Intrinsic Property-Based Soft Biometric Classification Using Wavelet CNNs and LRP
Conference proceedings article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Abdullahi S.B.; Chamnongthai K.
Publisher: Society of Photo-optical Instrumentation Engineers
Publication year: 2025
Journal: Proceedings of SPIE (0277-786X)
Volume number: 13518
ISBN: 978-151068829-2
ISSN: 0277-786X
eISSN: 1996-756X
Languages: English-Great Britain (EN-GB)
Abstract
The rapid evolution of optical sensors has significantly impacted the field of soft biometrics, necessitating the development of adaptive automatic deep learning methods. Traditional deep-learning approaches for feature extraction and classification often struggle with biases related to sensor position and activity configuration. Recent advancements in deep learning have leveraged attribute representation-based transfer learning for effective biometrics identification. However, these methods are limited in identifying the most contributive features for classification tasks. This study proposes a novel approach to transform human activity features using the effective wavelet transform (eW), which minimizes sensor biases by converting activity features into a novel representation of intrinsic biometric properties. These features are then learned through a well-trained Wavelet Convolutional Neural Network (eWCNN). To interpret the eWCNN, we employ Layer-wise Relevance Propagation (LRP) to analyze the features and plot relevance scores. Our method outperforms existing state-of-the-art techniques, providing an interpretable solution for soft biometrics identification and classification. © 2025 SPIE.
Keywords
No matching items found.
Contact Information