Implementasi Keras Library dan Convolutional Neural Network Pada Konversi Formulir Pendaftaran Siswa

  • Wahyu Andi Saputra - Institut Teknologi Telkom Purwokerto
  • Muhammad Zidny Naf’an Institut Teknologi Telkom Purwokerto
  • Asyhar Nurrochman Institut Teknologi Telkom Purwokerto
Keywords: optical character recognition, form-sheet conversion, keras library, convolutional neural network

Abstract

Form sheet is an instrument to collect someone’s information and in most cases it is used in a registration or submission process. The challenge being faced by physical form sheet (e.g. paper) is how to convert its content into digital form. As a part of study of computer vision, Optical Character Recognition (OCR) recently utilized to identify hand-written character by learning pattern characteristics of an object. In this research, OCR is implemented to facilitate the conversion of paper-based form sheet's content to be stored properly into digital storage. In order to recognize the character's pattern, this research develops training and testing method in a Convolutional Neural Network (CNN) environment. There are 262.924 images of hand-written character sample and 29 paper-based form sheets from SDN 01 Gumilir Cilacap that implemented in this research. The form sheets also contain various sample of human-based hand-written character. From the early experiment, this research results 92% of accuracy and 23% of loss. However, as the model is implemented to the real form sheets, it obtains average accuracy value of 63%. It is caused by several factors that related to character's morphological feature. From the conducted research, it is expected that conversion of hand-written form sheets become effortless.

Downloads

Download data is not yet available.

References

Tim Pusat Bahasa Departemen Pendidikan Nasional, Kamus Bahasa Indonesia, Edisi XVI. Jakarta: Pusat Bahasa, 2008.

Direktorat Jenderal Pendidikan Dasar dan Menengah, 2018. Jumlah Data Satuan Pendidikan (Sekolah) per Kabupaten/Kota: Kabupaten Cilacap. [Daring]. Tersedia di: http://referensi.data.kemdikbud.go.id/index21_t kra.php?kode=026600&level=2.

B. Warsita, 2015. Evaluasi Sistem Penerimaan Peserta Didik Baru (PPDB) Online untuk Peningkatan Kualitas Pembelajaran. Jurnal Kwangsan. 3 (1). hal. 27.

S. Maulina, Respon Orang Tua Peserta Didik SMP atas Layanan Inormasi Penerimaan Peserta Didik Baru (PPDB) Melalui Media Online oleh Dinas Pendidikan Kota Malang, 2013.

J. Sutresna, 2017. Perancangan Sistem Formulir Pelayanan Kedukaan Online Menggunakan Metode Web Base Engineering Pada Pt . Abadi Cahaya Universal ( Rumah Duka Abadi ) Jakarta. Jurnal Informatika Universitas Pamulang. 2 (2). hal. 108–113.

S. Hartanto, A. Sugiharto, dan S. N. Endah, 2015. Optical Character Recognition Menggunakan Algoritma Template Matching Correlation. Jurnal Masyarakat Informatika. 5 (9). hal. 1–12.

R. F. Falah, O. D. Nurhayati, dan K. T. Martono, 2016. Aplikasi Pendeteksi Kualitas Daging Menggunakan Segmentasi Region of Interest Berbasis Mobile. Jurnal Teknologi dan Sistem Komputer. 4 (2). hal. 333–343.

B. Al-Mahadeen, M. S. Altarawneh, dan I. H. Altarawneh, 2010. Signature Region of Interest using Auto cropping. IJCSI International Journal of Computer Science Issues. 7 (2). hal. 1–5.

H. A. Nugroho, W. A. Saputra, A. E. Permanasari, dan E. E. H. Murhandarwati, 2017. Automated determination of plasmodium region of interest on thin blood smear images. 2017 International Seminar on Intelligent Technology and Its Application: Strengthening the Link Between University Research and Industry to Support ASEAN Energy Sector, ISITIA 2017 - Proceeding. 2017-Janua . hal. 352–355.

M. Zufar dan B. Setiyono, 2016. Convolutional Neural Networks untuk Pengenalan Wajah Secara Real-Time. Jurnal Sains dan Seni. 5 (3). hal. 1–6.

Sukardi, Z. Arifin, dan M. Risaldi, Klasifikasi Penentuan Gambar Berbasis Tensorform Dan Framework Dengan Algoritma CNN, in Seminar Nasional APTIKOM (SEMNASTIKOM), 2017, hal. 1–4.

Y. Pramudana, 2015. Pengenalan Tulisan Tangan Dengan Menggunakan Metode Diagonal Feature Extraction dan K-Nearest Neighbour. Bandung.

J. Pujoseno, Implementasi Deep Learning Menggunakan Convolutional Neural Network Untuk Klasifikasi Alat Tulis, Universitas Islam Indonesia, Yogyakarta, 2018.

https://www.kaggle.com/tejasreddy/iam-handwriting-top50.

S. A. J. Zaidi, A. Buriro, M. Riaz, A. Mahboob, dan M. N. Riaz, 2019. Implementation and comparison of text-based image retrieval schemes. International Journal of Advanced Computer Science and Applications. 10 (1). hal. 611–618.

M. Jackson, J. P. Simmons, dan M. De Graef, 2010. MXA: A customizable HDF5-based data format for multi-dimensional data sets. Modelling and Simulation in Materials Science and Engineering. 18 (6).

R. Bhowmik, J. Hartog, dan M. Govindaraju, 2013. Processing HDF5 datasets on multi-core architectures. Proceedings - International Conference on Advanced Information Networking and Applications, AINA. hal. 666–673.

R. Wiles, 2019. Have we solved the problem of handwriting recognition? [Daring]. Tersedia di: https://towardsdatascience.com/https-medium-com-rachelwiles-have-we-solved-the-problem-of-handwriting-recognition-712e279f373b. [Diakses: 02-Okt-2019].

Published
2019-12-14
How to Cite
-, W. A. S., Muhammad Zidny Naf’an, & Asyhar Nurrochman. (2019). Implementasi Keras Library dan Convolutional Neural Network Pada Konversi Formulir Pendaftaran Siswa. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 3(3), 524 - 531. https://doi.org/10.29207/resti.v3i3.1338
Section
Artikel Teknologi Informasi

Most read articles by the same author(s)