Within the framework of Internet of Things or when constrained in limited space, lensless imaging technology provides effective imaging solutions with low cost and reduced size prototypes. In this paper, we proposed a method combining deep learning with lensless coded mask imaging technology. After replacing lenses with the coded mask and using the inverse matrix optimization method to reconstruct the original scene images, we applied FCN-8s, U-Net, and our modified version of U-Net, which is called Dense-U-Net, for post-processing of reconstructed images. The proposed approach showed supreme performance compared to the classical method, where a deep convolutional network leads to critical improvements of the quality of reconstruction. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.