A classification method of coconut wood quality based on Gray Level Co-occurrence matrices

• Published in: 2013 International Conference on Robotics, Biomimetics, Intelligent Computational Systems pp. 254 - 257
• Main Authors: Pramunendar, Ricardus Anggi, Supriyanto, Catur, Dwi Hermawan Novianto, Ignatius Ngesti Yuwono, Shidik, Guruh Fajar, Andono, Pulung Nurtantio
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2013
• Subjects: artificial neural network; coconut wood classification; gray level co-occurrence matrix; support vector machine; Support vector machines; texture features
• DOI: 10.1109/ROBIONETICS.2013.6743614

Coconut tree grows rapidly in tropical region such as Indonesia. Coconut wood is used as alternative or complementary raw material for housing or making furniture. Abundant coconut trees are planted, however the utilization of coconut wood as raw material for furniture is still very rare in Indonesia. This is caused by the low quality of coconut wood, since it has not found adequate technology for the processing of coconut wood. This paper presents our experimental work on coconut wood quality classification using self-tuning MLP classifier (AutoMLP) and Support Vector Machine (SVM). For SVM classifier we used the LibSVM library, available in RapidMiner. The Gray-Level Co-occurrence Matrix (GLCM) is used to extract the texture features of coconut wood images. Experiment result shows that AutoMLP gives the best accuracy rate at 78.82%, which is slightly better than 77.06% of SVM.