IC solder joint inspection via adaptive statistical modeling

Abstract

Purpose Statistical modeling has been successfully applied to integrated circuit (IC) solder joint inspection. However, there are some inherent problems in previous statistical modeling methods. This paper aims to propose an adaptive statistical modeling method to further improve the inspection performance for IC solder joints. Design/methodology/approach First, different pixels in the IC solder joint image were modeled by different templates, each of which was composed of the hue value of the pixel and a proposed template significance factor. Then, the potential defect image was obtained by adaptive template matching and the potential defect threshold for each pixel. It was noted that the number of templates, matching distance threshold, potential defect threshold and updating rate were adaptively updated during model training. Finally, the trained statistical model was used to inspect the IC solder joints by means of defect degree. Findings Experimental results indicated that the proposed adaptive schemes greatly contributed to the inspection performance of statistical modeling. Also, the proposed inspection method achieved better performance compared with some state-of-the-art inspection methods. Originality/value The proposed method offers a promising approach for IC solder joint inspection, which establishes different numbers of templates constructed by pixel values and template significance factors for different pixels. Also, some important parameters were adaptively updated with the updating of the model, which contributed to the inspection performance of the model.

Robust vision detection of pipeline solder joints

“…(2022) proposed an IC solder joints detection method based on optimal statistical modeling, which first developed a statistical model from qualified IC solder joints with template clustering, and then constructed a balanced set of potential defect images (PDIs) and optimized the evaluation model by L1- and L2- penalized normalized least squares. Finally, the qualities of IC solder joints are evaluated via the optimized weighted PDI; Xiao et al . (2022) proposed an improved statistical modeling method based on visual background extraction (ViBe) to detect integrated chip (IC) solder joints, which adaptively establishes multiple templates to represent images of IC solder joints images and statistically modeled the templates for different solder joint defects; Peng et al .…”

“…In recent years, machine vision technology has been widely used in solder joint defect detection due to its high efficiency, cost-effective, high degree of safety and reliability. Song et al (2017) At present, the solder joint detection is mainly based on image feature analysis (Song et al, 2017;Zeng et al, 2021;Wu and Xu, 2018), statistical feature analysis (Peng et al, 2022;Xiao et al, 2022;Chen et al, 2022) and deep learning methods (Peng et al, 2022;Sontheimer and Chou, 2022;Wu et al, 2020); and most research related to solder joint detection are about integrated chip (IC) solder joint and metal surface weld, which is essentially a classification task of different defect types. In contrast, detection methods for pipeline solder joints have rarely been proposed.…”

CSSD-YOLO: A Modified YOLOv5 Method for Solder Joint Defect Detection

“…The machine vision system embedding machine vision technology is widely used in various industrial product defect detection scenarios because of its high detection efficiency and the advantages of reducing labor costs [4][5][6]. The detection of solder joint defects based on machine vision can be divided into three categories: the feature-based method [7], the statistic-based method [8], and the deep-learning-based method [9]. The deep learning method has been used extensively in this research area, especially in developing a lightweight deep neural network (DNN) model.…”