The problem of multi-label classification by machine learning algorithms such as support vector machine (SVM) and convolutional neural network (CNN) is that a data sample can be classified into a multi-label class cannot be categorized into any class. Automated multi-label classification and recognition of fruit images play a crucial role in decision-making scheme in agro-based applications. In this paper, we proposed a fruit recognition and classification scheme based on deep convolutional neural network (CNN). The CNN is applied to the tasks of fruit detection and recognition through parameter optimization. To validate the proposed scheme, four normal fruits are considered, i.e., apple, lemon, tomato, and plum in testing. In this experiment, we demonstrate that the accuracy is improved by the CNNs over the conventional SVM and other classification methods. The result of the proposed method has good accuracy in the classification and it is close to 98% for the four classes of 1200 fruit images, indicating that the proposed method could be used in agro-based applications.
CITATION STYLE
Biswas, B., Ghosh, S. K., & Ghosh, A. (2020). A Robust Multi-label Fruit Classification Based on Deep Convolution Neural Network. In Advances in Intelligent Systems and Computing (Vol. 999, pp. 105–115). Springer. https://doi.org/10.1007/978-981-13-9042-5_10
Mendeley helps you to discover research relevant for your work.