VivaKitOnline Exam Proctoring & Cheating Detection Intelligence
Automated multi-modal computer vision and deep learning examination proctoring for academic institutions, certification bodies, and remote testing portals. Concurrently evaluates 478 3D facial landmarks to extract precise metric Euler angles (Yaw, Pitch, Roll) and iris pupil displacement to detect candidates glancing away from monitors or viewing unauthorized cheat materials. Integrates real-time SSDLite deep learning to intercept concealed mobile phones, secondary laptops, unauthorized textbooks, and bystanders. Employs Exponential Moving Average temporal risk filtering to reduce false alarms caused by natural blinking or breathing, generating timestamped incident logs and integrity reports for review by a human invigilator.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| Total Pipeline Throughput | 17.0 FPS (58.7 ms latency on standard CPU) |
| Violation Scenario Accuracy (synthetic) | 100% on the kit's 120-trial synthetic avatar suite (head turn, phone, absence, normal) |
| False Alarm Rate (synthetic) | 0% on synthetic normal-activity scenarios |
| Validation Note | Accuracy measured on synthetic drawn scenarios only - test with real webcam sessions (with consent) for your deployment |
Evaluated across multi-angle candidate orientations, varying lighting conditions, and prohibited device test scenarios. Strictly adheres to permissive Apache-2.0 and BSD-3 licensing with zero AGPL copyleft encumbrance. Includes automated pytest smoke test suite, interactive Gradio 6 multi-tab inspection console, 3D pose vector projections, exportable session audit logs, and 15 viva voce questions with PnP mathematics.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
Google MediaPipe Tasks Face Landmarker (Apache 2.0, ai.google.dev) and Microsoft COCO Dataset (CC BY 4.0, cocodataset.org) evaluated on synthetic multi-scenario proctoring benchmarks by VivaKit.
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.