Computer-vision classification of corn seed varieties using deep convolutional neural network

• Published in: Journal of stored products research 2021-05, Vol.92, p.101800, Article 101800
• Main Authors: Javanmardi, Shima, Miraei Ashtiani, Seyed-Hassan, Verbeek, Fons J., Martynenko, Alex
• Format: Article
• Language: English
• Subjects: Deep learning; Feature extraction; Machine vision; Non-handcrafted features; Texture descriptors
• ISSN: 0022-474X; 1879-1212
• DOI: 10.1016/j.jspr.2021.101800

Automated classification of seed varieties is of paramount importance for seed producers to maintain the purity of a variety and crop yield. Traditional approaches based on computer vision and simple feature extraction could not guarantee high accuracy classification. This paper presents a new approach using a deep convolutional neural network (CNN) as a generic feature extractor. The extracted features were classified with artificial neural network (ANN), cubic support vector machine (SVM), quadratic SVM, weighted k-nearest-neighbor (kNN), boosted tree, bagged tree, and linear discriminant analysis (LDA). Models trained with CNN-extracted features demonstrated better classification accuracy of corn seed varieties than models based on only simple features. The CNN-ANN classifier showed the best performance, classifying 2250 test instances in 26.8 s with classification accuracy 98.1%, precision 98.2%, recall 98.1%, and F1-score 98.1%. This study demonstrates that the CNN-ANN classifier is an efficient tool for the intelligent classification of different corn seed varieties. •The performance of different algorithms for corn seeds classification was evaluated.•The accuracy of classification models increased by combining CNN with handcrafted features.•CNN-ANN classification algorithm performed better than other models.