Peningkatan Akurasi Pembacaan Lembar Jawaban Komputer dengan Memperbaiki Ketidaksimetrisan Citra Hasil Pemindaian Menggunakan Transformasi Homografi

 Prayitno Prayitno (Universitas Dian Nuswantoro, Semarang, Indonesia)
 Guruh Fajar Shidiq (Universitas Dian Nuswantoro, Semarang, Indonesia)
 Ahmad Zainal Fanani (Universitas Dian Nuswantoro, Semarang, Indonesia)
 (*)M. Arief Soeleman Mail (Universitas Dian Nuswantoro, Semarang, Indonesia)

(*) Corresponding Author

Submitted: August 12, 2023; Published: October 22, 2023


Answer Sheet Reading Computers are one of the technologies for converting images into information which continues to develop until now. Some of the applications of this technology include correcting various school exams, psychological tests, surveys and voting. Accuracy is something that is often a problem in various studies on reading computer answer sheets. Accuracy is greatly influenced by the scanned image. In the process of scanning computer answer sheets, images often produce asymmetry, such as tilting, shifting and dilatation.The process of scanning computer answer sheets often produces asymmetrical images, such as tilted, shifted and dilated.  This incident will affect the accuracy of the results of reading the computer answer sheet, due to deformation of the shape between the reference image and the scanned image. This study aims to improve asymmetric images to become symmetrical with the Homografi transformation in order to get better reading accuracy. The results showed that the improvement of image symmetry with Homografi transformation was better than the skew correction method. This is shown from the respective RMSE values, the Homografi transformation method produces an RMSE value of 51.54 and the skew correction method produces a value of 67.04. The results of the study also stated that the accuracy of reading computer answer sheets with the Homografi transformation method was better than skew correction. The skew correction accuracy is 95.8%, while the Homografi transformation is 99.3%.


Improved Accuracy; Image Asymmetry; LJK; Homography; OMR

Full Text:


Article Metrics

Abstract view : 223 times
PDF - 68 times


G. Qorik et al., “Deteksi Pilihan Jawaban Otomatis pada Lembar Jawaban Komputer Menggunakan Metode Image Thresholding dan Contour Shorting,” COREAI J. Kecedasan Buatan, Komputasi dan Teknol. Inf., vol. 1, no. 1, pp. 1–9, 2020.

E. M. de Elias, P. M. Tasinaffo, and R. Hirata, “Optical Mark Recognition: Advances, Difficulties, and Limitations,” SN Comput. Sci., vol. 2, no. 5, 2021, doi: 10.1007/s42979-021-00760-z.

D. A. Hasibuan, “Pemeriksa Lembar Jawaban dengan Image Recognition Checking the Answer Sheet with Image Recognition,” JITE (Journal Informatics Telecommun. Eng., vol. 2, no. 1, pp. 1–8, 2018, [Online]. Available:

M. S. Konuk, “Development and Application of Android Based Mobile Optical Test Reading System,” Innov. Intell. Syst. Appl. Conf., 2020, doi: 10.1109/ASYU50717.2020.9259807.

J. Muangprathub, O. Shichim, Y. Jaroensuk, and S. Kajornkasirat, “Automatic grading of scanned multiple choice answer sheets,” Int. J. Eng. Technol., vol. 7, no. 2, pp. 175–179, 2018, doi: 10.14419/ijet.v7i2.23.11910.

H. Fahmi, M. Zarlis, H. Mawengkang, N. Zendrato, and Sulindawaty, “The Using of Thresholding and Region Merging Algorithm for Correcting the Multiple Choice Answer Sheets,” J. Phys. Conf. Ser., vol. 1255, no. 1, 2019, doi: 10.1088/1742-6596/1255/1/012047.

A. E. Tümer and Z. Küçükkara, “An Image Processing Oriented Optical Mark Recognition and Evaluation System,” Int. J. Appl. Math. Electron. Comput., vol. 6, no. 4, pp. 59–64, 2018, doi: 10.18100/ijamec.2018447788.

M. Afifi and K. F. Hussain, “The achievement of higher flexibility in multiple-choice-based tests using image classification techniques,” Int. J. Doc. Anal. Recognit., 2019, doi: 10.1007/s10032-019-00322-3.

R. A. Tamim, M. H. Bappy, S. Newaz, A. Islam, and A. Sreashtho, “Automatic Document Feeding Scanner: A Low Cost Approach,” 2018 21st Int. Conf. Comput. Inf. Technol. ICCIT 2018, no. 1, pp. 1–7, 2019, doi: 10.1109/ICCITECHN.2018.8631946.

H. Yusril Ichsan Hernafi, Tengku A. Riza, “Aplikasi Android Koreksi Lembar Jawaban Komputer Menggunakan OpenCV Android Apllication for Correcting Computer Answer Sheet using OpenCV,” e-Proceeding Appl. Sci., vol. 6, no. 1, pp. 477–489, 2020.

S. Shivapur, H. Tabassum, J. Najmusherh, and N. R. Deepak, “OMR Sheet Scanner using Image Processing in Android,” vol. 3, no. 3, pp. 1–8, 2021.

E. M. De Elias, P. M. Tasinaffo, and R. Hirata, “Alignment, Scale and Skew Correction for Optical Mark Recognition Documents Based,” Proc. - 15th Work. Comput. Vision, WVC 2019, pp. 26–31, 2019, doi: 10.1109/WVC.2019.8876933.

A. Kumar, H. Singal, and A. Bhavsar, “Cost Effective Real-Time Image Processing Based Optical Mark Reader,” World Acad. Sci. Eng. Technol. Int. J. Comput. Inf. Eng., vol. 12, no. 9, pp. 787–791, 2018.

G. M. R. I. Rasiq, A. Al Sefat, and M. M. F. Hasnain, “Mobile based MCQ Answer Sheet Analysis and Evaluation Application,” Proc. 2019 8th Int. Conf. Syst. Model. Adv. Res. Trends, SMART 2019., pp. 144–147, 2020, doi: 10.1109/SMART46866.2019.9117468.

I. A. Belag, Y. Gultepe, and T. M. Elmalti, “An Image Processing Based Optical Mark Recognition with the Help of Scanner,” Int. J. Eng. Innov. Res., vol. 7, no. 2, pp. 2277–5668, 2018.

J. Tong, H. Shi, C. Wu, H. Jiang, and T. Yang, “Skewness correction and quality evaluation of plug seedling images based on Canny operator and Hough transform,” Comput. Electron. Agric., vol. 155, no. October, pp. 461–472, 2018, doi: 10.1016/j.compag.2018.10.035.

M. F. Rizal, R. Sarno, and S. I. Sabilla, “Canny Edge and Hough Circle Transformation for Detecting Computer Answer Sheets,” Proc. - 2020 Int. Semin. Appl. Technol. Inf. Commun. IT Challenges Sustain. Scalability, Secur. Age Digit. Disruption, iSemantic 2020, pp. 346–352, 2020, doi: 10.1109/iSemantic50169.2020.9234208.

G. N. A. A. Putra, I. K. Buda, and I. N. Payuyasa, “Penerapan Komposisi Simetris Dan Asimetris Pada Dokumentasi Acara Miss Teen Internasional Indonesia 2021,” J. Film dan Telev. Calacitra, vol. 02, no. 02, pp. 1–8, 2022.

R. Ahad, R. Toufiq, and S. U. Zaman, “Information Retrieval from Damage OMR Sheet by Using Image Processing,” 3rd Int. Conf. Electr. Comput. Telecommun. Eng. ICECTE 2019, pp. 153–156, 2019, doi: 10.1109/ICECTE48615.2019.9303521.

K. Rachchh and E. S. Gopi, Inclusion of vertical bar in the omr sheet for image-based robust and fast omr evaluation technique using mobile phone camera, vol. 828. Springer Singapore, 2019. doi: 10.1007/978-981-13-1610-4_4.

J. Liu, S. Yang, Y. Fang, and Z. Guo, “Structure-Guided Image Inpainting Using Homography Transformation,” IEEE Trans. Multimed., vol. 20, no. 12, pp. 3252–3265, 2018, doi: 10.1109/TMM.2018.2831636.

H. Yoo and K. Jun, “Deep homography for license plate detection,” Inf., vol. 11, no. 4, 2020, doi: 10.3390/INFO11040221.

Q. Zhou and X. Li, “STN-Homography: Direct estimation of homography parameters for image pairs,” Appl. Sci., vol. 9, no. 23, 2019, doi: 10.3390/app9235187.

Y. Zhang, J. Zhong, H. Yu, and L. Kong, “Research on deskew algorithm of scanned image,” Proc. 2018 IEEE Int. Conf. Mechatronics Autom. ICMA 2018, pp. 397–402, 2018, doi: 10.1109/ICMA.2018.8484591.

S. S. Bafjaish, M. S. Azmi, M. N. Al-Mhiqani, A. R. Radzid, and H. Mahdin, “Skew detection and correction of Mushaf Al-Quran script using Hough transform,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 8, pp. 402–409, 2018, doi: 10.14569/ijacsa.2018.090852.

R. Zeng, S. Denman, S. Sridharan, and C. Fookes, “Rethinking Planar Homography Estimation Using Perspective Fields,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11366 LNCS, pp. 571–586, 2019, doi: 10.1007/978-3-030-20876-9_36.

W. Chojnacki, Z. L. Szpak, and M. Wadenbäck, “The equivalence of two definitions of compatible homography matrices,” Pattern Recognit. Lett., vol. 135, pp. 38–43, 2020, doi: 10.1016/j.patrec.2020.03.033.

T. Sung and H. J. Lee, “Images Alignment Using Homography Transformation Matrix,” no. July, 2021.

Y. Shankar, “Homography Estimation,” Towards Data Science, 2021.

A. Putra, V. Sihombing, and M. H. Munandar, “Rancang Bangun Aplikasi Deteksi Tepi Citra Digital,” Tekinkom, vol. 4, pp. 83–87, 2021, doi: 10.37600/tekinkom.v4i1.214.

S. Pare, A. Kumar, G. K. Singh, and V. Bajaj, “Image Segmentation Using Multilevel Thresholding: A Research Review,” Iran. J. Sci. Technol. - Trans. Electr. Eng., vol. 44, no. 1, 2020, doi: 10.1007/s40998-019-00251-1.

J. Dressel and H. Farid, “The accuracy, fairness, and limits of predicting recidivism,” Sci. Adv., vol. 4, no. 1, pp. 1–6, 2018, doi: 10.1126/sciadv.aao5580.

Y. Wang, M. Yu, G. Jiang, Z. Pan, and J. Lin, “Image registration algorithm based on convolutional neural network and local homography transformation,” Appl. Sci., vol. 10, no. 3, 2020, doi: 10.3390/app10030732.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Peningkatan Akurasi Pembacaan Lembar Jawaban Komputer dengan Memperbaiki Ketidaksimetrisan Citra Hasil Pemindaian Menggunakan Transformasi Homografi


  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

STMIK Budi Darma
Secretariat: Sisingamangaraja No. 338 Telp 061-7875998

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.