The layout of the pressure plate of the relay protection device is gradually simplified and standardized, which objectively provides conditions for the intelligent inspection of the pressure plate. However, limited by the actual scene, it is often impossible to provide a pressure plate image of sufficient size and resolution for pressure plate recognition. This paper proposes a method to identify low-resolution protective platen images through collaborative learning of two deep neural networks, image enhancement network and target recognition network. The proposed image enhancement network uses collaborative learning signals from the target recognition network to enhance extremely low-resolution images into clearer and more informative images. And the target recognition network with high-resolution image training weight actively participates in the learning of the image enhancement network. It also uses the output of the image enhancement network as enhanced learning data to improve its recognition performance for very low-resolution objects. Through experiments on various low-resolution image benchmark data sets, it is verified that this method can improve the performance of the protection platen image reconstruction and classification.