Neural Network-based Classification of Germinated Hang Rice Using Image Processing

ABSTRACT

Germinated Hang rice is produced using traditional folklore wisdom. It has drawn a lot of attention by researchers due to its high nutritional value to the human body. Conventionally, the quality of germinated Hang rice grains has been assessed manually into good/bad. However, this method is very time consuming and relies primarily on human skills and experience. Thus, the purpose of this research was to develop an algorithm capable of automatically determining the quality of germinated Hang rice by dividing it into six groups comprised of good, broken, discoloured, un-husked paddy, deformed and withered grains. The algorithm is based on image processing techniques and extracts the shape, colour and texture features, after which they are fed into a neural network classifier with PCA feature selection. The experimental results showed that the overall classification accuracy achieved was 94.0%.

KEYWORDS:

• Geminated Hang rice
• Grey level co-occurrence matrix
• Image processing
• Local adaptive thresholding
• Neural networks
• Principal component analysis

ACKNOWLEDGEMENTS

The authors would like to thank the Coordinating Centre for Thai Government Science and Technology Scholarship Students (CSTS).

Additional information

Funding

This research was supported by the National Science and Technology Development Agency (NSTDA) of Thailand [grant number MOST SCH-NR2014-533].

Notes on contributors

Jumpol Itsarawisut

Jumpol Itsarawisut was born in Khon Kaen, Thailand. He received his BEng in electronic engg and telecommunication from Prince of Rajamangala University, Thailand in 1998. He received his MSc in electrical engineering from University of Khon Kaen, Thailand in 2011. Currently, he is studying for a PhD degree in the field of electrical and computer engineering at the Faculty of Engineering, Mahasarakham University, Thailand. E-mail: [email protected].

Kiattisin Kanjanawanishkul

Kiattisin Kanjanawanishkul was born in Trang, Thailand. He received his BEng in electrical engineering from Prince of Songkla University, Thailand in 2000. He received his MSc in Mechatronics from University of Siegen, Germany in 2006. He received his PhD in Computer Science from University of Tuebingen, Germany in 2010. Since 2010, he has been employed at the Faculty of Engineering, University of Mahasarakham, Thailand. His current research interests include cooperative and distributed control, model predictive control, intelligent control, multi-robot systems and robotic motion control.