A weight pruned convolutional neural network for garbage image classification

Developing automatic garbage sorting technologies will be helpful to promote the construction of ecological civilization in China. A weighted convolutional neural network for the categorization of garbage images. First, a garbage image classification algorithm is implemented using a convolutional neural network. Then, the architecture of the network is simplified by weight pruning to get rid of the dependency of GPU servers. In addition, a garbage image database has been established to train and test the proposed algorithm. The experimental results show that the accuracy of proposed method can reach 90.88% on the test set, and the running time of processing each image takes 78ms.

I. Introduction

Garbage has caused serious harm to the ecological environment. Therefore, rational separation and reuse of garbage is important for the construction of a green and sustainable development society [1]. In China, waste separation is currently carried out mainly by manual means, either through residents' spontaneous waste separation or sorting by dedicated personnel, which is inefficient. Promotion of garbage sorting is difficult due to the inadequacy of relevant laws and regulations and the imperfection of safeguards and technologies [2]. The authors of this research suggest a lightweight garbage image classification algorithm based on Weight Pruning Convolutional Neural Network (WPCN), which provides the foundation for the implementation of automated waste sorting technology.