Index map prediction method based on genetic algorithm and BP neural network

• Main Authors: SONG CHUANMING, ZHENG HONGLIANG, WANG XIANGHAI, LIU DINGKUN
• Format: Patent
• Language: Chinese; English
• Published: 11.12.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an index map prediction method based on a genetic algorithm and a BP neural network, and the method comprises the steps: firstly exploring the good prediction and generalization capability of the BP neural network, building a BP neural network model for index map prediction coding, and enabling four pixels around a to-be-predicted pixel and in a causal neighborhood to serveas the input of the BP neural network model; predicting the index value of the pixel to be predicted, so that global data related and non-local related specific index modes of the index map can be effectively described; secondly, introducing a genetic algorithm with global search capability to optimize the initial connection weight and the neuron threshold of the BP neural network, and establishing a BP neural network model GABP based on the genetic algorithm, so that the sensitivity of the BP neural network to the initial connection weight and the neuron threshold is reduced, and the speed and the precision of netwo