Handwritten Javanese Character Recognition Using Several Artificial Neural Network Methods

Abstract

Abstract. Javanese characters are traditional characters that are used to write the Javanese language. The Javanese language is a language used by many people on the island of Java, Indonesia. The use of Javanese characters is diminishing more and more because of the difficulty of studying the Javanese characters themselves. The Javanese character set consists of basic characters, numbers, complementary characters, and so on. In this research we have developed a system to recognize Javanese characters. Input for the system is a digital image containing several handwritten Javanese characters. Preprocessing and segmentation are performed on the input image to get each character. For each character, feature extraction is done using the ICZ-ZCZ method. The output from feature extraction will become input for an artificial neural network. We used several artificial neural networks, namely a bidirectional associative memory network, a counterpropagation network, an evolutionary network, a backpropagation network, and a backpropagation network combined with chi2. From the experimental results it can be seen that the combination of chi2 and backpropagation achieved better recognition accuracy than the other methods.

Implementation of Javanese Text to Speech using MaryTTS Engine

“…After doing all the above steps, MaryTTS engine is ready for use by word processor application. This word processor application is the extended version from word processor application that has been developed in previous research [2]. In the last research, it used its own hanacaraka font, while currently the application used Google Noto Sans Javanese font.…”

“…This difference creates difficulty for people to read or write Javanese language literature or script. Several researches related to Java character have been done such as Java character recognition which is try to convert from Java character to Roman character [1,2,3,4] with aim to facilitate the learning of Java character easily especially for younger generation.…”

Pengenalan Pola Tulisan Tangan Aksara Sasak Menggunakan Metode Linear Discriminant Analysis dan Jaringan Syaraf Tiruan Jenis Backpropagation

“…Dataset dari penelitian tersebut berjumlah 620 data dengan output sebanyak 20 neuron. Metode JST-BP merupakan metode dengan akurasi tertinggi pada penelitian ini [16]. Penelitian terkait dengan metode JST-BP juga ada pada penelitian klasifikasi pola huruf vokal dengan jumlah kelas sebanyak 5 kelas dan jumlah dataset yang digunakan yaitu berjumlah 450 citra.…”

Convolutional Neural Networks for Handwritten Javanese Character Recognition

“…Similarly, Arum [6] used the combination of wavelet feature extraction technique and also backpropagation neural networks. Budhi and Adipranata [7] employed several artificial neural network methods with ICZ-ZCZ features for handwritten Javanese character recognition. Several other studies [8,9,10,11] show that neural networks are able to perform image classification task with good performance if they are combined with appropriate feature extraction techniques.…”