Solder Joint Defect Detection Based on Image Segmentation and Deep Learning

Gao, Shijia; Zhang, Hui; Mi, Hanguang

doi:10.1109/icsidp47821.2019.9173443

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10 , 12 , 14 , 16 , 18 , 20 \left.\right}$. [ 9,10,12,13,31 ] We also include a classification and segmentation MTL approach for comparison although it was originally used for biomedical images. [ 42 ] Similar to (13), the average accuracy on the test set

$D^{\left(\right.

…”

Section: Resultsmentioning

confidence: 99%

“…[8] Current approaches often treat PCB soldering defect detection as a supervised image classification problem. [9][10][11][12][13] Vanilla deep learning models are used and trained with thousands of PCB defect images. In fact, for most industrial-grade PCB manufacturing processes, soldering defects are not common.…”

Section: Introductionmentioning

confidence: 99%

“…[ 29,30 ] A rule‐based approach was used to crop out the soldering points, followed by a convolutional neural network (CNN) to classify whether the soldering point was normal or not. [ 9 ] CNN was also adopted for USB soldering point classification after localizing the USB connections. [ 10 ] VGGNet, a variant of CNN, was modified to classify abnormal solder joints.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PCB Soldering Defect Inspection Using Multitask Learning under Low Data Regimes

Tsang,

Suo,

Chan

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

To increase the reliability of the printed circuit board (PCB) manufacturing process, automated optical inspection is often employed for soldering defect detection. However, traditional approaches built on handcrafted features, predefined rules, or thresholds are often susceptible to the variation of the acquired images’ quality and give unstable performances. To solve this problem, a deep learning‐based soldering defect detection method is developed in this article. Like many real‐life deep learning applications, the number of available training samples is often limited. This creates a challenging low‐data scenario, as deep learning typically requires massive data to perform well. To address this issue, a multitask learning model is proposed, namely, PCBMTL, that can simultaneously learn the classification and segmentation tasks under low‐data regimes. By acquiring the segmentation knowledge, classification performance is substantially improved with few samples. To facilitate the study, a soldering defect image dataset, namely, PCBSPDefect, is built. It focuses on the dual in‐line packages (DIP) at the PCB back side, DIP at the PCB front side, and flat flexible cables. Experimental results show that the proposed PCBMTL outperforms the best existing approaches by over 5–17% of average accuracy for different datasets.

show abstract

$D^{\left(\right.

…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PCB Soldering Defect Inspection Using Multitask Learning under Low Data Regimes

Tsang,

Suo,

Chan

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Based on white light reflection and digital microscope capture [3][4][5][6][7][8], there are different proposed method using digital image processing and some other machine learning techniques. For example, the YOLO is the real-time object detection that applies to detect the solder joint defects [3][4].…”

Section: Introductionmentioning

confidence: 99%

“…The result shown that the CNN had the higher accuracy as 85%. In addition, the traditional solution of image processing with OpenCV library such as image subtraction and blob detection are still usable, by Fa'Iq Raihan and Win Ce in 2017, [6] for the automated inspection system. Another interesting solution for the white light reflection, B.C.…”

Section: Introductionmentioning

confidence: 99%

Defect Solder Classification in Print Circuit Boards using Machine Learning

Tangsuksant,

Inthiam,

Silangren

et al. 2023

Proceedings of International Conference on Artificial Life and Robotics

View full text Add to dashboard Cite

This research proposes the solder inspection using the digital image processing technique and machine learning base with our machine vision prototype. There are five classes of classifying solder, including acceptable, short circuit, insufficient, blow hole and too much of solder. Automatic Optical Inspection (AOI) is used for the light source in the designed prototype and industrial camera which are installed on the mini-CNC. For the algorithm, this research applies the scanning line of binary image for detecting short circuit defection and the Random Forrest model for classifying other defects. According to the experiments, the system can classify the defect types for two classes (acceptable and unacceptable types) and five classes as 89% and 71% of accuracy, respectively.

show abstract

PCB surface defect fast detection method based on attention and multi-source fusion

Zhao

Liang

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

Solder Joint Defect Detection Based on Image Segmentation and Deep Learning

Cited by 6 publications

References 3 publications

PCB Soldering Defect Inspection Using Multitask Learning under Low Data Regimes

PCB Soldering Defect Inspection Using Multitask Learning under Low Data Regimes

Defect Solder Classification in Print Circuit Boards using Machine Learning

PCB surface defect fast detection method based on attention and multi-source fusion

Contact Info

Product

Resources

About