This paper presents a novel bionic model based on olfactory systems to generate texture image. The model simulates one of the olfactory neural networks. The chaotic characters of Logistic function are used to adjust the parameters of model during iteration. A simple periodic function is used as the activation function of node in the model to generate periodic texture. And a random noise is introduced to simulate the background noise of brain when processing information. The experimental results show that the model can generate plentiful and multivariant texture images. The introduced random noise plays an important role and enriches the variety of texture images obviously. In addition

the model efficiency to generate texture image outperforms the conventional back propagation neural network model.