Handcrafted versus CNN Features for Ear Recognition

Alshazly, Hammam; Linse, Christoph; Barth, Erhardt; Martinetz, Thomas

doi:10.3390/sym11121493

Cited by 47 publications

(30 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The extracted feature vectors are then classified based on the cosine similarity metric. The reported results indicated superior performances for recognition models utilizing CNN features, see also [41], [42].…”

Section: Related Workmentioning

confidence: 76%

See 1 more Smart Citation

Deep Convolutional Neural Networks for Unconstrained Ear Recognition

et al. 2020

Self Cite

View full text Add to dashboard Cite

This paper employs state-of-the-art Deep Convolutional Neural Networks (CNNs), namely AlexNet, VGGNet, Inception, ResNet and ResNeXt in a first experimental study of ear recognition on the unconstrained EarVN1.0 dataset. As the dataset size is still insufficient to train deep CNNs from scratch, we utilize transfer learning and propose different domain adaptation strategies. The experiments show that our networks, which are fine-tuned using custom-sized inputs determined specifically for each CNN architecture, obtain state-of-the-art recognition performance where a single ResNeXt101 model achieves a rank-1 recognition accuracy of 93.45%. Moreover, we achieve the best rank-1 recognition accuracy of 95.85% using an ensemble of fine-tuned ResNeXt101 models. In order to explain the performance differences between models and make our results more interpretable, we employ the t-SNE algorithm to explore and visualize the learned features. Feature visualizations show well-separated clusters representing ear images of the different subjects. This indicates that discriminative and ear-specific features are learned when applying our proposed learning strategies.

show abstract

Section: Related Workmentioning

confidence: 76%

“…AlexNet [9] is considered a deep CNN architecture compared with previous CNNs such as LeNet-5 [49], and is the winner of the 2012 ImageNet Large Scale Visual Recognition Challenge (ILSVRC-2012) for image classification [50]. As a result, AlexNet has been applied to numerous recognition tasks including ear recognition [39], [51], [52], [42].…”

Section: A Alexnetmentioning

confidence: 99%

Deep Convolutional Neural Networks for Unconstrained Ear Recognition

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Transfer learning is a method in deep learning, which has become quite popular in the computer vision community because it might significantly boost recognition performance ( Alshazly et al, 2019b ). The idea bases on the transferability of network weights between related image recognition tasks and relies on the universal validity of the visual filters learned during training.…”

Section: Methodsmentioning

confidence: 99%

COVID-Nets: deep CNN architectures for detecting COVID-19 using chest CT scans

Alshazly

Linse

Abdalla

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

In this paper we propose two novel deep convolutional network architectures, CovidResNet and CovidDenseNet, to diagnose COVID-19 based on CT images. The models enable transfer learning between different architectures, which might significantly boost the diagnostic performance. Whereas novel architectures usually suffer from the lack of pretrained weights, our proposed models can be partly initialized with larger baseline models like ResNet50 and DenseNet121, which is attractive because of the abundance of public repositories. The architectures are utilized in a first experimental study on the SARS-CoV-2 CT-scan dataset, which contains 4173 CT images for 210 subjects structured in a subject-wise manner into three different classes. The models differentiate between COVID-19, non-COVID-19 viral pneumonia, and healthy samples. We also investigate their performance under three binary classification scenarios where we distinguish COVID-19 from healthy, COVID-19 from non-COVID-19 viral pneumonia, and non-COVID-19 from healthy, respectively. Our proposed models achieve up to 93.87% accuracy, 99.13% precision, 92.49% sensitivity, 97.73% specificity, 95.70% F1-score, and 96.80% AUC score for binary classification, and up to 83.89% accuracy, 80.36% precision, 82.04% sensitivity, 92.07% specificity, 81.05% F1-score, and 94.20% AUC score for the three-class classification tasks. We also validated our models on the COVID19-CT dataset to differentiate COVID-19 and other non-COVID-19 viral infections, and our CovidDenseNet model achieved the best performance with 81.77% accuracy, 79.05% precision, 84.69% sensitivity, 79.05% specificity, 81.77% F1-score, and 87.50% AUC score. The experimental results reveal the effectiveness of the proposed networks in automated COVID-19 detection where they outperform standard models on the considered datasets while being more efficient.

show abstract

“…The input sequences to the model can be raw pixel values or features (hand‐crafted or machine‐learned) extracted using a sliding window protocol. A number of recent studies [101–103], validated the superiority of machine‐learned features over hand‐engineered features (and raw pixel values). We, therefore, employ a CNN as a feature extractor.…”

Section: Methodsmentioning

confidence: 99%