Open AccessQuality Inspection of Gluing in Narrow Border Based on Depth Map
Author(s) -
Xiaopeng Zou,
Xingyu Gao,
Bin Liao,
Chuannen Wei
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1820/1/012132
Subject(s) - glue , sample (material) , measure (data warehouse) , pixel , position (finance) , computer vision , artificial intelligence , computer science , process (computing) , frame (networking) , data mining , engineering , telecommunications , physics , mechanical engineering , finance , economics , thermodynamics , operating system
To solve the problem of glue breakage and overflow in the packaging process of mobile phones, a glue detection algorithm based on the depth map is proposed. By collecting the image no gluing and gluing after dispensing, the pixel value of each frame in the corresponding position of the corresponding sample is sequentially intercepted in the same sample, and the glue contour is reconstructed by rearranging the intercepted ROI. Last, measure the width and height information of the glue according to the contour, and judge the defect problem at the same time. Experimental results show that the algorithm can accurately measure the result of the micron-level glue, and accurately determine the lack of glue. At the same time, the measurement accuracy of the algorithm is 0.01mm, and the measurement results are accurate and stable.