Fairness measures for biometric quality assessment
- URL: http://arxiv.org/abs/2408.11392v1
- Date: Wed, 21 Aug 2024 07:37:19 GMT
- Title: Fairness measures for biometric quality assessment
- Authors: André Dörsch, Torsten Schlett, Peter Munch, Christian Rathgeb, Christoph Busch,
- Abstract summary: Quality assessment algorithms measure the quality of a captured biometric sample.
It is essential to only process samples of sufficient quality and discard samples of low-quality.
Proposed measures, could be used as potential candidates for an upcoming standard in this important field.
- Score: 6.051899179464574
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Quality assessment algorithms measure the quality of a captured biometric sample. Since the sample quality strongly affects the recognition performance of a biometric system, it is essential to only process samples of sufficient quality and discard samples of low-quality. Even though quality assessment algorithms are not intended to yield very different quality scores across demographic groups, quality score discrepancies are possible, resulting in different discard ratios. To ensure that quality assessment algorithms do not take demographic characteristics into account when assessing sample quality and consequently to ensure that the quality algorithms perform equally for all individuals, it is crucial to develop a fairness measure. In this work we propose and compare multiple fairness measures for evaluating quality components across demographic groups. Proposed measures, could be used as potential candidates for an upcoming standard in this important field.
Related papers
- Multi-Facet Counterfactual Learning for Content Quality Evaluation [48.73583736357489]
We propose a framework for efficiently constructing evaluators that perceive multiple facets of content quality evaluation.
We leverage a joint training strategy based on contrastive learning and supervised learning to enable the evaluator to distinguish between different quality facets.
arXiv Detail & Related papers (2024-10-10T08:04:10Z) - A Fuzzy Logic-Based Quality Model For Identifying Microservices With Low Maintainability [0.0]
This paper proposes a hierarchical quality model based on fuzzy logic to measure and evaluate the maintainability of MSAs.
We use a fuzzification technique to transform crisp values of code metrics into fuzzy levels and apply them as inputs to our quality model.
arXiv Detail & Related papers (2024-06-20T16:53:37Z) - A Quality Aware Sample-to-Sample Comparison for Face Recognition [13.96448286983864]
This work integrates a quality-aware learning process at the sample level into the classification training paradigm (QAFace)
Our method adaptively finds and assigns more attention to the recognizable low-quality samples in the training datasets.
arXiv Detail & Related papers (2023-06-06T20:28:04Z) - Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement [55.8106019031768]
There is a growing consensus in the research community that the optimization of low-light image enhancement approaches should be guided by the visual quality perceived by end users.
We propose a gap-closing framework for assessing subjective and objective quality systematically.
We validate the effectiveness of our proposed framework through both the accuracy of quality prediction and the perceptual quality of image enhancement.
arXiv Detail & Related papers (2023-02-22T15:57:03Z) - Advanced Image Quality Assessment for Hand- and Fingervein Biometrics [5.218882272051637]
Natural Scene Statistics commonly used in non-reference image quality measures are proposed as biometric quality indicators for vasculature images.
The experiments were conducted on a total of 13 publicly available finger and hand vein datasets.
arXiv Detail & Related papers (2023-02-20T13:35:28Z) - Fingerprint Image-Quality Estimation and its Application to
Multialgorithm Verification [56.128200319868526]
Signal-quality awareness has been found to increase recognition rates and to support decisions in multisensor environments significantly.
Here, we study the orientation tensor of fingerprint images to quantify signal impairments, such as noise, lack of structure, blur, with the help of symmetry descriptors.
The quantitative results favor quality awareness under all aspects, boosting recognition rates and fusing differently skilled experts efficiently as well as effectively.
arXiv Detail & Related papers (2022-11-24T12:17:49Z) - Quality Measures in Biometric Systems [67.6699940572256]
Quality is a critical issue in security, especially in adverse scenarios involving surveillance cameras, forensics, portable devices, or remote access through the Internet.
This article analyzes what factors negatively impact biometric quality, how to overcome them, and how to incorporate quality measures into biometric systems.
arXiv Detail & Related papers (2021-11-17T13:28:07Z) - Measuring Fairness Under Unawareness of Sensitive Attributes: A
Quantification-Based Approach [131.20444904674494]
We tackle the problem of measuring group fairness under unawareness of sensitive attributes.
We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
arXiv Detail & Related papers (2021-09-17T13:45:46Z) - Towards objectively evaluating the quality of generated medical
summaries [70.09940409175998]
We ask evaluators to count facts, computing precision, recall, f-score, and accuracy from the raw counts.
We apply this to the task of medical report summarisation, where measuring objective quality and accuracy is of paramount importance.
arXiv Detail & Related papers (2021-04-09T15:02:56Z) - Face Quality Estimation and Its Correlation to Demographic and
Non-Demographic Bias in Face Recognition [15.431761867166]
Face quality assessment aims at estimating the utility of a face image for the purpose of recognition.
Currently, the high performance of these face recognition systems come with the cost of a strong bias against demographic and non-demographic sub-groups.
Recent work has shown that face quality assessment algorithms should adapt to the deployed face recognition system, in order to achieve highly accurate and robust quality estimations.
arXiv Detail & Related papers (2020-04-02T14:19:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.