International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Next-Gen Exam Evaluation: Integrating OMR Accuracy with AI-Powered Assessment and Adaptive Learning |
|---|---|
| ABSTRACT | The automation of exam evaluation has become essential in modern education systems, where large-scale assessments require accuracy, speed, and fairness. Traditional manual and hardware-dependent OMR systems are slow, error-prone, and costly. This paper presents an integrated AI-based evaluation framework that combines Optical Mark Recognition (OMR) with Optical Character Recognition (OCR) and Natural Language Processing (NLP) for automated grading of both objective and handwritten theory answers. Using computer vision techniques with Convolutional Neural Networks (CNN), the system detects marked answers from scanned sheets without specialized hardware. The OCR module converts handwritten responses to digital text, which are then evaluated using NLP-based semantic similarity measures against model answers. A Machine Learning module performs adaptive analysis to identify weak areas and generate personalized feedback. The proposed model ensures accuracy, scalability, and accessibility, aiming to make evaluation faster and more transparent for both educators and students. |
| AUTHOR | KRISH CHAUDHARI, PRATIK PACHARNE, ROHAN SHINDE, AMRUTA GANGAJI Student, Department of Computer Engineering, RMD Sinhgad School of Engineering, Pune, India Assistant Professor, Department of Computer Engineering, RMD Sinhgad School of Engineering, Pune, India |
| VOLUME | 181 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1402017 |
| pdf/17_Next-Gen Exam Evaluation Integrating OMR Accuracy with AI-Powered Assessment and Adaptive Learning.pdf | |
| KEYWORDS | |
| References | [1] Y. Ju, X. Wang, and X. Chen, “Research on OMR Recognition Based on Convolutional Neural Network TensorFlow Platform,” in Proc. 11th Int. Conf. Measuring Technology and Mechatronics Automation (ICMTMA), IEEE, 2019, pp. 688–691, doi: 10.1109/ICMTMA.2019.00157. [2] P. J. Mistry and N. N. Patel, “A Novel Approach – Automatic Paper Evaluation System,” Int. Res. J. Eng. Technol. (IRJET), vol. 6, no. 3, pp. 3901–3905, 2019. [3] Md. E. Alam, F. Akter, T. Alam, S. Farid, Md. I. Haque, and M. Arefin, “Approaching Computer Vision and Image Processing Technique for Optical Mark Recognition Sheet Scan and Verification,” Int. J. Eng. Res. Technol. (IJERT), vol. 11, no. 2, pp. 1–6, 2022. [4] Md. A. Rahaman and H. Mahmud, “Automated Evaluation of Handwritten Answer Script Using Deep Learning Approach,” Int. J. Comput. Sci. Inf. Security (IJCSIS), vol. 20, no. 4, pp. 45–52, 2022. [5] J. Sanchez and A. Lopez, “Automated Multiple-Choice Test Checking System,” J. Inf. Syst. Eng. Manage., vol. 7, no. 3, pp. 1–9, 2022. [6] “Analysis of OMR Sheet Using Advanced Intelligent Techniques,” Int. J. Res. Publication Rev., vol. 4, no. 6, pp. 20–27, 2023. [7] S. Srihari and J. Collins, “Automatic Scoring of Short Handwritten Essays in Reading Assessment,” Int. J. Document Anal. Recognit., vol. 26, no. 2, pp. 145–152, 2023. [8] L. Li, P. Zhao, and M. Zhang, “Automated Assessment of Multimodal Answer Sheets in the STEM Domain,” arXiv:2409.15749, 2024. [9] D. Patel and K. Sharma, “NLP and OCR-Based Automatic Answer Script Evaluation System,” Int. J. Comput. Appl., vol. 186, no. 42, pp. 1–7, 2024. [10] A. Shah and P. Deshmukh, “Survey on Automated Answer Sheet Evaluation and Recognition,” Int. J. Novel Res. Dev. (IJNRD), vol. 9, no. 6, pp. 145–151, 2024. |
