Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204562,
        author = {Krish Chaudhari and Pratik Pacharne and Rohan Shinde and Amruta Gangaji},
        title = {Next-GEN EXAM EVALUATION: INTEGRATING OMR ACCURACY WITH AI-POWERED ASSESSMENT AND ADAPTIVE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4400-4406},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204562},
        abstract = {The increasing scale of academic and competitive examinations demands fast, accurate, and reliable evaluation systems. Traditional manual checking and hardware-dependent OMR solutions are time-consuming, error-prone, and difficult to scale. This paper presents a next-generation AI-powered exam evaluation system that automates the complete assessment process, from scanning OMR sheets to generating personalized feedback. The system uses computer vision techniques with OpenCV to detect marked responses from scanned OMR images, eliminating the need for specialized hardware. Additionally, handwritten question papers are processed using Optical Character Recognition (OCR) through Document AI, which converts them into structured digital format for automated test creation.
The system further integrates Large Language Models (LLMs) to enable intelligent features such as automatic answer generation, student performance analysis, and personalized feedback. A full-stack architecture is implemented using ReactJS for the frontend, Python Flask for backend processing, and Firebase for authentication and real-time database management. The platform supports end-to-end evaluation including test creation, student response handling, OMR processing, AI-based feedback, and chatbot-assisted doubt solving. Experimental results show high efficiency with rapid processing and real-time feedback generation. This approach enhances evaluation accuracy, reduces manual effort, and provides an adaptive learning experience, making it suitable for modern educational environments},
        keywords = {},
        month = {June},
        }