中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于单目多视角视觉的珍珠品质检测 农业机械学报 2014,45 (4) 276-283
Position: Home > Articles > Evaluation of Pearl Quality Based on Monocular Multi-view Machine Vision Transactions of the Chinese Society for Agricultural Machinery 2014,45 (4) 276-283

基于单目多视角视觉的珍珠品质检测

作  者：
汤一平;夏少杰;李陈荣;朱治亮;陈新峰;冯亦军
单  位：
浙江工业大学信息工程学院
关键词：
珍珠;品质检测;机器视觉;单目多视角;图像融合
摘  要：
利用单目多视角摄像装置直接获取5个不同视角的珍珠表面图像,对其进行图像预处理并按照成像规则进行融合拼接,从融合拼接的珍珠全景图像中提取出珍珠表面颜色、光泽度及均匀度等特征参数;依据与国家标准相一致的判断指标与相应的检测算法来识别和检测珍珠品质。实验结果表明,设计的基于单目多视角机器视觉装置能保证在一个统一的颜色系统中一次获得珍珠整个球体表面的图像,可实时完成珍珠的颜色、光泽度及均匀度等外观品质指标的视觉检测与分类,各个指标的检测精度均达到了80%以上。
译  名：
Evaluation of Pearl Quality Based on Monocular Multi-view Machine Vision
作  者：
Tang Yiping;Xia Shaojie;Li Chenrong;Zhu Zhiliang;Chen Xinfeng;Feng Yijun;College of Information Engineering,Zhejiang University of Technology;
关键词：
Pearl Quality detection Machine vision Mo nocular multi-view Image fusion
摘  要：
In order to evaluate pearl color and luster,a monocular multi-view imaging device was designed by placing a HD camera in front of a symmetric bucket cavity body which constituted by the multiple pieces of plane mirror.The device could achieve the pearl's surface images taken from five different perspectives.Then image processing was used to fuse the five pearl images and achieve a new image which contained the pearl's whole surface.After that,a pearl's region was divided into highlight areas and bright area,then the characteristic parameter of color was picked-up from bright area and the characteristic parameter of luster from highlight area.Finally,the feature fusion was used to determine the quality of the pearl.The experimental results showed that the monocular multi-view machine vision device could obtain the entire surface of the pearl in the same color system,and accomplish the real-time detection and grading for pearl's color,luster and uniformity.

相似文章

导出引用
计量
文章访问数: 11
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46