Pattern Recognition Of Javanese Letter Using Template Matching Correlation Method

Abstract

In this modern age, the impact of globalization is increasingly entering and expanding into most societies. One impact of globalization makes people prefer to learn the language and use a foreign language rather than the local language, especially the Java language. It is very influential on the knowledge of the community about the existence or the existence of Javanese Letter, especially in the field of education. In this study, In this research will be made an application to recognize the writing of Javanese Letter based on Optical Character Recognition (OCR). Matching templates correlation can be used as pattern recognition methods. How the Template Matching Algorithm works by matching the template image with the test image after going through the Pre-processing and segmentation process. From the research that has been done by using 10 character template and 20 data testing get accuracy equal to 93.44% and error rate 6.56%. So the Matching Template Algorithm can well recognize the Javanese Letter pattern.

Pengaruh Linear Binary Pattern (Lbp) Dalam Pengenalan Citra Aksara Jawa Berbasis Optical Character Recognition (Ocr)

“…Sebagai generasi muda, melestarikan budaya tulisan Aksara Jawa khususnya di Pulau Jawa sangatlah penting agar tetap dikenal sampai ke generasi berikutnya. Menurut [6], [7] dalam penelitiannya yang membahas permasalahan membagi tulisan aksara yang terdapat pada naskah menjadi bagian-bagian karakter aksara yang dapat digunakan dalam pengenalan Aksara Jawa. Rismiyati, Djalal [8] yang membahas permasalahan meningkatkan akurasi dalam pengenalan karakter Jawa menggunakan fitur HOG dan fitur Zone Base.…”

“…Rismiyati, Djalal [8] yang membahas permasalahan meningkatkan akurasi dalam pengenalan karakter Jawa menggunakan fitur HOG dan fitur Zone Base. Irham, Fairuz [7] dalam Jurnal Pattern Recognition of Javanese Letter Using Template Matching Correlation Method, membahas implementasi algoritma template matching untuk melakukan pengenalan pola serta mengenal dan transliterasi huruf jawa dengan menggunakan metode Template Matching Correlation berbasis Optical Character Recognition dan membangun aplikasi. Aksara Jawa memiliki bentuk yang sulit serta memiliki unsur-unsur yang rumit yang terdapat pada Aksara Jawa.…”

“…Metode ini akan digunakan untuk memisahkan objek citra Aksara Jawa pada backgroundnya. Optical Character Recognition (OCR) [7], [13] merupakan suatu penggunaan teknologi yang dapat membantu dalam memindai gambar karakter teks baik yang dicetak atau tulisan tangan. Dengan memanfaatkan OCR akan dapat membantu dalam proses pengkonversian gambar yang berisi tulisan Aksara Jawa yang nantinya akan dilakukan proses transliterasi.…”

Convolutional Neural Network Method for Classification of Syllables in Javanese Script

“…The equation of the SoftMax layer is presented in equation ( 6) [8]. (6) Each architecture in the CNN model that is built has a difference in the number of convolution layers used [7]. The number of convolution layers used in this research is three layers with two filters measuring 5x5 and one filter measuring 3x3.…”

“…Based on this research, the combination of the Backpropagation method with Chi2 provides the best accuracy reaching 98% for data that has been trained and 73% for data that has not been trained [3]. Another approach to the introduction of Javanese characters is to use machine learning [4]- [6] and deep learning [7]- [10]. Deep learning is used CNN by applying a certain model variation and Deep Neural Network (DNN).…”