Multi-band PCA based ear recognition technique

Zarachoff, Matthew; Sheikh-Akbari, Akbar; Monekosso, Dorothy

doi:10.1007/s11042-022-12905-0

Cited by 5 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zarachoff et al [18] used a multi-band two-dimensional PCA(2D-MBPCA) technique for ear recognition. This technique divides the given input image into multiple bands, and standard PCA is applied to each band to generate eigenvectors for feature matching.…”

Section: Related Workmentioning

confidence: 99%

Ear Recognition Using Rank Level Fusion of Classifiers Outputs

Resmi

Joseph²,

Raju

et al. 2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

An individual's authentication plays a vital role in our daily life. In the last decade, biometric-based authentication has become more prevalent than traditional approaches like passwords and pins. Ear recognition has gained attention in the biometric community in recent years. Researchers defined several features for the identification of a person from ear image. The features play a vital role in the success of classification models. This paper considers an ensemble of features for designing a new classification model. The features are assessed in isolation as well as through feature-level fusion. Subsequently, a rank-level fusion for classification is introduced. The experiments are conducted on both constrained and unconstrained ear datasets. The results are promising and open up new possibilities in machine learning-based ear recognition

show abstract

Section: Related Workmentioning

confidence: 99%

Ear Recognition Using Rank Level Fusion of Classifiers Outputs

Resmi

Joseph²,

Raju

et al. 2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

“…Ear recognition technologies present multiple advantages, such as capturing ear images from afar, a feature beneficial for security and surveillance applications [7]. Additionally, the ear's morphology remains largely stable throughout a person's lifetime and is not influenced by facial expressions, making it a viable option for non-contact biometric identification [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of VGG-16 and ResNet-50 for Occluded Ear Recognition

Tey,

Chong,

Chong

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Occluded ear recognition is a challenging task in biometric systems due to the presence of occlusions that can hinder accurate identification. There is still a research gap in enhancing the robustness of deep learning to handle severities of occlusions with different datasets. This research focuses on developing a robust occluded ear recognition system by implementing fine-tuning techniques on three popular pre-trained deep learning models, Residual Neural Network (ResNet-50), Visual Geometry Group (VGG-16), and EfficientNet. The system is evaluated on two manually occluded ear datasets, which are the AMI ear dataset and the IITD ear dataset. The experiment results showed the fine-tuned ResNet-50 model performs better than the fine-tuned VGG-16 model. The results indicate that the model's ability to accurately predict the classes or labels decreases as more data is occluded. Higher occlusion rates lead to a loss of important information, making it more challenging for the model to distinguish between different patterns and make accurate predictions. According to the findings, the amount of occlusion influenced the identification accuracy and worsened as the occlusion became larger. In the future, ear recognition systems will likely continue to improve in accuracy and be adopted by a wider range of organizations and industries. They may also be integrated with other biometric technologies and used for personalization purposes. However, ethical considerations related to the use of ear recognition systems will also need to be addressed.

show abstract