Energy consumption of mobile application software is an important factor influencing the battery life of smart phone terminals. Currently, for the tens of thousands of Android software, we propose a static visual detection and classification method based on application energy consumption. Compared with the high-precision and complex application component energy consumption model, this model analyzes the bytecode images generated by the dex and xml files in the Android apk and trains them with deep learning methods. The energy consumption level of two kinds of different mobile terminal software can be obtained, which can quickly estimate the energy consumption of mobile terminal when the application is runing. Experimental results show that the model’s classification accuracy of energy consumption estimation is 50.49%, which can help mobile end users to easily predict the battery power consumed by applications.