检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]西安理工大学,西安710048
出 处:《包装工程》2017年第1期114-120,共7页Packaging Engineering
基 金:国家自然科学基金(11272253);陕西省自然科学基金(2014JM7290)
摘 要:目的针对啤酒生产过程中啤酒瓶盖背景复杂、激光雕刻的电子监管码难以定位识别的问题,提出一种综合图像匹配、形态学、霍夫变换等算法的啤酒瓶盖激光字符定位算法。方法该算法先采用抗任意角度旋转的图像匹配方法实现定位符的精确定位,再对定位符图像做二值化、形态学运算、边缘检测、轮廓提取、霍夫变换等处理,最终定位到字符。结果实验表明,该算法可以抗任意角度旋转,定位准确,鲁棒性强,图像定位准确率位高达97%。结论该算法较好地解决了啤酒生产包装中,激光雕刻的电子监管码字符识别过程中因为背景复杂难以定位识别、定位识别准确率低的难题。The work aims to put forward a new location algorithm of laser yards on beer bottle cap integrated with image matching, morphology and Hough transform, with respect to the complicated background of beer bottle cap in the process of producing beers and the problem of difficult location and recognition of electronic supervision codes engraved by laser. Firstly, an anti-arbitrary rotation image matching method was used to achieve accurate positioning of the locator. Secondly, binarization, morphological operation, edge detection, contour extraction, Hough transform and so on were carried out on the locator image. Finally, accurate positioning of the character was achieved. The experimental results showed that this method could give good positioning of arbitrary angle rotation locator and had higher veracity and robustness, and the image positioning accuracy was as high as 97%. The algorithm has properly solved such problems as difficult location and recognition and low accuracy of location and recognition due to complicated background in the process of producing beer packaging and recognizing the electronic supervision codes engraved by laser.
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.145