scholarly journals Logo Classification and Data Augmentation Techniques for PCB Assurance and Counterfeit Detection

2021 ◽  
Author(s):  
Mukhil Azhagan Mallaiyan Sathiaseelan ◽  
Olivia P. Paradis ◽  
Rajat Rai ◽  
Suryaprakash Vasudev Pandurangi ◽  
Manoj Yasaswi Vutukuru ◽  
...  
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Bag Of Visual Words ◽  
Visual Words ◽  
Bill Of Materials ◽  
Augmentation Techniques ◽  
Classification Tasks ◽  
Index Terms ◽  
Fully Connected ◽  
Future Work

Abstract In this manuscript, we present our work on Logo classification in PCBs for Hardware assurance purposes. Identifying and classifying logos have important uses for text detection, component authentication and counterfeit detection. Since PCB assurance faces the lack of a representative dataset for classification and detection tasks, we collect different variants of logos from PCBs and present data augmentation techniques to create the necessary data to perform machine learning. In addition to exploring the challenges for image classification tasks in PCBs, we present experiments using Random Forest classifiers, Bag of Visual Words (BoVW) using SIFT and ORB Fully Connected Neural Networks (FCN) and Convolutional Neural Network (CNN) architectures. We present results and also a discussion on the edge cases where our algorithms fail including the potential for future work in PCB logo detection. The code for the algorithms along with the dataset that includes 18 classes of logos with 14000+ images is provided at this link: https://www.trusthub.org/#/data Index Terms—AutoBoM, Logo classification, Data augmentation, Bill of materials, PCB Assurance, Hardware Assurance, Counterfeit avoidance

scholarly journals Data Augmentation and Feature Selection for Automatic Model Recommendation in Computational Physics

2021 ◽  
Vol 26 (1) ◽  
pp. 17
Author(s):  
Thomas Daniel ◽  
Fabien Casenave ◽  
Nissrine Akkari ◽  
David Ryckelynck
Keyword(s):  
Feature Selection ◽  
Data Augmentation ◽  
Classification Problem ◽  
Computational Physics ◽  
Training Data ◽  
Multilayer Perceptrons ◽  
Augmentation Techniques ◽  
Physical Fields ◽  
Classification Tasks ◽  
Selection Of

Classification algorithms have recently found applications in computational physics for the selection of numerical methods or models adapted to the environment and the state of the physical system. For such classification tasks, labeled training data come from numerical simulations and generally correspond to physical fields discretized on a mesh. Three challenging difficulties arise: the lack of training data, their high dimensionality, and the non-applicability of common data augmentation techniques to physics data. This article introduces two algorithms to address these issues: one for dimensionality reduction via feature selection, and one for data augmentation. These algorithms are combined with a wide variety of classifiers for their evaluation. When combined with a stacking ensemble made of six multilayer perceptrons and a ridge logistic regression, they enable reaching an accuracy of 90% on our classification problem for nonlinear structural mechanics.

scholarly journals Detection and Counting of Animals in Camera-Trap Images using Faster R-Cnn and Data Augmentation Techniques

2020 ◽  
Vol 9 (5) ◽  
pp. 931-943
Keyword(s):  
Data Augmentation ◽  
Camera Trap ◽  
Camera Traps ◽  
Counting Task ◽  
Original Dataset ◽  
Detection And Counting ◽  
Augmentation Techniques ◽  
The One ◽  
Future Work

Camera traps are used to recover images of animals in their habitats to help in the conservation of fauna. Millions of images are captured by camera traps and extracting information from these data delays and consumes enough resources so sometimes millions of images cannot be used due to lack of resources. That is why researchers have proposed solution approaches using Convolutional Neural Networks (CNNs) and object detection models to be able to automate the retrieval of information from these images. We used Faster R-CNN and data augmentation techniques on Gold Standard Snapshot Serengeti Dataset to detect animals in images and count them. The performances of the two models (the one trained on the original dataset and the one trained on the augmented dataset) were compared to show the importance of having more data for this task. Using the augmented dataset, we trained our model which reached an accuracy of 98.26% for classification of the proposed regions, an accuracy of 79.55% for counting the species present on the images and a mAP of 95.3%. For future work, the model can be trained to recognize the actions and characteristics of animals and tuned to be more efficient for counting task.

scholarly journals COVID-19 detection using cough sound analysis and deep learning algorithms

2021 ◽  
pp. 1-11
Author(s):  
Sunil Rao ◽  
Vivek Narayanaswamy ◽  
Michael Esposito ◽  
Jayaraman J. Thiagarajan ◽  
Andreas Spanias
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Data Augmentation ◽  
Learning Algorithms ◽  
Audio Signal ◽  
Lottery Ticket ◽  
Non Invasive ◽  
Performance Gains ◽  
Fully Connected ◽  
The Impact

Reliable and rapid non-invasive testing has become essential for COVID-19 diagnosis and tracking statistics. Recent studies motivate the use of modern machine learning (ML) and deep learning (DL) tools that utilize features of coughing sounds for COVID-19 diagnosis. In this paper, we describe system designs that we developed for COVID-19 cough detection with the long-term objective of embedding them in a testing device. More specifically, we use log-mel spectrogram features extracted from the coughing audio signal and design a series of customized deep learning algorithms to develop fast and automated diagnosis tools for COVID-19 detection. We first explore the use of a deep neural network with fully connected layers. Additionally, we investigate prospects of efficient implementation by examining the impact on the detection performance by pruning the fully connected neural network based on the Lottery Ticket Hypothesis (LTH) optimization process. In general, pruned neural networks have been shown to provide similar performance gains to that of unpruned networks with reduced computational complexity in a variety of signal processing applications. Finally, we investigate the use of convolutional neural network architectures and in particular the VGG-13 architecture which we tune specifically for this application. Our results show that a unique ensembling of the VGG-13 architecture trained using a combination of binary cross entropy and focal losses with data augmentation significantly outperforms the fully connected networks and other recently proposed baselines on the DiCOVA 2021 COVID-19 cough audio dataset. Our customized VGG-13 model achieves an average validation AUROC of 82.23% and a test AUROC of 78.3% at a sensitivity of 80.49%.

Data augmentation techniques for transfer learning improvement in drill wear classification using convolutional neural network

2019 ◽  
Vol 28 (1) ◽  
pp. 3-12
Author(s):  
Jarosław Kurek ◽  
Joanna Aleksiejuk-Gawron ◽  
Izabella Antoniuk ◽  
Jarosław Górski ◽  
Albina Jegorowa ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Good Condition ◽  
Training Data ◽  
Time Data ◽  
Learning Improvement ◽  
Original Dataset ◽  
Augmentation Techniques

This paper presents an improved method for recognizing the drill state on the basis of hole images drilled in a laminated chipboard, using convolutional neural network (CNN) and data augmentation techniques. Three classes were used to describe the drill state: red -- for drill that is worn out and should be replaced, yellow -- for state in which the system should send a warning to the operator, indicating that this element should be checked manually, and green -- denoting the drill that is still in good condition, which allows for further use in the production process. The presented method combines the advantages of transfer learning and data augmentation methods to improve the accuracy of the received evaluations. In contrast to the classical deep learning methods, transfer learning requires much smaller training data sets to achieve acceptable results. At the same time, data augmentation customized for drill wear recognition makes it possible to expand the original dataset and to improve the overall accuracy. The experiments performed have confirmed the suitability of the presented approach to accurate class recognition in the given problem, even while using a small original dataset.

Deep Learning for Printed Mottle Defect Grading

2020 ◽  
Vol 2020 (8) ◽  
pp. 184-1-184-9
Author(s):  
Jianhang Chen ◽  
Qian Lin ◽  
Jan P. Allebach
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Error Rate ◽  
Data Augmentation ◽  
Image Features ◽  
Learning Method ◽  
Single Image ◽  
Original Dataset ◽  
Fully Connected ◽  
First Time

In this paper, we propose a new method for printed mottle defect grading. By training the data scanned from printed images, our deep learning method based on a Convolutional Neural Network (CNN) can classify various images with different mottle defect levels. Different from traditional methods to extract the image features, our method utilizes a CNN for the first time to extract the features automatically without manual feature design. Different data augmentation methods such as rotation, flip, zoom, and shift are also applied to the original dataset. The final network is trained by transfer learning using the ResNet-34 network pretrained on the ImageNet dataset connected with fully connected layers. The experimental results show that our approach leads to a 13.16% error rate in the T dataset, which is a dataset with a single image content, and a 20.73% error rate in a combined dataset with different contents.

scholarly journals Image Segmentation Using Encoder-Decoder with Deformable Convolutions

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1570
Author(s):  
Andreea Gurita ◽  
Irina Georgiana Mocanu
Keyword(s):  
Neural Network ◽  
Image Analysis ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Real Life ◽  
Semantic Segmentation ◽  
Essential Step ◽  
Augmentation Techniques ◽  
Made In

Image segmentation is an essential step in image analysis that brings meaning to the pixels in the image. Nevertheless, it is also a difficult task due to the lack of a general suited approach to this problem and the use of real-life pictures that can suffer from noise or object obstruction. This paper proposes an architecture for semantic segmentation using a convolutional neural network based on the Xception model, which was previously used for classification. Different experiments were made in order to find the best performances of the model (eg. different resolution and depth of the network and data augmentation techniques were applied). Additionally, the network was improved by adding a deformable convolution module. The proposed architecture obtained a 76.8 mean IoU on the Pascal VOC 2012 dataset and 58.1 on the Cityscapes dataset. It outperforms SegNet and U-Net networks, both networks having considerably more parameters and also a higher inference time.

Sign in / Sign up

Export Citation Format

Share Document