MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115446 A) filed by Prabakaran Selvaraj; Mrs. T. Gayathri; Mrs. V. Manimala; V. S. B. Engineering College, Karur; and Dr. P. Anbumani on September 26, 2026, for Automated Examination Malpractice Detection System.
Inventors include Prabakaran Selvaraj; Mrs. T. Gayathri; Mrs. V. Manimala; V. S. B. Engineering College, Karur; and Dr. P. Anbumani.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: Examination malpractice is a major threat to academic integrity. Traditional invigilation methods often fail due to human limitations, especially in large examination halls. This project proposes an automated image-based examination malpractice detection system using Machine Learning and Deep Learning techniques. The system detects cheating behaviors such as cheat-bit usage, mobile phone usage, answer sheet exchange, and suspicious movements using real-time CCTV surveillance footage. The methodology combines handcrafted feature extraction techniques such as Histogram of Oriented Gradients (HOG) and Binary Robust Invariant Scalable Keypoints (BRISK) with deep learning-based feature extraction using ResNet50. Multiple classifiers including Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Logistic Regression, XGBoost, and LightGBM are evaluated. Experimental results demonstrate that LightGBM combined with ResNet50 features achieves the highest accuracy of 94.1%. The proposed system enhances fairness, reduces human error, and provides a scalable solution for examination monitoring.
Disclaimer: Curated by HT Syndication.
