Action recognition is a leading research topic in the field of computer vision. This paper proposes an effective method for action recognition task based on the skeleton data. Four features are proposed based on the joint differences from 3D skeleton data. From the differences of 3D coordinates of corresponding joints in successive frames, three maps are extracted related to x, y and z coordinates respectively and then these maps are encoded into 2D color images, named as Joint Difference Maps (JDMs). The fourth JDM is formed by mapping the individual x, y and z difference maps into red, green and blue values. Hence, the 3D action recognition problem is converted into 2D image classification problem. It enables us to fine tune CNNs to learn informative features for 3D action recognition problem. The proposed method achieved 79.30% recognition rate on UTD MHAD dataset.