Recycling waste classification using optimized convolutional neural network

• Published in: Resources, conservation and recycling Vol. 164; p. 105132
• Main Authors: Mao, Wei-Lung, Chen, Wei-Chun, Wang, Chien-Tsung, Lin, Yu-Hao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2021
• Subjects: Convolutional neural network (CNN); DenseNet; Genetic algorithm (GA); Image recognition; Recycling; Waste classification; DenseNet; Waste classification; Genetic algorithm (GA); Image recognition; Convolutional neural network (CNN); Recycling
• ISSN: 0921-3449; 1879-0658
• DOI: 10.1016/j.resconrec.2020.105132

•Automatic classification based on image recognition to reduce recycling labors.•Convolutional neural network (CNN) were transferred to identify the waste images.•Data augmentation improves the CNNs’ performance.•The optimized fully connected layer of CNNs enhances the CNNs’ performance.•Coarse features of the waste image by Grad-CAM validates the optimized CNN. An automatic classification robot based on effective image recognition could help reduce huge labors of recycling tasks. Convolutional neural network (CNN) model, such as DenseNet121, improved the traditional image recognition technology and was the currently dominant approach to image recognition. A famous benchmark dataset, i.e., TrashNet, comprised of a total of 2527 images with six different waste categories was used to evaluate the CNNs’ performance. To enhance the accuracy of waste classification driven by CNNs, the data augmentation method could be adopted to do so, but fine-tuning optimally hyper-parameters of CNN's fully-connected-layer was never used. Therefore, besides data augmentation, this study aims to utilize a genetic algorithm (GA) to optimize the fully-connected-layer of DenseNet121 for improving the classification accuracy of DenseNet121 on TrashNet and proposes the optimized DenseNet121. The results show that the optimized DenseNet121 achieved the highest accuracy of 99.6%, when compared with other studies’ CNNs. The data augmentation could perform higher efficiency on accuracy improvement of image classification than optimizing fully-connected-layer of DenseNet121 for TrashNet. To replace the function of the original classifier of DenseNet121 with fully-connected-layer can improve DenseNet121’s performance. The optimized DenseNet121 further improved the accuracy and demonstrated the efficiency of using GA to optimize the neuron number and the dropout rate of fully-connected-layer. Gradient-weighted class activation mapping helped highlight the coarse features of the waste image and provide additional insight into the explainability of optimized DenseNet121. [Display omitted]