Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

Sathiaseelan, Mukhil Azhagan Mallaiyan; Paradis, Olivia P.; Taheri, Shayan; Asadizanjani, Navid

doi:10.3390/cryptography5010009

Cited by 29 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While the algorithm is not perfect, this can successfully be utilized as a region proposal block for PCB Component detection neural networks using ideas from [34] [35]. This is our current focus and we hope to present more related work in the future [11]. In addition, borrowing ideas from graph-cuts, active contours and other segmentation methods to improve the current segmentation accuracy is also a potential area of focus.…”

Section: Discussionmentioning

confidence: 99%

“…We also present a novel method of automatic component detection, localization and segmentation in PCBs called the Electronic Component Segmentation algorithm (EC-Seg) that is both scale invariant and rotation invariant. EC-Seg could also be successfully used as a region proposal stage for neural networks [11]. The rest of the manuscript is organized as follows: in Section II we discuss related works, followed in Sec.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Sathiaseelan

Agrawal

Vutukuru

et al. 2021

International Symposium for Testing and Failure Analysis

Self Cite

View full text Add to dashboard Cite

PCB Assurance currently relies on manual physical inspection, which is time consuming, expensive and prone to error. In this study, we propose a novel automated segmentation algorithm to detect and isolate PCB components from the boards called EC-Seg. Segmentation and component localization is a vital preprocessing step in component identification, component authentication, as well as in detecting logos and text markings in components. EC-Seg is an efficient method to automate Quality assurance tool-chains and also to aid Bill of Material Extraction in PCBs. Finally, EC-Seg can be used as a Region proposal algorithm for object detection networks to detect and classify microelectronic components, and also to perform sensor fusion with X-Rays to aid in artifact removal in PCB X-Ray tomography. Index Terms—PCB Hardware Assurance, Component Segmentation, Component detection, AutoBoM, Physical Inspection, Visual inspection, Counterfeit detection

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Sathiaseelan

Agrawal

Vutukuru

et al. 2021

International Symposium for Testing and Failure Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…The systematic overview of a reverse engineering process is shown in Figure 37 [119]. Possible data samples for a reverse engineering-based detection and recognition system are provided in Figure 38 [121]. Figure 39 displays a component detection system using deep learning for reverse engineering [121].…”

Section: Cyber Attacks and Defenses In Medical Domainmentioning

confidence: 99%

“…Possible data samples for a reverse engineering-based detection and recognition system are provided in Figure 38 [121]. Figure 39 displays a component detection system using deep learning for reverse engineering [121]. In summary, The Internet connectivity of medical devices and inclusion of more computing elements in the network introduces various security issues that can produce malicious medical errors.…”

Section: Cyber Attacks and Defenses In Medical Domainmentioning

confidence: 99%

An Overview of Medical Electronic Hardware Security and Emerging Solutions

Taheri

Asadizanjani

2022

Electronics

Self Cite

View full text Add to dashboard Cite

Electronic healthcare technology is widespread around the world and creates massive potential to improve clinical outcomes and transform care delivery. However, there are increasing concerns with respect to the cyber vulnerabilities of medical tools, malicious medical errors, and security attacks on healthcare data and devices. Increased connectivity to existing computer networks has exposed the medical devices/systems and their communicating data to new cybersecurity vulnerabilities. Adversaries leverage the state-of-the-art technologies, in particular artificial intelligence and computer vision-based techniques, in order to launch stronger and more detrimental attacks on the medical targets. The medical domain is an attractive area for cybercrimes for two fundamental reasons: (a) it is rich resource of valuable and sensitive data; and (b) its protection and defensive mechanisms are weak and ineffective. The attacks aim to steal health information from the patients, manipulate the medical information and queries, maliciously change the medical diagnosis, decisions, and prescriptions, etc. A successful attack in the medical domain causes serious damage to the patient’s health and even death. Therefore, cybersecurity is critical to patient safety and every aspect of the medical domain, while it has not been studied sufficiently. To tackle this problem, new human- and computer-based countermeasures are researched and proposed for medical attacks using the most effective software and hardware technologies, such as artificial intelligence and computer vision. This review provides insights to the novel and existing solutions in the literature that mitigate cyber risks, errors, damage, and threats in the medical domain. We have performed a scoping review analyzing the four major elements in this area (in order from a medical perspective): (1) medical errors; (2) security weaknesses of medical devices at software- and hardware-level; (3) artificial intelligence and/or computer vision in medical applications; and (4) cyber attacks and defenses in the medical domain. Meanwhile, artificial intelligence and computer vision are key topics in this review and their usage in all these four elements are discussed. The review outcome delivers the solutions through building and evaluating the connections among these elements in order to serve as a beneficial guideline for medical electronic hardware security.

show abstract

“…In [16] the authors talk about some challenges in the field of PCB detection due to the various component's shape and size. Therefore, there are some more challenges to solve and collaboration needed from the hardware assurance and security community for automated, accurate, and scalable PCB component detection.…”

Section: Pcb Defect Detection Using Deep Learningmentioning

confidence: 99%

SMD Detection and Classification Using YOLO Network Based on Robust Data Preprocessing and Augmentation Techniques

Fabrice¹,

Lee²

2021

J Multimed Inf Syst

View full text Add to dashboard Cite

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

Cited by 29 publications

References 33 publications

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

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

An Overview of Medical Electronic Hardware Security and Emerging Solutions

SMD Detection and Classification Using YOLO Network Based on Robust Data Preprocessing and Augmentation Techniques

Contact Info

Product

Resources

About