Logo Classification

Logo Classification

Description This study examines various methods for automating the recognition and categorization of logos found on printed circuit boards (PCBs) and integrated circuits (ICs). It evaluates the effectiveness of machine learning and computer vision techniques, along with neural network algorithms. The authors describe the process of creating a comprehensive dataset for machine learning, achieved by gathering diverse logo variations from PCBs and utilizing data augmentation methods. In addition to tackling the challenges associated with image classification, the research presents the outcomes of experiments using Random Forest classifiers, Bag of Visual Words (BoVW) employing SIFT and ORB, Fully Connected Neural Networks (FCN), and Convolutional Neural Network (CNN) architectures. Furthermore, it delves into scenarios where the algorithms may encounter difficulties and highlights potential avenues for future research in the realms of PCB logo recognition, component verification, and counterfeit detection.
Downloads Logo Classification
Citations
×

Citation Formats

Text Format BibTeX
Mukhil Azhagan Mallaiyan Sathiaseelan, Olivia P. Paradis, Rajat Rai, Suryaprakash Vasudev Pandurangi, Manoj Yasaswi Vutukuru, Shayan Taheri, Navid Asadizanjani; October 31–November 4, 2021. "Logo Classification and Data Augmentation Techniques for PCB Assurance and Counterfeit Detection." Proceedings of the ISTFA 2021. ISTFA 2021: Conference Proceedings from the 47th International Symposium for Testing and Failure Analysis. Phoenix, Arizona, USA. (pp. pp. 12-19). ASM. https://doi.org/10.31399/asm.cp.istfa2021p0012 @proceedings{10.31399/asm.cp.istfa2021p0012, author = {Sathiaseelan, Mukhil Azhagan Mallaiyan and Paradis, Olivia P. and Rai, Rajat and Pandurangi, Suryaprakash Vasudev and Vutukuru, Manoj Yasaswi and Taheri, Shayan and Asadizanjani, Navid}, title = "{Logo Classification and Data Augmentation Techniques for PCB Assurance and Counterfeit Detection}", volume = {ISTFA 2021: Conference Proceedings from the 47th International Symposium for Testing and Failure Analysis}, series = {International Symposium for Testing and Failure Analysis}, pages = {12-19}, year = {2021}, month = {10}, abstract = "{This paper evaluates several approaches for automating the identification and classification of logos on printed circuit boards (PCBs) and ICs. It assesses machine learning and computer vision techniques as well as neural network algorithms. It explains how the authors created a representative dataset for machine learning by collecting variants of logos from PCBs and by applying data augmentation techniques. Besides addressing the challenges of image classification, the paper presents the results of experiments using Random Forest classifiers, Bag of Visual Words (BoVW) based on SIFT and ORB Fully Connected Neural Networks (FCN), and Convolutional Neural Network (CNN) architectures. It also discusses edge cases where the algorithms are prone to fail and where potential opportunities exist for future work in PCB logo identification, component authentication, and counterfeit detection. The code for the algorithms along with the dataset incorporating 18 classes of logos and more than 14,000 images is available at this link: https://www.trusthub.org/#/data.}", doi = {10.31399/asm.cp.istfa2021p0012}, url = {https://doi.org/10.31399/asm.cp.istfa2021p0012}, eprint = {https://dl.asminternational.org/istfa/proceedingspdf/ISTFA2021/84215/12/607162/istfa2021p0012.pdf}, }