Semantic Segmentation of a Printed Circuit Board for Component Recognition Based on Depth Images

Abstract

Locating and identifying the components mounted on a printed circuit board (PCB) based on machine vision is an important and challenging problem for automated PCB inspection and automated PCB recycling. In this paper, we propose a PCB semantic segmentation method based on depth images that segments and recognizes components in the PCB through pixel classification. The image training set for the PCB was automatically synthesized with graphic rendering. Based on a series of concentric circles centered at the given depth pixel, we extracted the depth difference features from the depth images in the training set to train a random forest pixel classifier. By using the constructed random forest pixel classifier, we performed semantic segmentation for the PCB to segment and recognize components in the PCB through pixel classification. Experiments on both synthetic and real test sets were conducted to verify the effectiveness of the proposed method. The experimental results demonstrate that our method can segment and recognize most of the components from a real depth image of the PCB. Our method is immune to illumination changes and can be implemented in parallel on a GPU.

Image-Based Detection of Modifications in Assembled PCBs with Deep Convolutional Autoencoders

“…Although these approaches were successful, they rely on controlled capture conditions, and only work for limited types of anomalies, found in unassembled boards. For assembled boards, a common strategy is using supervised training to produce a component detector [ 11 , 12 ]. The layout of the detected components can be compared to a reference, providing a way of detecting anomalies.…”

“…While we have the fraud detection scenario as our main motivation, this problem shares most characteristics with the image-based inspection of PCBs in general—a task for which several methods have been proposed in recent years. Some methods are used to detect defects in unassembled PCBs [ 6 , 7 , 8 , 9 , 10 ], where common anomalies are missing holes and open circuits, while other methods deal with assembled PCBs [ 3 , 11 , 12 ]. These methods are usually based on supervised machine learning, where a decision model is trained by observing samples with and without defects or anomalies.…”

EC-Seg: Electronic Component Segmentation for PCB Assurance and Counterfeit Avoidance

“…They propose two different methods of segmenting small SMDs like resistors, capacitors and large devices like ICs using a corner-based model fitting approach and Ridge based analysis of Distributions (RAD) respectively. Another semantic segmentation method for PCB recycling is explained in [28] which considers depth images of the PCBs and extract the components through a random forest pixel classifier.…”

Combined Use of 3D and HSI for the Classification of Printed Circuit Board Components

“…The segmentation of Through Hole Components (THCs) is part of [5] and is achieved by using a combination of RGB images and depth frames from a Microsoft Kinect sensor. A further study based also on depth frames obtained from the Microsoft Kinect sensor and pixel classification can be found in [6]. The studies mentioned here either focus on the segmentation of one type of component (e.g., SMDs or THCs) or are designed for inspection tasks.…”