Aiming at the problem that there are many parameters in the process of plant leaf recognition and itis easy to produce over-fitting，in order to reduce the cost of storage and calculation，this paper proposes a plantleaf recognition convolutional neural network model based on Bayesian fusion. Firstly，the recursive Bayesianalgorithm is used for network pruning to adaptively remove network redundancy. Then，the convolutional layer andthe fully connected layer in the K-Means cluster quantization network are introduced to compress the entireconvolutional neural network. Finally，combined with the classical convolutional neural network model AlexNet，plant leaf recognition experiments were carried out. The experimental results show that in the same data set，thecompressed convolutional neural network takes less storage space，36 times compression and achieves a slightlybetter performance with 88. 58% accuracy than the original network and other compression methods.