Hybrid Neural Network and Linear Model for Natural Produce Recognition Using Computer Vision

Joko Siswantoro (Departement of Informatics Engineering, Faculty of Engineering, Universitas Surabaya, Jalan Raya Kali Rungkut, Surabaya, 60293)
Anton Satria Prabuwono (Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh 21911,)
Azizi Abdullah (Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, 43600 UKM, Selangor D.E.)
Bahari Indrus (Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, 43600 UKM, Selangor D.E.)

Journal of ICT Research and Applications
Vol. 11 No. 2 (2017)

Natural produce recognition is a classification problem with various applications in the food industry. This paper proposes a natural produce recognition method using computer vision. The proposed method uses simple features consisting of statistical color features and the derivative of radius function. A hybrid neural network and linear model based on a Kalman filter (NN-LMKF) was employed as classifier. One thousand images from ten categories of natural produce were used to validate the proposed method by using 5-fold cross validation. The experimental result showed that the proposed method achieved classification accuracy of 98.40%. This means it performed better than the original neural network and k-nearest neighborhood.