TinySiamese Network for Biometric Analysis
Islem Jarraya, Tarek M. Hamdani, Habib Chabchoub, Adel M. Alimi

TL;DR
TinySiamese is a lightweight neural network that efficiently performs biometric verification by using a pre-trained CNN and a small, fast Siamese network, suitable for low-resource devices with minimal accuracy loss.
Contribution
The paper introduces TinySiamese, a compact Siamese network that reduces training and matching time while maintaining high accuracy, enabling biometric verification on low-power hardware.
Findings
Matching time decreased by 76.78% using TinySiamese.
Training time reduced by approximately 93.14%.
Accuracy improved or comparable to standard Siamese networks.
Abstract
Biometric recognition is the process of verifying or classifying human characteristics in images or videos. It is a complex task that requires machine learning algorithms, including convolutional neural networks (CNNs) and Siamese networks. Besides, there are several limitations to consider when using these algorithms for image verification and classification tasks. In fact, training may be computationally intensive, requiring specialized hardware and significant computational resources to train and deploy. Moreover, it necessitates a large amount of labeled data, which can be time-consuming and costly to obtain. The main advantage of the proposed TinySiamese compared to the standard Siamese is that it does not require the whole CNN for training. In fact, using a pre-trained CNN as a feature extractor and the TinySiamese to learn the extracted features gave almost the same performance…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGait Recognition and Analysis · Biometric Identification and Security · Video Surveillance and Tracking Methods
