An official website of the United States government
Deep learning models have demonstrated significant advantages over traditional algorithms in image processing tasks like object detection. However, a large amount of data are needed to train such deep networks, which limits their application to tasks such as biometric recognition that require more training samples for each class (i.e., each individual). Researchers developing such complex systems rely on real biometric data, which raises privacy concerns and is restricted by the availability of extensive, varied datasets. This paper proposes a generative adversarial network (GAN)-based solution to produce training data (palm images) for improved biometric (palmprint-based) recognition systems. We investigate the performance of the most recent StyleGAN models in generating a thorough contactless palm image dataset for application in biometric research. Training on publicly available H-PolyU and IIDT palmprint databases, a total of 4839 images were generated using StyleGAN models. SIFT (Scale-Invariant Feature Transform) was used to find uniqueness and features at different sizes and angles, which showed a similarity score of 16.12% with the most recent StyleGAN3-based model. For the regions of interest (ROIs) in both the palm and finger, the average similarity scores were 17.85%. We present the Frechet Inception Distance (FID) of the proposed model, which achieved a 16.1 score, demonstrating significant performance. These results demonstrated StyleGAN as effective in producing unique synthetic biometric images.
more »
« less
Elucidating the relationships between two automated handwriting feature quantification systems for multiple pairwise comparisons
Abstract Recent advances in complex automated handwriting identification systems have led to a lack of understandability of these systems’ computational processes and features by the forensic handwriting examiners that they are designed to support. To mitigate this issue, this research studied the relationship between two systems: FLASH ID®, an automated handwriting/black box system that uses measurements extracted from a static image of handwriting, and MovAlyzeR®, a system that captures kinematic features from pen strokes. For this study, 33 writers each wrote 60 phrases from the London Letter using cursive writing and handprinting, which led to thousands of sample pairs for analysis. The dissimilarities between pairs of samples were calculated using two score functions (one for each system). The observed results indicate that dissimilarity scores based on kinematic spatial‐geometric pen stroke features (e.g., amplitude and slant) have a statistically significant relationship with dissimilarity scores obtained using static, graph‐based features used by the FLASH ID®system. Similar relationships were observed for temporal features (e.g., duration and velocity) but not pen pressure, and for both handprinting and cursive samples. These results strongly imply that both the current implementation of FLASH ID®and MovAlyzeR®rely on similar features sets when measuring differences in pairs of handwritten samples. These results suggest that studies of biometric discrimination using MovAlyzeR®, specifically those based on the spatial‐geometric feature set, support the validity of biometric matching algorithms based on FLASH ID®output.
more »
« less
- Award ID(s):
- 1828492
- PAR ID:
- 10446215
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Journal of Forensic Sciences
- Volume:
- 67
- Issue:
- 2
- ISSN:
- 0022-1198
- Page Range / eLocation ID:
- p. 642-650
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Many algorithms for virtual tree generation exist, but the visual realism of the 3D models is unknown. This problem is usually addressed by performing limited user studies or by a side-by-side visual comparison. We introduce an automated system for realism assessment of the tree model based on their perception. We conducted a user study in which 4,000 participants compared over one million pairs of images to collect subjective perceptual scores of a large dataset of virtual trees. The scores were used to train two neural-network-based predictors. A view independent ICTreeF uses the tree model's geometric features that are easy to extract from any model. The second is ICTreeI that estimates the perceived visual realism of a tree from its image. Moreover, to provide an insight into the problem, we deduce intrinsic attributes and evaluate which features make trees look like real trees. In particular, we show that branching angles, length of branches, and widths are critical for perceived realism. We also provide three datasets: carefully curated 3D tree geometries and tree skeletons with their perceptual scores, multiple views of the tree geometries with their scores, and a large dataset of images with scores suitable for training deep neural networks.more » « less
-
ImportanceAssessing nontechnical skills in operating rooms (ORs) is crucial for enhancing surgical performance and patient safety. However, automated and real-time evaluation of these skills remains challenging. ObjectiveTo explore the feasibility of using motion features extracted from surgical video recordings to automatically assess nontechnical skills during cardiac surgical procedures. Design, Setting, and ParticipantsThis cross-sectional study used video recordings of cardiac surgical procedures at a tertiary academic US hospital collected from January 2021 through May 2022. The OpenPose library was used to analyze videos to extract body pose estimations of team members and compute various team motion features. The Non-Technical Skills for Surgeons (NOTSS) assessment tool was employed for rating the OR team’s nontechnical skills by 3 expert raters. Main Outcomes and MeasuresNOTSS overall score, with motion features extracted from surgical videos as measures. ResultsA total of 30 complete cardiac surgery procedures were included: 26 (86.6%) were on-pump coronary artery bypass graft procedures and 4 (13.4%) were aortic valve replacement or repair procedures. All patients were male, and the mean (SD) age was 72 (6.3) years. All surgical teams were composed of 4 key roles (attending surgeon, attending anesthesiologist, primary perfusionist, and scrub nurse) with additional supporting roles. NOTSS scores correlated significantly with trajectory (r = 0.51,P = .005), acceleration (r = 0.48,P = .008), and entropy (r = −0.52,P = .004) of team displacement. Multiple linear regression, adjusted for patient factors, showed average team trajectory (adjustedR2 = 0.335; coefficient, 10.51 [95% CI, 8.81-12.21];P = .004) and team displacement entropy (adjustedR2 = 0.304; coefficient, −12.64 [95% CI, −20.54 to −4.74];P = .003) were associated with NOTSS scores. Conclusions and RelevanceThis study suggests a significant link between OR team movements and nontechnical skills ratings by NOTSS during cardiac surgical procedures, suggesting automated surgical video analysis could enhance nontechnical skills assessment. Further investigation across different hospitals and specialties is necessary to validate these findings.more » « less
-
Many developers of biometric systems start with modest samples before general deployment. However, they are interested in how their systems will work with much larger samples. To assist them, we evaluated the effect of gallery size on biometric performance. Identification rates describe the performance of biometric identification, whereas ROC-based measures describe the performance of biometric authentication (verification). Therefore, we examined how increases in gallery size affected identification rates (i.e., Rank-1 Identification Rate, or Rank-1 IR) and ROC-based measures such as equal error rate (EER). We studied these phenomena with synthetic data as well as real data from a face recognition study. It is well known that the Rank-1 IR declines with increasing gallery size, and that the relationship is linear against log(gallery size). We have confirmed this with synthetic and real data. We have shown that this decline can be counteracted with the inclusion of additional information (features) for larger gallery sizes. We have also described the curves which can be used to predict how much additional information would be required to stabilize the Rank-1 IR as a function of gallery size. These equations are also linear in log(gallery size). We have also shown that the entire ROC-curve was not systematically affected by gallery size, and so ROC-based scalar performance metrics such as EER are also stable across gallery size. Unsurprisingly, as additional uncorrelated features are added to the model, EER decreases. We were interested in determining the impact of adding more features on the median, spread and shape of similarity score distributions. We present evidence that these decreases in EER are driven primarily by decreases in the spread of the impostor similarity score distribution.more » « less
-
A recently reported vision ray metrology technique [Opt. Express29,43480(2021)OPEXFF1094-408710.1364/OE.443550] measures geometric wavefronts with high precision. This paper introduces a method to convert these wavefront data into height information, focusing on the impact of back surface flatness and telecentricity errors on measurement accuracy. Systematic errors from these factors significantly affect height measurements. Using ray trace simulations, we estimate reconstruction errors with various plano-concave and plano-convex elements. We also developed a calibration technique to mitigate telecentricity errors, achieving submicron accuracy in surface reconstruction. This study provides practical insights into vision ray metrology systems, highlighting validity limits, emphasizing the importance of calibration for larger samples, and establishing system alignment tolerances. The reported technique for the conversion of geometric wavefronts to surface topography employs a direct non-iterative ray-tracing-free method. It is ideally suited for reference-free metrology with application to freeform optics manufacturing.more » « less
