uploaded by user.
- Finely tampered Image can’t give accurate output . as Structural Similarity will
be high.
Proposed System
Steps involved in this project are as follows :
1. Import necessary libraries (Skimage, Imutils, cv2, PIL, requests)
2. Scraping the tampered and original pan card from website.
3. Scaling down the shape of tampered image as original image.
4. Read original and tampered image.
5. Converting image into grayscale image.
6. Applying Structural Similarity Index (SSIM) technique between the two images.
7. Calculate Threshold.
8. Find contour using Imutils.
9. Draw a bounding rectangle using these contours
10. Experience real time contours and threshold on images.
11. Compare all the images and check the similarity score to decide tampering
Architecture
Technical Modules
Technical Modules
Module Implementation Details (CODE)
Import libraries & Resize
Changing the format & converting into grayscal
Structural similarity index (SSIM)
Calculating threshold and contours
Summary
- Finding out structural similarity of the images helped us in finding the difference
or similarity in the shape of the images.
- Similarly, finding out the threshold and contours based on those threshold for the
images converted into grayscale binary also helped us in shape analysis and
recognition.
- As, our SSIM is ~31.2% we can say that the image user provided is fake or
tampered.
- Finally we visualized the differences and similarities between the images using
by displaying the images with contours, difference and threshold.
Scope
This project can be used in different organizations where customers or users need to
provide any kind of id in order to get themselves verified. The organization can use
this project to find out whether the ID is original or fake. Similarly, this can be used
for any type of ID like Aadhar, voter id, etc.
Thank You

Sriram R M - RA1811003040152
Department : B.Tech, CSE
Semester/ Year : VII / IV | SEC : C