Smart Signature Verification Using Machine Learning (EVOLVE) / (Record no. 611690)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01920nam a22001817a 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | NUST |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20240923121753.0 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 621.382,SAQ |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Saqib, Hamza |
| 9 (RLIN) | 125982 |
| 245 ## - TITLE STATEMENT | |
| Title | Smart Signature Verification Using Machine Learning (EVOLVE) / |
| Statement of responsibility, etc. | Hamza Saqib, Muhammad Attiq Ur Rehman, Rameez Uddin, Maham Aslam. |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | MCS, NUST |
| Name of publisher, distributor, etc. | Rawalpindi |
| Date of publication, distribution, etc. | 2024 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 72 p |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | This work focuses on the implementation of a smart signature verification system using machine learning. The main goal of this project is to develop a model which can deliver both speed and precision, making it quick in processing while consuming less resources. The plan for the project includes blending a Machine Learning(ML) model with mobile deployment strategies to provide users with an effortless experience. This method has a lot of potential to make authentication processes more reliable and trustworthy, dealing with basic difficulties in security areas. Using the most recent technology, this project opens new endeavors for using Machine Learning.<br/>The proposed system uses Siamese neural network which is trained on CEDAR dataset for strong signature verification. The already existing Siamese Neural Network model reduction is achieved in terms of memory optimization and reduced processing time thus make it light and fast in computation deployment. The model gets combined with Tensor Flow Lite to make it light and quick in functioning therefore getting an optimized model. Furthermore, we built a Flutter app that can effectively put the optimized model onto mobile devices. This new method not just makes signature verification better, it also creates an example for using machine learning and mobile deployment to enhance security rules in the time ahead. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | UG EE Project |
| 9 (RLIN) | 118090 |
| 651 ## - SUBJECT ADDED ENTRY--GEOGRAPHIC NAME | |
| Geographic name | BEE-57 |
| 9 (RLIN) | 125983 |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor Dr Alina Mirza |
| 9 (RLIN) | 118355 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Project Report |
No items available.