首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
王雨滢,赵庆生,梁定康. 基于深度学习网络的电气设备图像分类[J]. 科学技术与工程, 2020, 20(23): 9491-9496.
WANG Yu-ying,梁定康.Electrical Equipment Image Classification Based on Deep Learning Network[J].Science Technology and Engineering,2020,20(23):9491-9496.
基于深度学习网络的电气设备图像分类
Electrical Equipment Image Classification Based on Deep Learning Network
投稿时间:2019-12-07  修订日期:2020-05-06
DOI:
中文关键词:  电气设备  图像分类  深度学习  卷积神经网络  支持向量机
英文关键词:electric equipment  image classification  deep learning  convolutional neural network  support vector machine
基金项目:山西省自然科学基金 (201801D221362)
        
作者单位
王雨滢 太原理工大学电力系统运行与控制山西省重点实验室
赵庆生 太原理工大学电力系统运行与控制山西省重点实验室
梁定康 太原理工大学电力系统运行与控制山西省重点实验室
摘要点击次数: 143
全文下载次数: 59
中文摘要:
      为了对变电站中智能巡检系统采集到的海量图片进行快速分析和识别,提出一种深度学习和支持向量机(SVM)相结合的图像分类模型。首先,运用旋转、翻折等方法对采集到的原始数据进行扩充。然后,合并扩展图像集,并在相同类型的条件下将其随机划分为训练集和测试集。基于实际图像改进卷积神经网络(CNN),并提取训练集的图像特征。最后,通过使用训练集图片的深度特征来训练SVM分类器,并且在测试集图片上实现分类测试。利用巡检机器人采集到的8000张图片对模型精度进行实验验证,结果表明,该模型具有较强的分类性能。
英文摘要:
      In order to quickly analyze and identify the massive images collected by the intelligent inspection system in the substation, an image classification model combining deep learning and support vector machine(SVM) is proposed. First, the original data collected was expanded by means of rotation, folding, etc. The expanded images were then randomly divided into training sets and test sets according to the types, and the parameters in the convolutional neural network (CNN) were improved by actual data, and the training set image features were extracted on the trained CNN models. Finally, the SVM classifier was trained by using the depth features of the training set image, and the test set image was classified and verified. The experiment uses 8000 pictures collected by the inspection robot in a substation to verify the accuracy of the model. The results show that the model has strong classification performance.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第32688200位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号