IMAGE BACKGROUND PROCESSING FOR COMPARING ACCURACY VALUES OF OCR PERFORMANCE

Pengolahan Latar Belakang Citra Untuk Membandingkan Nilai Akurasi Terhadap Kinerja OCR

  • Desiana Nur Kholifah (1) STMIK Nusa Mandiri Jakarta, Indonesia
  • Hendri Mahmud Nawawi (2*) STMIK Nusa Mandiri
  • Indra Jiwana Thira (3) STMIK Nusa Mandiri Jakarta, Indonesia

  • (*) Corresponding Author
Keywords: OCR, Dokumen, Dokumen Gambar, Eliminasi

Abstract

Optical Character Recognition (OCR) is an application used to process digital text images into text. Many documents that have a background in the form of images in the visual context of the background image increase the security of documents that state authenticity, but the background image causes difficulties with OCR performance because it makes it difficult for OCR to recognize characters overwritten by background images. By removing background images can maximize OCR performance compared to document images that are still background. Using the thresholding method to eliminate background images and look for recall values, precision, and character recognition rates to determine the performance value of OCR that is used as the object of research. From eliminating the background image with thresholding, an increase in performance on the three types of OCR is used as the object of research.

Downloads

Download data is not yet available.

References

Ahmad, N., & Hadinegoro, A. (2012). Metode Histogram Equalization untuk Perbaikan Citra Digital. Seminar Nasional Teknologi Informasi & Komunikasi Terapan (SEMANTIK), 2012(Semantik), 439–445.

Alginahi, Y. M., & Munawarah, M. (2008). Digital Image Computing : Techniques and Applications THESHOLDING AND CHARACTER RECOGNITION IN SECURITY DOCUMENTS WITH WATREMARKED BACKGROUND. https://doi.org/10.1109/DICTA.2008.90

Bahtiar, A. (2016). Sistem Deteksi Nomor Polisi Mobil dengan Menggunakan Metode Haar Classifier dan OCR guna Mempermudah Administrasi Pembayaran Parkir. Journal of Information and Technology, Volume 04(9), 40–46. https://doi.org/10.1017/CBO9781107415324.004

Budianita, E., Jasril, & Handayani, L. (2015). Implementasi Pengolahan Citra dan Klasifikasi K-Nearest Neighbour Untuk Membangun Aplikasi Pembeda Daging Sapi dan Babi. Jurnal Sains, Teknologi Dan Industri, 12(2), 242–247.

Gusa, R. F. (2013). Pengolahan Citra Digital Untuk Menghitung Luas Daerah Bekas Penambangan Timah. Jurnal Nasional Teknik Elektro (JNTE), 2(2), 27–34. https://doi.org/https://doi.org/10.25077/jnte.v2n2.71.2013

Hasugian, A. H., & Zufira, I. (2018). Perancangan Sistem Restorasi Citra Dengan Metode Image Inpainting. Jurnal Ilmu Komputer Dan Informatika, 03(November), 31–45.

Kholifah, D. N., Nawawi, H. M., & Thira, I. J. (2020). Laporan Akhir Penelitian Mandiri: Pengolahan Latar Belakang Citra Untuk Membandingkan Nilai Akurasi Terhadap Kinerja OCR. Jakarta.

Kumaseh, M. R., Latumakulita, L., & Nainggolan, N. (2013). Segmentasi Citra Digital Ikan Menggunakan Metode Thresholding. Jurnal Ilmiah Sains, 13(1), 74. https://doi.org/10.35799/jis.13.1.2013.2057

Priyawati, D. (2013). Teknik Pengolahan Citra Digital Berdomain Spasial Untuk Peningkatan Citra Sinar-X. Jurnal KomuniTi, II(2), 44–50.

Santi, C. N. (2011). Mengubah Citra Berwarna Menjadi Gray­Scale dan Citra biner. Teknologi Informasi DINAMIK, 16(1), 14–19.

Shen, M., & Lei, H. (2015). Improving OCR performance with background image elimination. 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015, 1566–1570. https://doi.org/10.1109/FSKD.2015.7382178

Susanto, A. (2019). Penerapan Operasi Morfologi Matematika Citra Digital Untuk Ekstraksi Area Plat Nomor Kendaraan Bermotor. Pseudocode, 6(1), 49–57. https://doi.org/10.33369/pseudocode.6.1.49-57

Yogi, M. (2016). Aplikasi Deteksi Kematangan Buah Semangka Berbasis Nilai RGB Menggunakan Metode Thresholding. Jurnal Riset Komputer (JURIKOM), 3(6), 84–89.

Published
2020-03-15
How to Cite
Kholifah, D., Nawawi, H., & Thira, I. (2020). IMAGE BACKGROUND PROCESSING FOR COMPARING ACCURACY VALUES OF OCR PERFORMANCE. Jurnal Pilar Nusa Mandiri, 16(1), 33-38. https://doi.org/10.33480/pilar.v16i1.1076
Article Metrics

Abstract viewed = 60 times
PDF downloaded = 38 times