文章摘要
李海山,唐海艳,梁栋,韩军.基于卷积神经网络的印刷品颜色缺陷检测[J].包装工程,2021,42(23):170-177.
LI Hai-shan,TANG Hai-yan,LIANG Dong,HAN Jun.Detection of Printing Color Defect Based on Convolutional Neural Network[J].Packaging Engineering,2021,42(23):170-177.
基于卷积神经网络的印刷品颜色缺陷检测
Detection of Printing Color Defect Based on Convolutional Neural Network
投稿时间:2021-02-09  
DOI:10.19554/j.cnki.1001-3563.2021.23.024
中文关键词: 图像直方图特征  色差缺陷  卷积神经网络  检测效率
英文关键词: histogram features of image  color difference defect  convolutional neural network  detection efficiency
基金项目:
作者单位
李海山 陕西金叶印务有限公司西安 710000 
唐海艳 陕西金叶印务有限公司西安 710000 
梁栋 陕西金叶印务有限公司西安 710000 
韩军 陕西金叶印务有限公司西安 710000 
摘要点击次数:
全文下载次数:
中文摘要:
      目的 提取样本图像颜色直方图特征对卷积神经网络进行训练,达到快速、高准确率检测图像颜色缺陷的目的。方法 将标准图像从RGB颜色空间转换至HSV颜色空间,通过改变图像H,S,V三分量值获取训练样本和测试样本;在HSV颜色空间中非均匀量化图像的颜色直方图,得到所有训练样本和测试样本的颜色直方图特征;利用样本图像颜色直方图特征训练卷积神经网络,然后对测试样本进行检测,研究检测的速度、准确率,并将该检测方法与逐像素、超像素、BP神经网络和支持向量机方法进行对比。结果 对于图片尺寸为512×512的彩色图像,卷积神经网络检测单幅图片的平均检测时间约为57.66 ms,训练样本图像为50 000张时,卷积神经网络方法对10 000张测试样本进行检测的准确率为99.77%。结论 卷积神经网络方法在保证高准确率的前提下大幅提高检测精度,对于印刷品色差缺陷在线检测具有良好的应用价值。
英文摘要:
      The work aims to train the convolutional neural network (CNN) by extracting color histogram features of sample images, so as to achieve the purpose of detecting image color defect quickly and accurately. RGB color space of standard image was converted to HSV color space and training and testing samples were obtained by change of H, S and V component in image. The color histogram of image was non-equally quantized in HSV color space, and then all of the color histogram features of training and testing samples were obtained. The CNN was trained by color histogram features of sample image, and then the testing sample image was detected to study the detection speed and precision. Finally, this method was compared to each-pixel, super-pixel, BP and support vector machine (SVM) recognition methods. For the color image of 512×512, the mean detection time of each image by CNN was 57.66 ms. When the number of training samples was 50 000, the detection precision of CNN for 10 000 testing samples was 99.77%. Therefore, the detection method of convolutional neural network can significantly improve the detection precision while ensuring the accuracy and has good application value in on-line color defect monitoring of printing.
查看全文   查看/发表评论  下载PDF阅读器
关闭

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第21142761位访问者    渝ICP备15012534号-2

版权所有:《包装工程》编辑部 2014 All Rights Reserved

邮编:400039 电话:023-68795652 Email: designartj@126.com

    

渝公网安备 50010702501716号