Abstract:
Pulse coupled neural networks have been proposed for a variety of applications in the field of image processing. Its improved version, the dual channel pulse coupled neural network, also has excellent performance in the field of image fusion. In order to combine the excellent parallel performance of quantum computing with dual channel pulse coupled neural networks and reduce their algorithmic complexity, the dual channel quantum pulse coupled neural network (DQPCNN) is proposed. In this model, quantum logic gates are used to construct quantum modules, such as quantum full adder, quantum multiplier, quantum comparator and a quantum image convolution module for DQPCNN. And these modules are employed to perform the required calculations for DQPCNN. The effectiveness of the DQPCNN is demonstrated by simulation experiments, and the complexity of the DQPCNN is lower than other models.