Computer vision‐based method for classification of wheat grains using artificial neural network

• Published in: Journal of the science of food and agriculture Vol. 97; no. 8; pp. 2588 - 2593
• Main Authors: Sabanci, Kadir, Kayabasi, Ahmet, Toktas, Abdurrahim
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 01.06.2017; John Wiley and Sons, Limited
• Subjects: Accuracy; Algorithms; artificial neural network (ANN); Artificial neural networks; Bread; breads; cameras; Classification; color; Computer vision; data collection; durum wheat; Food science; Grain; Image acquisition; Image classification; Image processing; Image Processing, Computer-Assisted - methods; Mathematical models; multilayer perceptron; Multilayer perceptrons; Neural networks; Neural Networks (Computer); Parameters; Seeds - chemistry; Seeds - classification; Triticum - chemistry; Triticum - classification; Wheat; wheat grains; image processing; multilayer perceptron; artificial neural network (ANN); wheat grains; classification
• ISSN: 0022-5142; 1097-0010; 1097-0010
• DOI: 10.1002/jsfa.8080

BACKGROUND A simplified computer vision‐based application using artificial neural network (ANN) depending on multilayer perceptron (MLP) for accurately classifying wheat grains into bread or durum is presented. The images of 100 bread and 100 durum wheat grains are taken via a high‐resolution camera and subjected to pre‐processing. The main visual features of four dimensions, three colors and five textures are acquired using image‐processing techniques (IPTs). A total of 21 visual features are reproduced from the 12 main features to diversify the input population for training and testing the ANN model. The data sets of visual features are considered as input parameters of the ANN model. The ANN with four different input data subsets is modelled to classify the wheat grains into bread or durum. The ANN model is trained with 180 grains and its accuracy tested with 20 grains from a total of 200 wheat grains. RESULTS Seven input parameters that are most effective on the classifying results are determined using the correlation‐based CfsSubsetEval algorithm to simplify the ANN model. The results of the ANN model are compared in terms of accuracy rate. The best result is achieved with a mean absolute error (MAE) of 9.8 × 10−6 by the simplified ANN model. CONCLUSION This shows that the proposed classifier based on computer vision can be successfully exploited to automatically classify a variety of grains. © 2016 Society of Chemical Industry