Method of verifying declared identity in optical answer sheets

作者：Levi Joseph A^*; Solewicz Yosef A; Dvir Yael; Steinberg Yisca

来源：Soft Computing, 2011, 15(3): 461-468.

DOI：10.1007/s00500-009-0526-x

• Forensic science
• Support vector machine
• Optical mark recognition
• Examinations
• Document examination
• Impersonation

In the use of optical answer sheet examinations, occasionally the identity of the examinee is in question. A novel method for characterizing the personal quality of mark shapes in optically read answer sheets is described. The method may be used to identify imposters in multiple choice examinations. All the marks are segmented and measured in multiple parameters including area, dimensions, perimeter and optical density. Imposter decisions are made on the collected data by comparing an identified test form against the form in question in comparison with a population using SVM (support vector machine) modeling. In testing the method, 300 test forms from 100 examinees from past tests were used. An EER (equal error rate) of 15-17% was found. While performance of the presented method is currently insufficient for practical purposes, future research options have been mentioned.

• 出版日期2011-3