基于单角区域特征的烟标图像配准方法  

Cigarette Package Image Registration Method Based on Feature of Single-Angle Region

作　　者：王凯彬 李莹[1] 李殷昊 何自芬[1] Wang Kaibin;Li Ying;Li Yinhao;He Zifen(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,Yunnan,China)

机构地区：[1]昆明理工大学机电工程学院,云南昆明650500

出　　处：《激光与光电子学进展》2023年第2期111-116,共6页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61761024)。

摘　　要：实时图像与标准图像高效配准是保证烟标质量检测效率的关键步骤之一。根据烟标的结构和印刷工艺,提出了一种单角区域配准方法。所提单角区域配准法包括粗配准和精配准两步:粗配准利用烟标的边界特征调整烟标在图像中的姿态和位置,并去除图像中的冗余像素;精配准利用单角区域中的特征点求出实时图像与标准图像之间的单应性矩阵,然后利用单应性矩阵完成配准。实验结果表明,所提单角区域配准方法在烟标图像的配准速度和效果上优于尺度不变特征变换、ORB和AKAZE算法,能满足烟标质量检测的实时性要求。Efficient registration of real-time image and standard image is one of the key steps to ensure the efficiency of cigarette package quality inspection.According to the structure and printing process of cigarette package,a single-angle region registration method is proposed.The method is divided into two steps:rough registration and accurate registration.Rough registration uses the boundary features of cigarette labels to adjust the posture and position of cigarette labels in the image,and removes redundant pixels in the image.The accurate registration uses the homography matrix between the realtime image and the standard image to complete the registration.The experimental results show that the single-angle region registration algorithm is superior than scale invariant feature transformation,ORB,and AKAZE algorithms in registration speed and effect,and can meet the real-time requirements of cigarette package quality detection.

关 键 词：图像处理 数字图像处理 图像配准 单角区域特征 烟标 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]