What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics
read more
Citations
50 years of biometric research
Handbook Of Biometrics
Big Privacy: Challenges and Opportunities of Privacy Study in the Age of Big Data
Demographic Bias in Biometrics: A Survey on an Emerging Challenge
References
A global geometric framework for nonlinear dimensionality reduction.
A flexible new technique for camera calibration
Active appearance models
Active Appearance Models
Related Papers (5)
Frequently Asked Questions (10)
Q2. What techniques have been used to obtain geometric anthropometric measurements?
Contour coordinates and dynamic time warping were used resulting in an EER of 1.33% on a dataset of 50 individuals (BIOGIGA [171]).a) 3D techniques in geometric anthropometric measurements: Recently, 3D techniques have been used to obtain geometric anthropometric measurements.
Q3. What is the importance of balancing privacy with performance?
By balancing privacy with performance, it is likely that soft biometric traits will have a critical role to play in next generation identification systems.
Q4. What is the main issue of the defining the number of categories for a particular trait?
Defining the number of categories for a soft biometric trait: A main issue also relates to finding an efficient and robust way to create the corresponding categories for a particular trait.
Q5. What is the main reason that facial geometric anthropometric measures are of importance?
As mentioned earlier, the main reason that such facial geometric anthropometric measures are of importance, has to do with the fact that localization of facial landmarks (related to eyes, mouth, nose, chin), is often a key step towards precise geometry-extraction, which is in turn crucial for human identification and a class of other recognition systems [288] that generally employ these traits as trackers.
Q6. What is the significance of a scarf detection algorithm?
Min et al. [166] presented a scarf detection algorithm based on PCA and SVM, and reported a detection rate of about 99%, on the ARFD database ([163]) which features 300 scarf-occluded and 300 not-occluded faces.
Q7. What is the challenge of combining soft biometrics with primary traits?
One wide open challenge is to design soft biometric matching systems that account for human variability in describing different traits.
Q8. What was used to detect occluded faces?
This work was later used by Min et al. [168] towards face recognition, where Gabor wavelets, PCA and SVM were employed for occluded faces, while nonoccluded facial parts were computed by block-based LBP.
Q9. What is the challenge of designing and combining soft biometric systems?
In this setting, the challenge is to design and fuse the component systems in a way that satisfies the specific speed and reliability requirements of the overall system.f)
Q10. What is the difference between the traditional definition of race and the modern definition of ethnicity?
The traditional definition of race is related to biological factors and often refers to a person’s physical appearance corresponding to traits such as skin color, eye color, hair color, bone/jaw structure, face and body shape, and other traits , while the traditional definition of ethnicity is more related to sociological factors and it relates primarily to cultural identifiers such as nationality, culture, ancestry, language as well as beliefs.