微型相机模组贴装过程画胶表面三维测量方法

Three-dimensional Measurement Method of Glue Surface During the Mounting Process of Micro-camera Module

微型相机模组画胶工艺的三维测量是确保其贴装质量的关键。针对微型相机模组贴装过程的画胶表面三维测量需求,基于单目视觉成像模型提出了画胶表面的三维测量方法。首先,基于单目视觉系统的成像机理建立其成像模型,进而揭示该成像模型中各参数对图像灰度值的影响规律。其次,分析单幅画胶图像的三维信息特征,建立待测画胶表面高度信息的映射模型,给出待测画胶表面高度信息的求解方法。最后,通过实验测量微型相机模组贴装过程的画胶表面三维。实验结果表明,所提方法的高度测量平均误差小于±10μm,且单张图像的检测时间小于0.2 s,验证了所提方法的有效性和实时性。

The production process of Micro-camera module includes plate washing,plate drying,glue painting,crystal pasting,bonding,glue baking,detection,etc. The glue painting is an important step and its quality has an important effect on the mounting performance of the Micro-camera module. Threedimensional measurement is the key technology to ensure its mounting quality,and usually,the quick glue painting process needs the accuracy and agile detected method. To meet the real-time measurement requirements of glue surface in the mounting process of Micro-camera module,the height information mapping model of the detected glue surface is established based on monocular vision imaging system,and a three-dimensional measurement method of glue surface is proposed in this manuscript. The proposed method can be divided into following three steps. Firstly,by analyzing the influencing factors of visible light focusing imaging system and describing the image features based on the mentioned monocular vision system,the imaging model is built,which reveals the influence rule of light source intensity,object surface inclination,diffuse reflection coefficient and reflected light deflection angle on image gray value in such imaging model. Secondly,the mapping model of the surface height information of the detected object is established,and the height calculating equations of the visual surface are derived based on the proposed mapping model. Especially,the proposed equations only contain two un-knowns variables,and the threedimensional information of the detected surface is obtained by solving the equations.Furthermore,because of the proposed one-to-one mapping model,the theoretical analysis results show that the proposed method can avoid the solution uncertainty problem arising from Shape-from-shading method(SFS method)and the matching problem arising from binocular vision method. Finally,the validity of the proposed method was verified by the glue measurement experiment. In this process,three different detected methods are compared with the same testing condition. Experimental results showed that the proposed method can recover the three-dimensional morphology of the glue surface,and its average height measurement error is less than ±10 μm with the single image detection speed of less than 0.2 s,which verifies the effectiveness and real-time performance of the proposed method.