Periocular biometrics in the visible spectrum: A feasibility study
read more
Citations
Periocular Biometrics in the Visible Spectrum
Partial Face Recognition: Alignment-Free Approach
Deep Learning for Biometrics: A Survey
Periocular biometrics: When iris recognition fails
On the Fusion of Periocular and Iris Biometrics in Non-ideal Imagery
References
Distinctive Image Features from Scale-Invariant Keypoints
Distinctive Image Features from Scale-Invariant Keypoints
SURF: speeded up robust features
Speeded-Up Robust Features (SURF)
A performance evaluation of local descriptors
Related Papers (5)
Frequently Asked Questions (12)
Q2. What are the future works in this paper?
Future work will involve utilizing multispectral information for feature extraction ; using more robust image alignment and matching methods ; combining the periocular matcher with iris matcher ; and developing more robust feature encoding schemes. The authors would also like to study the impact of cosmetics on the texture of the periocular region and the ensuing recognition capability.
Q3. What is the proposed periocular recognition process?
The proposed periocular recognition process consists of a sequence of operations: image alignment (for the global matcher described below), feature extraction, and matching.
Q4. How many images were used in the face recognition experiment?
The authors also performed a face recognition experiment on the full-face images using 449 images in session 2 as probes and 30 images in session 1 as gallery images.
Q5. What is the way to detect iris?
While frontal iris detection can be performed fairly well due to the approximately circular geometry of the iris and the clear contrast between iris and sclera, the accurate detection of eyelids is more difficult.
Q6. Why do the authors believe the accuracy of the matcher decreases with the use of eyebrows?
The authors believe this is due to the noisy keypoints detected around the eyebrow, which results in false matches thereby inflating the imposter matching scores.
Q7. What are the three types of descriptors used in SIFT?
Mikilajczyk et al. [10] have categorized the descriptor types as distribution-based, spatial frequency-based, and differential-based.
Q8. What is the way to represent a fingerprint image?
B. Image Alignment Periocular images contain common components (i.e., iris, sclera, and eyelids) that can be represented in a common coordinate system.
Q9. What is the empirical performance for the global and local representations?
The set of parameters that results in the best empirical performance is selected to be used for the global and local representations.
Q10. How is the performance observed by fusing the global matcher with the SIFT?
7. The best performance is observed to be 80.8% and 77.3% by fusing the LBP based global matcher with SIFT on DB1 and DB2, respectively.
Q11. What is the way to use periocular biometric?
This implies the following; i) periocular biometric should be used as a secondary method supporting the primary biometric or as an alternative when the primary biometric is not available and ii) periocular region contains ~80% of the identity information in associated with the face.
Q12. What is the main difference between global and local feature based biometrics?
When all available pixel values are encoded into the feature vector (as is the case when global features are used), it becomes more susceptible to image variations especially with respect to geometric transformations and spatial occlusions.