A color image encryption based on the chaotic system, PSO-BP neural network and DNA mutation is proposed in this paper. Firstly, chaotic characteristics of the non-autonomous laser system are analyzed by phase diagram, Lyapunov exponent, and bifurcation diagram. Secondly, the hash value calculated by SHA-256 algorithm is used to change the initial conditions of chaotic system and generate chaotic sequence. Then, the color image is compressed by the back-propagation neural network based on particle swarm optimization. Based on dynamic encoding and decoding rules, image confusion and diffusion and DNA mutation are designed. Finally, experiments verify that the scheme can compress and encrypt color images, save transmission cost and improve the security performance, which is beneficial to the efficient transmission.