Abstract:
Fisheye cameras present a challenge for face recognition due to their wide-angle perspective and image distortion. This paper introduces a novel approach to enhancing tra...Show MoreMetadata
Abstract:
Fisheye cameras present a challenge for face recognition due to their wide-angle perspective and image distortion. This paper introduces a novel approach to enhancing training data for fisheye-based face recognition without requiring image calibration. We employ five image-remapping transformations to diversify and expand the training dataset and evaluate the effectiveness of this approach using deep learning networks: HRNetV2 and ResNet50. The results demonstrate significant improvements in classification accuracy when utilizing authentic fisheye facial data. Specifically, HRNetV2 exhibits an increase of 30.2%, while ResNet50’s performance improves by 11.8% compared to their respective baseline performances. This study presents a fresh method for refining face recognition in fisheye camera scenarios, thereby extending its potential for real-world applications.
Date of Conference: 10-13 October 2023
Date Added to IEEE Xplore: 16 November 2023
ISBN Information:
ISSN Information:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Data Augmentation ,
- Face Recognition ,
- Deep Learning ,
- Training Dataset ,
- Classification Accuracy ,
- Image Distortion ,
- Improve Classification Accuracy ,
- Fisheye Lens ,
- Neural Network ,
- Convolutional Neural Network ,
- Test Dataset ,
- Image Classification ,
- Generative Adversarial Networks ,
- Recognition Accuracy ,
- Face Images ,
- Z Coordinates ,
- Normal Images ,
- Image Correction ,
- Normal Dataset ,
- Data Augmentation Methods ,
- ResNet-50 Model ,
- Conventional Camera ,
- Need For Correction ,
- Margin Parameter ,
- Low-resolution Feature ,
- Backbone Model ,
- Multi-scale Fusion ,
- Degree Of Distortion ,
- Cross-entropy Loss
- Author Keywords
Contents Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Data Augmentation ,
- Face Recognition ,
- Deep Learning ,
- Training Dataset ,
- Classification Accuracy ,
- Image Distortion ,
- Improve Classification Accuracy ,
- Fisheye Lens ,
- Neural Network ,
- Convolutional Neural Network ,
- Test Dataset ,
- Image Classification ,
- Generative Adversarial Networks ,
- Recognition Accuracy ,
- Face Images ,
- Z Coordinates ,
- Normal Images ,
- Image Correction ,
- Normal Dataset ,
- Data Augmentation Methods ,
- ResNet-50 Model ,
- Conventional Camera ,
- Need For Correction ,
- Margin Parameter ,
- Low-resolution Feature ,
- Backbone Model ,
- Multi-scale Fusion ,
- Degree Of Distortion ,
- Cross-entropy Loss
- Author Keywords
