• Durgarao Kumuli
• M.Naga Keerthi

This project presents a novel method for optical mark recognition (OMR) correction utilizing machine learning[2](ml) techniques. While conventional OMR correction approaches have conventionally dominated educational assessments, this research showcases a shift toward automated, precise, and insightful grading. The core of this system involves capturing high-resolution images of individual student OMR sheets using commonly available digital devices. Central to this approach is the ml model, extensively trained to interpret and grade these images accurately, thus reducing the need for manual correction. An innovative aspect of this system is its capacity for difficulty analysis. Through the examination of collective responses, the ML model identifies questions frequently answered incorrectly, offering educators valuable insights into areas where students face challenges. This enables educators to tailor instructional methods for enhanced learning outcomes. In addition to correction, the system also identifies and highlights the top three scores on the test. This functionality streamlines the process of recognizing outstanding performers, facilitating prompt acknowledgment and rewards.

optical mark recognition (OMR), machine learning (ml), automated grading, high-resolution images, digital devices, ml model training, accurate interpretation, reduced manual correction, top scores identification, outstanding performers.

"Next-gen educational assessment: automated OMR correction and gradings analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.d130-d137, July-2024, Available :http://www.jetir.org/papers/JETIR2407313.pdf

"Next-gen educational assessment: automated OMR correction and gradings analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppd130-d137, July-2024, Available at : http://www.jetir.org/papers/JETIR2407313.pdf