Printed circuit board defect detection using mathematical morphology and MATLAB image processing tools

Abstract

various concentrated work on detection of defects on printed circuit boards (PCBs) have been done, but it is also crucial to classify these defects in order to analyze and identify the root causes of the defects. This project is aimed in detecting and classifying the defects on bare single layer PCBs by introducing a hybrid algorithm by combining the research done by Heriansyah et al [1] and Khalid [2]. This project proposes a PCB defect detection and classification system using a morphological image segmentation algorithm [1] and simple the image processing theories [2]. Based on initial studies, some PCB defects can only exist in certain groups. Thus, it is obvious that the image processing algorithm could be improved by applying a segmentation exercise. This project uses template and test images of single layer, bare, grayscale computer generated PCBs. The research improves Khalid [2] work by increasing the number of defect categories from 5 to 7, with each category classifying a minimum of 1 to a maximum 4 different types of defects and a total of 13 out of 14 defects were classified.

CNN‐based reference comparison method for classifying bare PCB defects

“…As well as save time, the use of case library can also constantly be updated to meet actual demand. Indera Putera and Ibrahim [9] combined the research done in [10] and [11] and introduced a hybrid algorithm to detect and classify defects on exposed single‐layer PCBs. The project proposes a PCB defect detection and classification system that uses morphological image segmentation algorithms and simple image processing theory.…”

MATLAB based defect detection and classification of printed circuit board

“…Any anomalies between Template and Test Image are declared as defects. Indera Putera [1] classified these defects into seven groups.…”

“…Thus an automation inspection system is highly desirable. 'MATLAB Based Defect Detection And Classification of Printed Circuit Board' seeks to improve the classification of defects by an algorithm developed by Indera Putera [1]. From seven groups, it is observed that several groups contain more than one defect each.…”

Automatic Misalignment Defects Detection Correction in PCB using SURF (Speed up Robust Features) Technique

“…Indera Putera et al [2] proposed a methodology that is modification of Khalid's method by providing the seven groups instead of five. In this process produced twenty new images with the help of four patterns by combining the image processing & segmentation algorithm.…”