Classification of Green coffee bean images basec on defect types using convolutional neural network (CNN)

In Timor-Leste, the coffee is one of the most important product for the acquisition of foreign currency. However, there are almost no rationalizations, therefore, enhancing the value of the coffee efficiently at the local of production is desired. The final objective of our study is to develop the automatic coffee beans sorting system for the producers of coffee beans in Timor-Leste. As the first step, we developed an image processing system which classifies the images of green coffee beans into each type of defect. We employed deep convolutional neural networks, the state-of-the-art machine learning technique, for the image processing. As the results, we succeeded to sort defect beans from 72.4% to 98.7% of accuracies based on the types of defects.

[1]  José Blasco,et al.  Computer vision for automatic quality inspection of dried figs (Ficus carica L.) in real-time , 2016, Comput. Electron. Agric..

[2]  Faridah Faridah,et al.  Coffee Bean Grade Determination Based on Image Parameter , 2011 .

[3]  Mostafa Mehdipour-Ghazi,et al.  Plant identification using deep neural networks via optimization of transfer learning parameters , 2017, Neurocomputing.

[4]  Christian E. Portugal-Zambrano,et al.  Automatic classification of physical defects in green coffee beans using CGLCM and SVM , 2014, 2014 XL Latin American Computing Conference (CLEI).

[5]  Adriana S. Franca,et al.  Composition of green and roasted coffees of different cup qualities , 2005 .

[6]  Betelihem Mesfin Ayitenfsu.  Method of Coffee Bean Defect Detection , 2014 .

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Paulo Mazzafera,et al.  Chemical composition of defective coffee beans , 1999 .

[9]  Leandro S. Oliveira,et al.  Physical and chemical attributes of defective crude and roasted coffee beans , 2005 .

[10]  Bruno Cabral,et al.  Prototyping a GPGPU Neural Network for Deep-Learning Big Data Analysis , 2017, Big Data Res..

[11]  Bruno H.G. Barbosa,et al.  A computer vision system for coffee beans classification based on computational intelligence techniques , 2016 .

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Pablo M. Granitto,et al.  Deep learning for plant identification using vein morphological patterns , 2016, Comput. Electron. Agric..

[14]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[15]  Flávio Meira Borém,et al.  Evaluation of the sensory and color quality of coffee beans stored in hermetic packaging , 2013 .

[16]  Marçal Avelino Ximenes.  A tecnologia pós-colheita e qualidade física e organoléptica do café arábica de Timor , 2010 .

[17]  Jee-Hyun Cho,et al.  Assessment of green coffee bean metabolites dependent on coffee quality using a 1H NMR-based metabolomics approach , 2015 .