Performing content-based retrieval of humans using gait biometrics
read more
Citations
Learning Race from Face: A Survey
Soft biometrics for surveillance: an overview
Soft Biometrics; Human Identification Using Comparative Descriptions
On soft biometrics
Biometric recognition in surveillance scenarios: a survey
References
Indexing by Latent Semantic Analysis
Social Psychology of Intergroup Relations
An introduction to biometric recognition
Visual perception of biological motion and a model for its analysis
A survey on visual surveillance of object motion and behaviors
Related Papers (5)
Frequently Asked Questions (13)
Q2. What are the characteristics of the traits that are used in the biometric approach?
Soft biometric techniques use a mixture of categorical metrics (e.g. Ethnicity) and value metrics (e.g. Height) to represent their traits.
Q3. What is the semantic term used for retrieval?
For retrieval by semantic terms, a query document matrix is constructed where all visual and non-relevant semantic terms are set to zero 2
Q4. What are the recent uses of biometrics?
More recently, physical descriptions have also been used in biometric techniques as an ancillary data source where they are referred to as soft biometrics [28], as opposed to primary biometric sources such as iris, face or gait.
Q5. What are the two types of descriptions?
Semantic whole body descriptions (Height, Figure etc.) and global descriptions (Sex, Ethnicity, Age, etc.) are a natural way to describe individuals.
Q6. What is the effect of the hair colour on the construction of binary silhouettes?
the construction of binary silhouettes is undoubtedly affected by hair colour when compared to background, and as such the average silhouette images retain hair colour as brightness in the head region.
Q7. How do the authors account for the anchoring of terms?
The authors have accounted for anchoring of terms gathered for individual traits by setting the default term of a trait to a neutral “Unsure” rather than any concept of “Average”.
Q8. What is the problem with the manual annotation of videos?
the manual annotation of videos is a laborious[7][16] process, too slow for effective use in real time CCTV footage and vulnerable to various sources of human error (subject variables, anchoring etc.).
Q9. What are the common ethnic terms?
Their ethnic terms encompass the three categories mentioned most often and an extra two categories (Indian and Middle Eastern) matching the UK census4.
Q10. What is the popular approach to extracting gait information from video?
In their experiments, the videos used are from camera set-up “a” during which subjects walk at a natural pace side on to the plane of the camera view and walking either towards the left or right.
Q11. What is the use of character descriptions in narrative?
Their use is abundant in character description in narrative, helping readers put characters in a richer context with a few key words such as slender or stout.
Q12. What are some of the techniques which focus on low level action features?
Some approaches concentrate on low level action features, such as trajectory and direction, whilst others include detection of more complex concepts such as actor goals and scenario detection.
Q13. How many annotators have been used to analyse gait videos?
Each subject has been annotated by at least two separate annotators, though 10 have been annotated with 40 annotators as part of a previous, more rigourous, though smaller scale experiment [35].