基于深度学习的青藏高原畜牧业多目标动物图像检索研究  

Research on Multi-objective Animal Image Retrieval of Animal Husbandry in Qinghai Tibet Plateau Based on Deep Learning

作　　者：更藏卓玛 安见才让[1] GENG ZANG Zhuo-ma;AN JIAN Cai-rang(Qinghai Nationalities University,qinghai 810000)

机构地区：[1]青海民族大学,青海810000

出　　处：《软件》2020年第7期126-131,共6页Software

基　　金：青海省科技计划项目(2019-ZJ-7066);国家自然科学基金项目(61862054)。

摘　　要：深度学习作为机器学习的一大重要分支,近年来在图像处理与自然语言处理领域应用极为广泛,随着深度学习被应用于各行各业,越来越多复杂的问题也随之简化。本文利用深度学习中的卷积神经网络模型进行研究,采用当下较为流行的YOLO框架,设计并实现了一套实用于青藏高原畜牧业动物图像检索的系统,该系统可根据相应需求检索单目标和多目标图像,在多次实验结果反馈中正确率较高,可在一定范围内满足实际应用。As an important branch of machine learning, deep learning has been widely used in the field of image processing and natural language processing in recent years. With the application of deep learning in all walks of life, more and more complex problems are also simplified. In this paper, the convolution neural network model in deep learning is used for research, and a set of practical animal image retrieval system is designed and implemented based on the current popular yo framework. The system can retrieve single target and multi-target images according to the corresponding needs. The accuracy of the system is high in multiple experimental results feedback, and it can meet the practical application in a certain range.

关 键 词：深度学习 卷积神经网络 图像检索系统 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]