Omr Research Papers

Research Paper : Scanner-Based Optical Mark Recognition

Scanner-Based Optical Mark Recognition
Chatree Saengtongsrikamon*, Phayung Meesad**, Sunantha Sodsee*

Abstract The objective of this work was to develop Optical Mark Recognition (OMR) software for implementation in the simple scanner and for its usage as an OMR machine. It was developed using Java language. The software will help the assessor to capture and score responses of the multiple choices-answer sheets with a ccur acy and effi cien cy. Moreover, it was proposed to be a replacement for the costly OMR machine. The developed software was evaluated by simulating an actual implementation. It interpreted 1,000 answer sheers scanned by 5 different scanners in 4 different resolutions. The evaluation’s results were favorable, with an estimated number of mistakes were less than 1 per 1,000 or 0.1 percent. As a result, the quality and accuracy of the software that has been developed is thus within acceptable limits. Keyword: Optical Mark Recognition, Optical Mark Reader 1. Introduction It is undeniable that the method of assessment is very important in any education system. The assessment is a powerful force in driving the way students learn. From the students’ perspective, only the most important knowledge in a subject is assessed. Also, the teachers usually apply an appropriate assessment method to ensure that their students gain the maximum knowledge from the instruction. So by changing the assessment method, the various subject teachers can affect the way students learn the subject content. Different ways of assessment provide the measurement of a student’s capabilities in different contexts. Stiggins [1] groups the different methods of assessment into 4 main categories : Selected Response, Essays, Performance Assessment and Personal Communication. The Multiple Choice Questions (MCQs), which is a method in the Selected Response category, is the most common method chosen to assess the students in

References: [1] Stiggins, R. Student-involved assessment for learning. Upper Saddle River, N.J., Prentice Hall, 2005. [2] Bergeron, Bryan P. (1998, August). Optical mark recognition. Postgraduate Medicine online. June 7, 2006. [3] Haag, S., Cummings, M., McCubbrey, D., Pinsonnault, A., Donovan, R. Management Information Systems for the Information Age, 3rd ed., Canada: McGraw-Hill Ryerson, 2006. [4] Gonzalez, R. C. and Wintz, P. Digital Image Processing, 2nd ed., Addison-Wesley, Reading, Massachusetts, pp. 30-31 and 130-134 , 1987. [5] McConnell, Steve . Software Estimation: Demystifying the Black Art. N.C., Microsoft Press, 2006. [6] Heywood John, Assessment in Higher Education. Jessica Kingsley Publishers, London, Pages 350-372, 2000. [7] TAWIP. Image Capture, Image Recognition and Image Processing.[Online],(n.d.).,Available from : http://www. tawpi.org/image-capture-recognition-processing.html [8] Payne DA. The Assessment of Learning — Cognitive and Affective. Lexington, Ky: D.C. Heath and Company: 255,272, 1974. [9]. Lowe Doug. Java™ All-in-One Desk Reference For Dummies. River Street, Hoboken, Wiley Publishing, 2005. [10] French, Christine L. “A Review of Classical Methods of Item Analysis”. Presened at the annual meeting of the Southwest Educational Research Association, New Orleans, 2001. [11] Raksakietisak Sunee. The Development of Online Item banking and Testing System. Masters Thesis, Faculty of Science, Srinakharinwirot University, 2003. [12] Pornsiriprasert Nisarath. Design and development of page segmentation program for character recognition. Masters Thesis, Chulalongkorn University, 2002. Figure 10 : Sample Result of Item analysis process done and a re-scoring of the answers is needed. The last function, which is the Analysis function, allows the user to conduct an Item analysis. 3.2 Evaluation Results After developing the proposed software, this program is tested by the author to ensure that all functions work correctly. The next step is the evaluation. The main propose of the evaluation is to check the software for accurate results. This is the most important process in checking for software reliability as incorrect results could potentially result in major problems and is thus highly undesirable. The software was evaluated by executing the runs repeatedly. The images were scanned by 5 different scanners. The scanner models are namely: Canon MX318, Lexmark-X6170, Epson CX5500, HP LaserJet3020, and Canon LiDE20. Each scanner was used to scan the test images in 4 different resolutions ( 600 dpi, 300 dpi, 150 dpi and 75 dpi). After scanning 50 test-answer sheets marked by 50 different students with 5 scanners in 4 resolutions, the 1,000 images (50x5x4) were produced and ready to be executed by the program. As a result, there were 1,000 images interpreted via this valuation and there were no wrong responses detected from the execution. Consequently, The results of the evaluation were favorable, with an estimated number of mistakes of less than 1 per 1,000 or 0.1 percent. The quality and reliability of the software that has been developed is thus within acceptable limits. 4. Conclusion and Future Work The Optical Mark Recognition (OMR) was developed for facilitating the MCQ scoring. The OMR machine or Optical Mark Readers are used to capture and score responses on scoring sheets that are then used by the assessor for analysing and reporting. It is a powerful tool in scoring with accuracy and efficiency, but it is also a very expensive tool that has not seen a substantial reduction in cost even as new technologies have constantly evolved to bring technological costs lower than ever. The new OMR machines are able to perform faster and with better accuracy than the old ones. However, even as the new model is priced at the same price as the earlier versions, this is still too expensive to be commonly used in the smaller sized schools or education institutes. The problem is made »Õ·Õè 5 ©ºÑº·Õè 9 Á¡ÃÒ¤Á - ÁԶعÒ¹ 2552 ÇÒÃÊÒÃà·¤â¹âÅÂÕÊÒÃʹà·È 73