基于多对象匹配与融合字符特征的印刷质量检验方法
|
摘要
目的为了增强字符配准对字符位姿变化的鲁棒性和识别能力,以及印刷质量检验精度和缺陷类型分析对不同字符产品的自适应性,提出一种基于多对象匹配与融合字符特征的印刷质量检验方法。方法采用多张合格字符样品图像进行模板构建;借助多对象匹配来配准多个待检验的字符,消除字符位姿的变化对字符配准的影响;进行逐像素的比对,检验字符区域的质量;利用灰度阈值分割以及Sobel边缘检测,将字符区域分成3个待检验的局部特征区域:边缘、前景、后景;进而获取边缘完整性,前景面积和灰度,背景面积和灰度这些显著的字符特征,由多张字符样品训练每个特征的自适应的合格范围;将其组合,形成融合字符特征,分析缺陷的类型。结果测试数据表明,针对不同种类、不同精度要求的字符产品,所提方法对于字符质量的判断准确率达到100%,对缺陷类型的分类准确率保持在84.2%以上。结论所提字符质量检验方法拥有良好的鲁棒性与自适应性,在包装、印刷等行业具备较高的应用价值。
This work aims to propose a character printing quality inspection method based on multi-object matching and fusion character features, to enhance the robustness and recognition of character registration to changes in character pose, as well as print quality inspection accuracy and defect type analysis for different character products. Firstly, multiple qualified character sample images were applied to template construction. Then the multi-object matching method was introduced to match the characters to be inspected to eliminate the effect of changes in character pose on character registration. Then a pixel-by-pixel comparison was performed to verify the quality of the character area. Last, with gray threshold segmentation and Sobel edge detection, the character region was divided into three local feature regions to be tested: edge,foreground, and background. Significant character features such as edge integrity, area and gray scale of foreground and background were collected. The adaptive qualifying range for each feature was trained from multiple character samples. The type of defect was given with the fused character features. Experimental results show that, when it came to different types of character products with different precision requirements, the accuracy of the proposed method for character quality was 100%, and the accuracy of classification of defect types remained above 84.2%. Featured by good robustness and adaptability, the proposed character quality inspection method has good application value in packaging, printing and other industries.
This work aims to propose a character printing quality inspection method based on multi-object matching and fusion character features, to enhance the robustness and recognition of character registration to changes in character pose, as well as print quality inspection accuracy and defect type analysis for different character products. Firstly, multiple qualified character sample images were applied to template construction. Then the multi-object matching method was introduced to match the characters to be inspected to eliminate the effect of changes in character pose on character registration. Then a pixel-by-pixel comparison was performed to verify the quality of the character area. Last, with gray threshold segmentation and Sobel edge detection, the character region was divided into three local feature regions to be tested: edge,foreground, and background. Significant character features such as edge integrity, area and gray scale of foreground and background were collected. The adaptive qualifying range for each feature was trained from multiple character samples. The type of defect was given with the fused character features. Experimental results show that, when it came to different types of character products with different precision requirements, the accuracy of the proposed method for character quality was 100%, and the accuracy of classification of defect types remained above 84.2%. Featured by good robustness and adaptability, the proposed character quality inspection method has good application value in packaging, printing and other industries.
引文
[1]陈华彩,李梅.试论印刷品质量的内容及其实际意义[J].广东印刷,2013(1):7-10.CHEN Hua-cai,LI Mei.Content of Print Quality and Its Practical Significance[J].Guangdong Print,2013(1):7-10.
[2]王国庆.浅谈印刷品质量在线检测技术[J].广东印刷,2014(4):54-55.WANG Guo-qing.Content of Print Quality Online Detection Technology[J].Guangdong Print,2014(4):54-55.
[3]李雪枚,罗世永,李绍国,等.喷墨印刷质量缺陷的产生原因和解决对策[J].包装工程,2018,39(1):174-178.LI Xue-mei,LUO Shi-yong,LI Shao-guo,et al.Causes and Solutions for Inkjet Printing Quality Defects[J].Packaging Engineering,2018,39(1):174-178.
[4]和红顺.利用证据神经网络的多分类器系统构造[J].西安交通大学学报,2018,52(11):97-103.HE Hong-shun.Research and Application of Image Defect Recognization Algorithm Based on Dynamic Threshold and Storied Inspect[J].Journal of Xi'an Jiaotong University,2018,52(11):97-103.
[5]胡方尚,郭慧.基于改进多类支持向量机的印刷缺陷检测[J].华东理工大学学报(自然科学版),2017,43(1):143-148.HU Fang-shang,GUO Hui.Printing Defects Inspection Based on Improved Multi-Class Support Vector Machine[J].Journal of East China of Science and Technology,2017,43(1):143-148.
[6]徐敏,唐万有,马千里,等.基于blob算法的印刷缺陷在线检测的研究[J].包装工程,2011,32(9):20-23.XU Min,TANG Wan-you,MA Qian-li,et al.Research on Online Detection of Printing Defects Based on Blob Algorithm[J].Packaging Engineering,2011,32(9):20-23.
[7]VERIKAS A,LUNDSTR?M J,BACAUSKIENE M,et al.Advances in Computational Intelligence-Based Print Quality Assessment and Control in Offset Colour Printing[J].Expert Systems with Applications,2011,38(10):13441-13447.
[8]王兮之.浅谈印刷质量视觉检测系统的设计与应用[J].大科技,2013(15):282-283.WANG Xi-zhi.Content of the Design and Application of Printing Quality Visual Inspection System[J].Super Science,2013(15):282-283.
[9]杨艺,南建昌,赵严,等.一种印刷品质量检测方法.CN106251341A[P].2016-07-22.YANG Yi,NAN Jian-chang,ZHAO Yan,et al.A Print Quality Inspection Method,CN106251341A[P].2016-07-22.
[10]程小飞.一种印刷品质量检测方法,CN105844621A[P].2016-03-17.CHENG Xiao-fei.A Print Quality Inspection Method,CN105844621A[P].2016-03-17.
[11]李瑞娟,楚高利,邓倩,等.印刷品质量检测颜色转换模型研究[J].包装工程,2015,36(11):145-148.LI Rui-juan,CHU Gao-li,DENG Qian,et al.Research On Color Conversion Model of Print Quality Inspection[J].Packaging Engineering,2015,36(11):145-148.
[12]ULRICH M,BAUMGARTNER A,STEGER C.Automatic Hierarchical Object Decomposition for Object Recognition,2002,14:99-104.
[13]ULRICH M,STEGER C.Hierarchical Model Construction for Hierarchical Component Based Object Recognition Involves Determining Relative Search Spaces of Object Portions,from Which Hierarchical Model Is Formed,for Utilization in Object Recognition Phase.EP1394727-A1;JP2004094954-A;US2004042661-A1;US7239929-B2;JP2009104666-A;JP4334301-B2;EP1394727-B1;JP2012212476-A;JP5329254-B2;JP5330579-B2[P].
[14]朱保平,张张.数据结构与算法分析[M].北京:人民邮电出版社,2016.ZHU Bao-pin,ZHANG Zhang.Data Structure and Algorithm Analysis[M].Beijing:People Post Press,2016.
[15]范晓鹏.人眼灰度感知建模及其在图像增强中的应用[J].计算机工程与应用,2018,54(13):215-221.FAN Xiao-peng.Human Eye Gray level Perception Modeling and Its Application in Image Enhancement[J].Computer Engineering and Applications,2018,54(13):215-221.
[16]刘海娟.基于图像处理的印刷品缺陷检测技术研究[D].哈尔滨:哈尔滨工业大学,2012.LIU Hai-juan.Research on Print Defect Detection Technology Based on Image Processing[D].Harbin:Harbin Institute of Technology,2012.
[17]孙云.图像腐蚀在pcb喷墨打印中的应用[J].电脑知识与技术,2016,12(4):186-187.SUN Yun.The Application of Image Corrosion in PCBInkjet Printer[J].Computer Knowledge and Technology,2016,12(4):186-187.
[2]王国庆.浅谈印刷品质量在线检测技术[J].广东印刷,2014(4):54-55.WANG Guo-qing.Content of Print Quality Online Detection Technology[J].Guangdong Print,2014(4):54-55.
[3]李雪枚,罗世永,李绍国,等.喷墨印刷质量缺陷的产生原因和解决对策[J].包装工程,2018,39(1):174-178.LI Xue-mei,LUO Shi-yong,LI Shao-guo,et al.Causes and Solutions for Inkjet Printing Quality Defects[J].Packaging Engineering,2018,39(1):174-178.
[4]和红顺.利用证据神经网络的多分类器系统构造[J].西安交通大学学报,2018,52(11):97-103.HE Hong-shun.Research and Application of Image Defect Recognization Algorithm Based on Dynamic Threshold and Storied Inspect[J].Journal of Xi'an Jiaotong University,2018,52(11):97-103.
[5]胡方尚,郭慧.基于改进多类支持向量机的印刷缺陷检测[J].华东理工大学学报(自然科学版),2017,43(1):143-148.HU Fang-shang,GUO Hui.Printing Defects Inspection Based on Improved Multi-Class Support Vector Machine[J].Journal of East China of Science and Technology,2017,43(1):143-148.
[6]徐敏,唐万有,马千里,等.基于blob算法的印刷缺陷在线检测的研究[J].包装工程,2011,32(9):20-23.XU Min,TANG Wan-you,MA Qian-li,et al.Research on Online Detection of Printing Defects Based on Blob Algorithm[J].Packaging Engineering,2011,32(9):20-23.
[7]VERIKAS A,LUNDSTR?M J,BACAUSKIENE M,et al.Advances in Computational Intelligence-Based Print Quality Assessment and Control in Offset Colour Printing[J].Expert Systems with Applications,2011,38(10):13441-13447.
[8]王兮之.浅谈印刷质量视觉检测系统的设计与应用[J].大科技,2013(15):282-283.WANG Xi-zhi.Content of the Design and Application of Printing Quality Visual Inspection System[J].Super Science,2013(15):282-283.
[9]杨艺,南建昌,赵严,等.一种印刷品质量检测方法.CN106251341A[P].2016-07-22.YANG Yi,NAN Jian-chang,ZHAO Yan,et al.A Print Quality Inspection Method,CN106251341A[P].2016-07-22.
[10]程小飞.一种印刷品质量检测方法,CN105844621A[P].2016-03-17.CHENG Xiao-fei.A Print Quality Inspection Method,CN105844621A[P].2016-03-17.
[11]李瑞娟,楚高利,邓倩,等.印刷品质量检测颜色转换模型研究[J].包装工程,2015,36(11):145-148.LI Rui-juan,CHU Gao-li,DENG Qian,et al.Research On Color Conversion Model of Print Quality Inspection[J].Packaging Engineering,2015,36(11):145-148.
[12]ULRICH M,BAUMGARTNER A,STEGER C.Automatic Hierarchical Object Decomposition for Object Recognition,2002,14:99-104.
[13]ULRICH M,STEGER C.Hierarchical Model Construction for Hierarchical Component Based Object Recognition Involves Determining Relative Search Spaces of Object Portions,from Which Hierarchical Model Is Formed,for Utilization in Object Recognition Phase.EP1394727-A1;JP2004094954-A;US2004042661-A1;US7239929-B2;JP2009104666-A;JP4334301-B2;EP1394727-B1;JP2012212476-A;JP5329254-B2;JP5330579-B2[P].
[14]朱保平,张张.数据结构与算法分析[M].北京:人民邮电出版社,2016.ZHU Bao-pin,ZHANG Zhang.Data Structure and Algorithm Analysis[M].Beijing:People Post Press,2016.
[15]范晓鹏.人眼灰度感知建模及其在图像增强中的应用[J].计算机工程与应用,2018,54(13):215-221.FAN Xiao-peng.Human Eye Gray level Perception Modeling and Its Application in Image Enhancement[J].Computer Engineering and Applications,2018,54(13):215-221.
[16]刘海娟.基于图像处理的印刷品缺陷检测技术研究[D].哈尔滨:哈尔滨工业大学,2012.LIU Hai-juan.Research on Print Defect Detection Technology Based on Image Processing[D].Harbin:Harbin Institute of Technology,2012.
[17]孙云.图像腐蚀在pcb喷墨打印中的应用[J].电脑知识与技术,2016,12(4):186-187.SUN Yun.The Application of Image Corrosion in PCBInkjet Printer[J].Computer Knowledge and Technology,2016,12(4):186-187.