Bidirectional digital image secure transmission and recognition based on a long-distance chaos synchronization system with machine learning capability

Abstract

Based on chaos synchronization of two response lasers (RLs) injected by the common chaos signals from a driving laser (DL) with double optical feedback (DOF) and an additional neural network (NN), a bidirectional chaotic secure communication system with machine learning capability is proposed and the long-distance digital image transmission and recognition performances are numerically investigated. The simulated results show that the time delay signature (TDS) of the driving chaotic signals from DL with DOF is greatly weakened under suitable operation conditions. Two RLs can generate chaos signals with low TDS and broad bandwidth, and the high-quality chaos synchronization between two RLs can be achieved while the synchronization quality between DL and any one of RLs is extremely bad, which is helpful to realize the secure communication. Using the synchronized chaos output signals from two RLs as chaos carriers and chaos masking (CM) encoding method, the bidirectional 10\xa0Gb/s secure communication over 140\xa0km fiber channel can be realized and the effects of the fiber parameters on the communication performances are discussed. After adopting an additional NN, a long-distance digital image transmission and recognition based on this proposed secure communication system can be realized and the communication distance can be extended to 220\xa0km.