QQ客服 官方微博 反馈留言

	基于灰度图像的压印凹凸字符质量检测研究
	曹建海 ; 路长厚 ; 李磊 ; CAO Jian-hai ; LU Chang-hou ; LI Lei
	2010-06-09 ; 2010-06-09
关键词	灰度字符 质量检测 矢量和 特征抽取 gray-scale character vector sum experimental quality inspecting feature extraction TP274.4
其他题名	Product Quality Inspecting On-line for the Pressed Protuberant Character
中文摘要	提出了直接在灰度图像上进行的压印字符质量检测的新方法。首先利用基于矢量和的最优圆心定位算法得到字符相似误差进行1次质量检测,然后以3点定位获得倾角误差进行2次质量检测。该方法是直接在灰度图像上提取检测特征,不仅保留图像的原始特征,克服了通常字符检测算法过分依赖于二值化算法及抗干扰性差等的弊病,而且快速,适合在线检测要求。实验表明,该方法不仅能检测不同灰度、位置和角度的压印字符,而且也适宜于有重叠、缺损等干扰的字符图像,正确检测率为97.27%。; The pressed protuberant character is a reflectorized character on the difference of reflectance.The image quality of the protuberant character is lower than that of the general character on the chromatic difference of background and foreground.So,the general character quality inspectiing method based on the binary-scale is unfit for the protuberant character.To solve this problem,a new method for direct gray-scale feature extraction based on the ring projection algorithm and the vector sum for inspecting the quality of the pressed character is presented.The new method keeps integrity feature information of the protuberant character and can overcome the main shortages of the traditional method on binary-scale image,such as binarization algorithm,the lower performance of anti-jamming.The experimental results show that the proposed method adapts to detecting the variant gray-scale,location and orientation of the character,and can yield an excellent performance under the conditions of noise and deformity.; 山东省重点产业化资助项目(0203c06)
语种	中文 ; 中文
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/55801]
专题	清华大学
推荐引用方式 GB/T 7714	曹建海,路长厚,李磊,等. 基于灰度图像的压印凹凸字符质量检测研究[J],2010, 2010.
APA	曹建海,路长厚,李磊,CAO Jian-hai,LU Chang-hou,&LI Lei.(2010).基于灰度图像的压印凹凸字符质量检测研究..
MLA	曹建海,et al."基于灰度图像的压印凹凸字符质量检测研究".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。