基于卷积神经网络的猪只个体身份识别研究

Research on pig individual identity based on convolutional neural networks

为了便于管理猪只,需及时关注每只猪的状态,本研究以真实条件下的7只猪只为研究对象,利用Keras建立了卷积层-池化层-卷积层-池化层2层卷积神经网络模型对猪只个体身份进行识别。建立的卷积神经网络模型对猪只个体身份识别的准确率可达85.71%。建立的猪只个体身份识别模型简单,执行效率高,可以较准确的实现猪只身份识别。

In order to facilitate the management of pigs,it is necessary to pay attention to the status of each pig in time.In this paper,using Keras and taking seven pigs under real conditions as the research object,a two-layer convolutional neural network model which includes convolutional layer-pooling layer-convolutional layer-pooling layer is established to identify individual pigs.The accuracy of the convolutional neural network model for individual identification of pigs can reach 85.71%.The pig individual identification model is simple and efficient,which can identify pigs more accurately.