{"title":"Cost Effective Real-Time Image Processing Based Optical Mark Reader","authors":"Amit Kumar, Himanshu Singal, Arnav Bhavsar","volume":141,"journal":"International Journal of Computer and Information Engineering","pagesStart":787,"pagesEnd":792,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10009558","abstract":"In this modern era of automation, most of the academic<br \/>\r\nexams and competitive exams are Multiple Choice Questions (MCQ).<br \/>\r\nThe responses of these MCQ based exams are recorded in the<br \/>\r\nOptical Mark Reader (OMR) sheet. Evaluation of the OMR sheet<br \/>\r\nrequires separate specialized machines for scanning and marking.<br \/>\r\nThe sheets used by these machines are special and costs more than a<br \/>\r\nnormal sheet. Available process is non-economical and dependent on<br \/>\r\npaper thickness, scanning quality, paper orientation, special hardware<br \/>\r\nand customized software. This study tries to tackle the problem of<br \/>\r\nevaluating the OMR sheet without any special hardware and making<br \/>\r\nthe whole process economical. We propose an image processing<br \/>\r\nbased algorithm which can be used to read and evaluate the scanned<br \/>\r\nOMR sheets with no special hardware required. It will eliminate the<br \/>\r\nuse of special OMR sheet. Responses recorded in normal sheet is<br \/>\r\nenough for evaluation. The proposed system takes care of color,<br \/>\r\nbrightness, rotation, little imperfections in the OMR sheet images.","references":"[1] Sumitra B. Gaikwad, \u201cImage Processing Based OMR Sheet Scanning,\u201d\r\nInternational Journal of Advanced Research in Electronics and\r\nCommunication Engineering (IJARECE).\r\n[2] Rusul Hussein Hasan, Emad I Abdul Kareem, \u201cAn Image Processing\r\nOriented Optical Mark Reader Based on Modify MultiConnect\r\nArchitecture MMCA,\u201d International Journal of Modern Trends in\r\nEngineering and Research (IJMTER) Volume 02,Issue 07, (July 2015).\r\n[3] Qi-Chuan Tian and Quan Pan and Yong-Mei Cheng and Quan-Xue\r\nGao, \u201c Fast algorithm and application of Hough transform in iris\r\nsegmentation,\u201d International Conference on Machine Learning and\r\nCybernetics, 2004.\r\n[4] Gorgevic Dejan1, Grcevski Nikola2, Mihajlov Dragan1, \u201cA Simple\r\nSystem For Automatic Exam Scoring Using Optical Markup Reader,\u201d\r\nApplied Automatic System AAS\u20192000.\r\n[5] S, Rakesh and Atal, Kailash and Arora, Ashish, \u201c Cost Effective Optical\r\nMark Reader,\u201d International Journal of Computer Science and Artificial\r\nIntelligence, 2013.\r\n[6] Deng, Hui and Wang, Feng and Liang, Bo, \u201cA Low-Cost OMR Solution\r\nfor Educational Applications,\u201d 2008.\r\n[7] N. H. Lestriandoko and R. Sadikin, \u201c Circle detection based on\r\nhough transform and Mexican Hat filter,\u201d 2016 International Conference\r\non Computer, Control, Informatics and its Applications (IC3INA),\r\nTangerang, 2016, pp. 153-157.\r\n[8] OpenCv Documentation, (Online). Available:\r\nhttps:\/\/docs.opencv.org\/3.1.0\/da\/d53\/tutorial py houghcircles.html\r\n[9] Sebastian Ruder, \u201c An overview of gradient descent optimization\r\nalgorithms,\u201d CoRR, abs\/1609.04747, 2016.\r\n[10] Puneet and Naresh Garg, \u201c Article: Binarization Techniques used for\r\nGrey Scale Images.\u201d International Journal of Computer Applications\r\n71(1):8-11, June 2013.\r\n[11] Devi, H. K. A, \u201c Thresholding: A Pixel-Level Image Processing\r\nMethodology Preprocessing Technique for an OCR System\r\nfor the Brahmi Script. \u201d Ancient Asia. 1, pp.161165. DOI:\r\nhttp:\/\/doi.org\/10.5334\/aa.06113.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 141, 2018"}