The differences in material properties of various common recyclable garbage will be directly mapped to the difference inspectral characteristics. While acquiring the spectral information of the garbage, the hyperspectral imaging technology canobtain the spatial information of the garbage, and realize the rapid detection and classification of garbage by using themethod of "spectral-spatial" .The classification model is established combined the spectral characteristics under the samplefeature space with CNN (convolutional neural network) machine learning algorithm, and then the classification model istrained and optimized by using database training sample set. Finally, 92.10% classification accuracy is achieved aftertesting the sample set.
展开▼