Rekognisi Huruf Tulisan Tangan Menggunakan Convolutional Neural Network
Abstract
The development of technology in the field of computer vision in recent years with the application of Technological developments in the field of computer vision in recent years with the application of convolutional neural networks have shown sophisticated performance with a high level of accuracy, such as object detection. The problem in the world of computer vision that has been looking for a solution for a long time is object classification in general images. How to duplicate the human ability to understand images, so that computers can recognize objects in images like humans. Therefore, the need for deep learning is one branch of machine learning where the algorithm used is inspired by the workings of the human brain. Some people may be more familiar with Convolution Neural Network. CNN is used to recognize and classify patterns in handwriting. The network assumes that the input used is an image. The network has a special layer called the convolution layer. In this layer, the images are inserted according to the predefined filters. In this study, various combinations of CNN architectural designs were carried out such as the number of convolution layers, stride size, number of epochs, type of kernel size optimizer. The research data comes from the National Institute of Standards and Technology (NIST) database, then the data is divided into three, namely 60% training data, 20% validation and 20% testing. The results of this experiment produce a very good accuracy value using 2 convolution layers, 50 epochs, with Adam optimizer producing an accuracy value of 99.5% when testing the model. Then evaluate the model using the confusion matrix, assigning a high value with an average value of 100% accuracy, while for the average value of precision with a value of 100%, for an average recall value of 100%, and finally an average value of f1 score of 100%.
Downloads
References
Feng, R., Gu, J., Qiao, Y & Dong, C., ”Suppressing Model Overfitting for Image Super-Resolution Network,” Computer Vision Foundation, June 2019, doi: https://arxiv.org/abs/1906.04809.
I Wayan Suartika E. P, Arya Yudhi Wijaya, and Rully Soelaiman, “Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) pada Caltech 101,” Jurnal Teknik ITS, Vol 5, No 1 (2016), doi: https://garuda.kemdikbud.go.id/documents/detail/1440423.
Y. hen, Z. Lin, X. Zhao, G. Wang, and Y. Gu, “A Novel Deep Convolutional Neural Network For Spectral–Spatial Classification Of Hyperspectral Data,” Journal of Selected Topics in Developments, Technologies and Applications in Remote Sensing, vol. 7, no. 6, 2018. Doi: 10.5194/isprs-archives-XLII-3-897-2018.
Siwi Prihatiningsih, Nadhiranisa Shafiy M, Feni Andriani, and Nurma Nugraha, “Analisa Performa Pengenalan Tulisan Tangan Angka Berdasarkan Jumlah Iterasi Menggunakan Metode Convolutional Neural Network,” Jurnal Ilmiah Teknologi dan Rekayasa, Vol. 24 No. 1, April 2019, doi: https://garuda.kemdikbud.go.id/documents/detail/1364267.
K. Fukushima, "Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position," Biological Cybernetics, 36, 193 202 (1980), doi: https://link.springer.com/article/10.1007/BF00344251.
A.Karpathy, ''CS231n Convolutional Neural Network for Visual Recognition, ''Stanford University, 2020, doi : http://cs231n.stanford.edu/2020/
Jiawei Han, and Micheline Kamber Jian Pei, “Data Mining: Concepts and Techniques. 3rd penyunt,” Morgan Kaufmann is an imprint of Elsevier, MA 02451, 2012, doi: http://myweb.sabanciuniv.edu/rdehkharghani/files/2016/02/The-Morgan-Kaufmann-Series-in-Data-Management-Systems-Jiawei-Han-Micheline-Kamber-Jian-Pei-Data-Mining.-Concepts-and-Techniques-3rd-Edition-Morgan-Kaufmann-2011.pdf.
Sam’ani, and M. Haris Qamaruzzaman, “Pengenalan Huruf Dan Angka Tulisan Tangan Mengunakan Metode Convolution Neural Network (CNN),” Journal Speed – Sentra Penelitian Engineering dan Edukasi, Volume 9, No 2 (2017), doi: http://speed.web.id/ejournal/index.php/speed/article/view/296.
I Khandokar, Md M Hasan, F Ernawan, Md S Islam, M N Kabir, “Handwritten character recognition using convolutional neural network”, Journal of Physics: Conference Series, Vol. 1918, 2021. Doi: https://iopscience.iop.org/article/10.1088/1742- 6596/1918/4/042152.
NIST Special Database 19 “NIST Handprinted Forms and Characters Database” STANDARD REFERENCE DATA. Doi: https://www.nist.gov/srd/nist-special-database-19.
Damir Krstinić, Maja Braović, Ljiljana Šerić and Dunja Božić-Štulić, “Multi-Label Classifier Performance Evaluation With Confusion Matrix” Artificial Intelligence and Machine Learning, (2020). Doi: 10.5121/csit.2020.100801.
Najwa Altwaijry dan Isra Al-Turaiki, “Arabic handwriting recognition system using convolutional neural network,” Neural Computing and Applications. (2021). Doi: https://doi.org/10.1007/s00521-020-05070- 8.
XenonStack, “Log Analytics With Deep Learning And Machine Learning”. Medium, 13 Mei 2017. Doi: https://medium.com/@xenonstack/loganalytics-with-deep-learning-and-machine-learning-20a1891ff70e.
Hidayatullah, Priyanto, “Pengolahan Citra Digital Teori dan Aplikasinya,” Penerbit Informtika Bandung. (2017). Doi: https://opac.perpusnas.go.id/DetailOpac.aspx?id=1059250.
Mayur Bhargab Bora, Dinthisrang Daimary, Khwairakpam Amitab, Debdatta Kandar, “Handwritten Character Recognition from Images using CNN-ECOC”, Procedia Computer Science, Vol. 167, 2020, Pages 2403-2409. Doi: https://doi.org/10.1016/j.procs.2020.03.293.
