Javanese Character Feature Extraction Based on Shape Energy
Journal Title: EMITTER International Journal of Engineering Technology - Year 2017, Vol 5, Issue 1
Abstract
Javanese characters is part of Javanese culture, which is one of Indonesia's noble culture. However, the number of Javanese people who are able to read the letters has decreased so that there needs some effort in the form of a system that is able to recognize the characters. One solution to this problem lies in Optical Character Recognition (OCR) studies, where one of its heaviest points lies in feature extraction (which is) to distinguish each character. Shape Energy is one of feature extraction methods with the basic idea of how the character can be distinguished simply through its skeleton. Based on the basic idea, then the development of feature extraction is done based on its components to produce an angular histogram with various variations of multiples angle. Furthermore, the performance test of this method and its basic method is conducted in Javanese character dataset, which has been obtained from various images, is 387 data with 19 labels by using K-Nearest Neighbors as its classification method. Performance values were obtained based on the accuracy which is generated through the Cross-Validation process of 81.90% in the angular histogram with an angle of 20 degrees, 27.32% better performance than using Shape Energy. In addition, other test results show that this method is able to recognize rotated character with the lowest performance value of 87.73% at 180-degree rotation and the highest performance value of 96.21% at 90-degree rotation. It can be concluded that this method is able to improve the performance of Shape Energy in the form of recognition of Javanese characters as well as robust to the rotation.
Authors and Affiliations
Galih Hendra Wibowo, Riyanto Sigit, Ali Ridho Barakbah
Keywords
Related Articles
- EP ID EP313634
- DOI 10.24003/emitter.v5i1.175
- Views 85
- Downloads 0
Comparison of The Data-Mining Methods in Predicting The Risk Level of Diabetes
Mellitus Diabetes is an illness that happened in consequence of the too high glucose level in blood because the body could not release or use insulin normally. The purpose of this research is to compare the two methods i...
Evacuation System in a Building Using Cellular Automata for Pedestrian Dynamics
The sense of safety in public facilities for pedestrians can be shown by the availability of good infrastructure, particularly the building. One of the aspects that can make pedestrians feel comfortable and safe is the a...
An Augmented Reality Application for the Community Learning about the Risk of Earthquake in a Multi-storey Building Area
Area surrounding tower is a danger area when earthquake attack. It has an enermous risk. People in this area have to know the risk for their safety. Socialization, simulation, and learning media need to be provided conti...
Combination Adaptive Traffic Algorithm and Coordinated Sleeping in Wireless Sensor Network
Wireless sensor network (WSN) uses a battery as its primary power source, so that WSN will be limited to battery power for long operations. The WSN should be able to save the energy consumption in order to operate in a l...
Semantic Madurese Batik Search with Cultural Computing of Symbolic Impression Extraction and Analytical Aggregation of Color, Shape and Area Features
Lack of information media about Madurese batik causes low awareness of younger generation to maintain the production of Madurese batik. Actually, Madurese Batik also has a high philosophy, which the motif and colour refl...