Related Experiment Video
Updated: Feb 9, 2026
06:58
Behavioral Tasks for Examining Identity Recognition In Mice
Published on: February 7, 2025
1.2K
Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms
P Jonathon Phillips1, Amy N Yates2, Ying Hu3
1Information Access Division, National Institute of Standards and Technology, Gaithersburg, MD 20899; jonathon@nist.gov.
Summary
Human and machine collaboration significantly improves face identification accuracy in forensic science. Combining expert judgments and advanced algorithms offers a clear path to minimizing identification errors and their consequences.
Area of Science:
- Forensic Science
- Computer Vision
- Human-Computer Interaction
Background:
- Face identification is critical in forensic applications, yet systematic accuracy tests for examiners are rare.
- Minimizing identification errors is crucial due to their significant social and personal consequences.
- The optimal approach to face identification accuracy—human, machine, or collaborative—remains an open question.
Purpose of the Study:
- To comprehensively compare face identification accuracy between humans and machines.
- To evaluate the benefits of collaboration between human experts and between humans and machines.
- To establish an evidence-based strategy for maximizing face identification accuracy in forensic contexts.
Main Methods:
- A challenging face identification test was administered to forensic facial examiners, facial reviewers, superrecognizers, fingerprint examiners, and students.
- Four deep convolutional neural networks (DCNNs) developed between 2015-2017 were tested on the same identification task.
- Crowd-sourcing was used to fuse the judgments of multiple forensic facial examiners and compare fused performance with individual and algorithmic performance.
Main Results:
- Forensic specialists (examiners, reviewers, superrecognizers) outperformed students and fingerprint examiners.
- DCNNs performed within the range of human accuracy, with newer algorithms showing improved performance.
- Fused judgments from multiple examiners significantly enhanced accuracy and stabilized performance compared to individuals.
- Combining a single examiner with the best-performing algorithm surpassed the accuracy of two examiners.
Conclusions:
- Collaboration among human experts demonstrably improves face identification accuracy.
- Integrating machine algorithms, specifically DCNNs, with human expertise further boosts identification performance.
- These findings provide a roadmap for optimizing face identification in forensic applications through human-machine collaboration.
Related Concept Videos
02:07Improving Translational Accuracy
15.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.0K
02:07Improving Translational Accuracy
3.7K
3.7K
03:37Uncertainty in Measurement: Accuracy and Precision
103.1K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
103.1K
01:52Accuracy and Precision
15.6K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value. Highly accurate...
15.6K
01:12Trial and Error and Algorithm
429
A problem-solving strategy is a plan of action used to find a solution. Different strategies have distinct action plans. Trial and error involves trying different solutions until one works. For instance, to fix a broken printer, you might check ink levels, ensure the paper tray isn't jammed, and verify the printer's connection to your laptop. This method can be time-consuming but is commonly used. Thomas Edison, for example, used trial and error to find a suitable filament for the light...
429
01:28Accuracy, limits, and approximation
1.3K
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
1.3K