Automatic fruit classification using support vector machines: a comparison with artificial neural network

2nd International Conference on Eco Engineering Development 2018

生态环境科学

Astuti, Winda^1 ; Dewanto, Satrio^1 ; Soebandrija, Khristian Edi Nugroho^2 ; Tan, Sofyan^1

Computer Engineering Department, Faculty of Engineering, Bina Nusantara University, Jakarta

11480, Indonesia^1

Indutrial Engineering Department, Faculty of Engineering, Bina Nusantara University, Jakarta

11480, Indonesia^2

关键词: Classification system;    Food industries;    Food processing industry;    Food processing technology;    Indonesia;    Support vector machine (SVMs);    Training time;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/195/1/012047/pdf
DOI  :  10.1088/1755-1315/195/1/012047

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Food processing Technologies play important roles in supporting Making Indonesia (MI) 4.0. The effectiveness in food processing becomes emerging in the food industry. The automatic fruit classification system is becoming important for use in many food processing industries. A novel approach for classifying, using support vector machines (SVM) is presented in this paper. Fruit classification based on their shape is proposed in this work. The system differentiates the fruit based on their shape. Fast Fourier Transform (FFT) is extracted and later used as input to the SVM-based identifier. The fruit parameters are compared and classified, the results of computer simulation show that this technique produces better accuracy than that of the existing technique that is based on artificial neural network (Ann). The SVM also requires less training time than artificial neural network (Ann).