Download Project Document/Synopsis
Every person has a unique signature that is used primarily for personal identification and verification of important documents or legal transactions. Mostly used to authenticate checks, draughts, certificates, approvals, letters, and other legal documents. Because a signature is used in such critical activities, verification of its authenticity is essential.
This type of verification is critical in preventing document forgery and falsification in a variety of financial, legal, and commercial settings. Traditionally, signatures were manually verified by comparing them to copies of genuine signatures. This simple method may not be sufficient as technology advances, bringing with it new techniques for forgery and falsification of signatures.
So, in order to tackle such a problem new efficient tool is needed. Our Signature Verification System can help in the authentication of a handwritten signature by reducing human error.
The user would need to sign in using their basic information to log in. To verify a signature, the user would need to fill in two images, one will be the original image, and the second will be the comparison image. Once the images are filled in, the user will be directed to the results page to see the results.
For the purpose of classifying the signature classification model, we have implemented a machine-learning model. We will use CNN for this. To test and see the results, we will take a sample signature (about 100 sample pictures of the same signature) and compare the sample pictures of the original signature with other random signatures.The framework used in this project is Django. The Front End involves Html, CSS and JavaScript. The Back End involves MySQL Database. The Back End Language is Python.
Advantages
- The system is easy to maintain.
- It is user-friendly.
- It automatically detects without any human supervision.
- A simple and effective method for identifying a person’s signature.