HALL TICKET FRAUD DETECTION SYSTEM USING ANN CLASSIFIER

Hall tickets are commonly used in both online and offline examinations. The problem of fraud in hall ticket detection and recognition is of great interest in the document domain as it enables us to identify the ownership of the document. In the context of document image retrieval, hall tickets provide an important form of indexing that enables effective exploration of data. Given a large collection of hall tickets, detecting a fraud hall ticket is a highly effective way of retrieving documents. The main focus of this paper is to detect fraud in the exam hall tickets which consists of textual elements like name, register number, etc and graphical elements like a photo of the candidate. The system is aimed to detect unauthorized person appearing for examination i.e., by replacing the original candidate photo with an unauthorized person.The detection of fraud in hall tickets is a challenging task for the purpose of classifying the distinct image entities in an automated approach. The hall ticket images are used in the proposed system for off-line exams to provide security based on their entities. The hall ticket images are processed and segmented using morphological operation. Each segment is labeled using connected component labeling technique. The features such as area, form vector, roundness, compactness, density, etc are extracted. ANN classifier is used to detect the fraud in hall ticket images i.e., if candidate name, seat number is mismatched with candidate photo then the system displays person is unauthenticated. The system is developed for the offline examination system to detect the fraudulent hall ticket. The behavior of the student is visualized by using different visualization techniques. Different data visualization techniques are discussed, for varying dimensional data. Scatter plot, survey plot, line graph and bar charts are used for visualizing two dimensional data. The same techniques are used in visualization of three dimensional data, by addition of the third dimension perpendicular to the remaining two dimensions. Icon based, hierarchical methods, geometrical methods and pixel oriented techniques are used for visualizing high dimensional data. By usage of these techniques, tracking of the student behavior is done and continues monitoring is provided thus implementing an enhanced security in online exam.

[1] “Anandavalli D1, Devi Nachiyar N2, Deepshika H3, Priyadharshini M4” Automated Fraud Detection Framework in Examination Halls, International Research Journal of Engineering and Technology (IRJET). [2] Sejal. S. Chhabile*1, Dr. Ashwini Kumar Varma*2 “AUTOMATED FRAUD DETECTION IN EXAMINATION FROM HALL TICKET” International Research Journalof Modernization in Engineering Technology and Science.Volume:03/Issue:03/March-2021. [3] Shridevi Soma, Vidyashree S.A , An Automated Fraud Detection of Hall Ticket in an Offline Examination System using ANN Classifier International Journal of Computer Applications (0975 – 8887) Volume 126 – No.8, September 2015. [4]Tejaswini.S.G.FRAUD DETECTION IN EXAMINATION USING LBP METHOD” International Journal of Latest Engineering and Management Research (IJLEMR)ISSN: 2455-4847. [5] Liang, X., Cai, X., Li, L., & Chen, Y. (2019). Facial feature extraction method based on shallow and deep fusion CNN. 2019 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). doi:10.1109/fskd.2019.8393320. [6] Suriya Prakash, J., Annamalai Vignesh, K., Ashok, C., & Adithyan, R. (2012). Multi-class Support Vector Machines classifier for machine vision application. 2021 International Conference on Machine Vision and Image Processing (MVIP). doi:10.1109/mvip.2012.6428794. [7] Tyas Purwa Hapsari, D., Gusti Berliana, C., Winda, P., & Arief Soeleman, M. (2020). Face Detection Using Haar Cascade in Difference Illumination. 2018 International Seminar on Application for Technology of Information and Communication. doi:10.1109/isemantic.2018.8549752. [8] Beveridge, J. Ross, et al. , Face Recognition Across Pose and Illumination ("Factors that influence algorithm performance in the face recognition grand challenge." Computer Vision and Image Understanding113.6 (2021): 750-762.). PRMIT&R//DCSE//2022-23 Page 43Hall Ticket Fraud Detection System using ANN Classifier [9] Smart card technology IJSER International Journal of Scientific & Engineering Research, Volume 7, Issue 3, March-2016 157 ISSN 2229-5518 IJSER © 2020. [10] Adams O. U. Onuka1 , Esther O. Durowoju2 “Stakeholder ’ Role in Curbing Examination in Nigeria” International Journal of Economy, Management, and social sciences, Malpractice 2(6) June 2013 pp:342- 348.