Authors

Abstract

In order to solve the problem that the behavior of domestic pig and wild boar in the pigsty will bring harm to the growth of pigs,a recognition and classification system of pigs based on convolution neural algorithm is developed in this paper.Different from the previous detection system, the system uses convolution neural network algorithm to cooperate with the monitoring system to complete the function of real-time monitoring.When the algorithm is integrated into the image processing module of the client, the accuracy can reach 97.08%.This paper introduces the architecture of the system and the design of the front end and back end, and analyzes the recognition and classification method based on convolution neural network algorithm.

Abstract in Chinese

针对猪舍中存在的家养猪和野猪的蹿窝行为会给猪只成长带来危害的问题，本文研究出了一款基于卷积神经算法的猪只识别分类的系统。不同于以往的检测系统，该系统通过卷积神经网络算法与监控系统相协作完成实时监测的功能。将算法融入到客户端的图像处理模块，准确率可达到97.08%。本文介绍了该系统的架构以及前后端的设计，分析了基于卷积神经网络算法识别分类的方法。