Pengenalan Pola Huruf pada Kata dengan Menggunakan Algoritma Backpropagation dan Hybrid Feature
AbstractWith the advancement of information technology today, especially in the process of writing words and sentences where a person will be easier in the process of writing using hands and neat but the writing process carried out at this time also cannot be abandoned. Some activities require us to use handwriting manually such as making statement letters or other important documents. In the implementation that will be carried out on the system of letter pattern recognition in words using handwriting will produce a lower level of accuracy compared to the introduction made on systems that is in computers such as Times New Roman, Calibri, and so on. By using Hybrid Features extraction and backpropagation algorithm, it is expected to reduce problems in the process of recognizing one's handwriting pattern. To get a feature pattern, Hybrid Features extraction used from diagonal features, x and y axis gradients and averages are used. The feature will be used is artificial neural networks with the backpropagation algorithm. The test parameters used are the accuracy of the number of written images recognized by the system. Based on models' performance tests, the highest accuracy was 93.86% for uppercase letters with 45 datasets, 80.46% with 30 datasets for lowercase letters and 78.205 with 45 datasets for all letters. The testing of the program made obtained an accuracy value of 72.92% for the image of the new word, 83.33% for the image of the new letter and 82.56% for the image of the letter that had been studied.
 D. Putra, Pengolahan Citra Digital. Yogyakarta: Andi Offset, 2010.
 G. Katiyar and S. Mehfuz, “MLPNN Based Handwritten Character Recognition Using Combined Feature Extraction,” in International Conference on Computing, Communication & Automation, 2015, pp. 1155–1159.
 U. Dwivedi, P. Rajput, and M. K. Sharma, “Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network,” Int. Res. J. Eng. Technol., vol. 04, no. 03, pp. 2202–2206, 2017.
 A. P. Wijaya and H. A. Santoso, “Naive Bayes Classification pada Klasifikasi Dokumen Untuk Identifikasi Konten E-Government,” J. Appl. Intell. Syst., vol. 1, no. 1, pp. 48–55, 2016.
 S. Winardi and H. Hamzah, “PENERAPAN METODE JARINGAN SYARAF TIRUAN BACKPROPAGATION DALAM PENGENALAN POLA AKSARA HANACARAKA,” J. Teknol. Inf. Respati, vol. 9, no. 27, pp. 33–42, 2017.
 S. Solikhun, M. Safii, and A. Trisno, “aringan Saraf Tiruan Untuk Memprediksi Tingkat Pemahaman Sisiwa Terhadap Matapelajaran Dengan Menggunakan Algoritma Backpropagation,” J-SAKTI (Jurnal Sains Komput. dan Inform., vol. 1, no. 1, pp. 24–36, 2017.
 Y. Permadi and M. Murinto, “Aplikasi Pengolahan Citra Untuk Identifikasi Kematangan Mentimun Berdasarkan Tekstur Kulit Buah Menggunakan Metode Ekstraksi Ciri Statistik,” J. Inform. Ahmad Dahlan, vol. 9, no. 1, pp. 1028–1038, 2015.
 R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Second Edition). 2004.
 I. M. G. Sunarya, M. W. A. Kesiman, and I. A. P. Purnami, “Segmentasi Citra Tulisan Tangan Aksara Bali Berbasis Proyeksi Vertikal Dan Horizontal,” J. Inform., vol. 9, no. 1, pp. 982–992, 2015.
 D. Putra, Sistem Biometrika. Yogyakarta: Andi Offset, 2009.
 S. Mori, “Deep architecture neural network-based real-time image processing for imageguided radiotherapy,” Phys. Medica, 2017.
 Y. Chauvin and D. E. Rumelhart, Backpropagation: Theory, Architectures, and Applications. New York: Psychology Press, 2013.
 E. Pandie, “Implementasi Algoritma Data mining KNearest Neighbour (KNN) Dalam Pengambilan Keputusan Pengajuan Kredit,” Universitas Nusa Cendana, Kupang, 2012.
 S. F. Rodiyansyah and E. Winarko, “Klasifikasi Posting Twitter Kemacetan Lalu Lintas Kota Bandung Menggunakan Naive Bayesian Classification,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 6, no. 1, pp. 91–100, 2012.