Abstract

In order to put OMR (Optical Mark Recognition) into practice using a common scanner, we have created a special application for this project. Our project's aim is to provide an OMR-based grading system to academic institutions. Each student will be given a sheet with blank circles for grading. To automatically grade student response sheets on a mobile device, we use an image processing technique. The program will automatically tally student grades and save the results to a database. In addition, with the push of a button, a list of defaulters will be generated.The present project was inspired by the need to automate multiple-choice evaluations in school contests at a low cost. This was done by combining optical mark recognition (OMR) technology with artificial vision algorithms for multiple choice questions. It was able to assess the amount of precision using common scanning technologies based on four critical variables, including economic images, the identification and repair of images with changes, student coding, and time reading. The recognition success has been calculated as 97.6%. OMR is useful for applications in which large numbers of hand-filled forms need to be processed quickly and with great accuracy, such as surveys, questionnaires. OMR allows for processing of hundreds or thousands of physical documents per hour. The existing system requires special hardware which turns out to be very costly for any organization. So using such a system may be cost inefficient or not feasible by organizations. The error rate for OMR technology is less than 1.5%However, the OMR technique does have its limitations, such as its inability to deal with inaccurate printing or thin materials. In this research, a fresh strategy for improving OMR is explored. After scanning papers that have been structured and marked according to a template, software may examine the resultant image to identify which answers were circled. We also detail how to fix mistakes introduced by modifying the scanned copy using techniques like resizing, rotating, and transposing.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.