Biometrics is [Automated] recognition of [living] persons based on observation of behavioral and biological (anatomical and physiological) characteristics.
2. What is Biometric Data and which are the different biometric data being used for the identification and verification of individuals in e-Governance applications?
Biometric data is the data representing a biometric characteristic. For Example, Image data, behavioural data, sensor data, etc.
The Indian Government proposes to use biometric data for identification and verification of individuals in e-Governance applications. The biometric data includes fingerprint image, minutiae, face image and iris data.
Biometric Sample is defined as the data obtained from a biometric device , either directly or after processing.
Biometric is defined as the biometric sample or combination of biometric samples that is suitable for storage as a reference for future comparison.
An automated system capable of:
• Capturing a biometric sample from an end user;
• Extracting biometric data from that sample;
• Comparing the biometric data with that contained in one or more reference templates;
• Deciding how well they match;
• Indicating whether or not an identification or verification of identify has been achieved.
Biometric Standards are developed to ensure interoperability of biometric devices and algorithms so as to avoid vendor lock-in and also ensure long term storage of data with technology independence. The defined biometric standards are applicable to all e-Governance applications in India as per the Government’s Policy on Open Standards.
Biometric Recognition – It refers to automated recognition of individuals based on their behavioral and biological characteristics. Automated recognition implies that a machine based system is used for the recognition either for the full process or assisted by a human being. Biometric recognition encompasses biometric verification and identification. (Note: This definition of the term ‘Biometric Recognition’ has been included from ‘CD 2382-37, Vocabulary – Biometrics’) Biometric Verification – In verification, a transaction by a subject is processed by the system in order to verify a positive specific claim about the subject’s enrolment (e.g. “I am enrolled as subject X”). Verification will either accept or reject the claim. The verification decision outcome is considered to be erroneous if either a false claim is accepted (false accept) or a true claim is rejected (false reject). Biometric Identification - In identification, a transaction by a subject is processed by the system in order to find an identifier of the subject’s enrolment. Identification provides a candidate list of identifiers that may be empty or contain only one identifier. Identification is considered correct when the subject is enrolled, and an identifier for their enrolments in the candidate list. The identification is considered to be erroneous if either an enrolled subject’s identifier is not in the resulting candidate list (false-negative identification error), or if a transaction by a non-enrolled subject produces a non-empty candidate list (false-positive identification error). For more details, please refer Biometric Standards for e-Governance published on the portal https://egovstandards.gov.in/.
• Personal data privacy
• Confidential financial transaction
• Law enforcement
• Entry devices for buildings
• Computer network access
• Entity authentication etc.
• UIDAI (Aadhar)
• NPR (National Population Register)
• PDS (Public Distribution System)
• RSBY (Rashtriya Swasthya Bima Yojna)
• Transport department for issuing or renewing Driving License, etc
A fingerprint is an impression of the friction ridges found on the inner surface of a finger or a thumb. The ridges follow a global pattern identified as whorl, right loop, left loop, arch, tented arch and twin loop etc. Skin pores also present a detailed pattern in fingerprints. There are also local patterns where ridges end or bifurcate, known as minutiae. Local and/or global patterns of fingerprints are matched to provide a means of identification or verification. The science of fingerprint recognition constitutes accurate means of positive identification known to humans.
10. In fingerprint pattern, what is a Friction Ridge and what are three basic patterns of fingerprint ridges?
Friction ridge is defined as the ridges present on the skin of the fingers and toes, the palms and soles of the feet, which makes contact with an incident surface under normal touch. On the fingers, the unique patterns formed by the friction ridges make up fingerprints. The three basic patterns of fingerprint ridges are the arch, loop, and whorl:
• Arch: The ridges enter from one side of the finger, rise in the center forming an arc, and then exit the other side of the finger.
• Loop: The ridges enter from one side of a finger, form a curve, and then exit on that same side.
• Whorl: Ridges form circularly around a central point on the finger.
Face Image Type: The Full Frontal Image should be captured as per the specifications laid down in Face Image Data Standard version 1.0 published on e-Governance Standards portal https://egovstandards.gov.in.
Color Space: 24 Bit RGB (i.e. Code ox01)
Inter-eye Distance: The Inter-eye distance should be a minimum 120 pixels for a head width of 240 pixels
Pose Angle: Rotation of the head shall be less than ±5 degrees from frontal in every direction (i.e. roll, pitch and yaw)
Shoulders: Both the shoulders should be visible.
The Iris is the muscle within the eye that regulates the size of the pupil, controlling the amount of light that enters the eye. "Eye colour" is the colour of the Iris, which can be green, blue, or brown. In some cases it can be hazel (light brown) or grey. It is the area between sclera and pupil. The texture, and patterns of each person’s Iris are as unique as a fingerprint. Iris Image Specifications: Iris Image Type – The interchange format type of the Iris images that is defined in this standard is for rectilinear images only. If the image is collected by a camera that captures only one eye at a time and is stored using a rectilinear coordinate system, no specific pre-processing is required Cameras that capture images of both eyes simultaneously may use the following processing steps to calculate the rotation angle of the Iris images. i. Pre-processing to calculate rotation angle Before compression, the Iris image will have to be pre-processed to calculate rotation angle. Refer section 6.3.1 of ISO 19794-6:2005(E) for rotation angle calculation for rectilinear images. ii. Rectilinear Image Rotation Uncertainty Refer section 126.96.36.199 of ISO 19794-6:2005(E). Number of eyes: For enrollment: Two eyes For verification: One/Two eyes depending upon application sensitivity requirement Iris Diameter: As per ISO 19794-6:2005(E) medium and higher quality images are only acceptable,. Hence for this Standard, minimum acceptable Iris diameter will be150 pixels Image Margin Segmentation: 50% left and right of Iris diameter 25% top and bottom of Iris diameter Color and Pixel Depth: The iris images shall be captured and stored in grey scale with pixel depth 8bits/pixel Illumination: The eye should be illuminated using near infrared light with wavelength between 700 and 900 nano meters (nm) approximately Image Acquisition Format: Lossless (Raw/PNG/ JPEG 2000) formats
The accuracy of a biometric system is determined through a series of tests in the following order: i. Technology Evaluation: Assessment of matching algorithm accuracy ii. Scenario Evaluation: Assessment of performance in a mock environment iii. Operational evaluation: Live testing on site If all the tests done properly, users will come to know, to a high degree of accuracy, how the system will perform.
In addition to common electronics/computer and hardware failures, common biometric issues include poor-quality biometric samples, user confusion, evasion or non-cooperation, noise, inadequate or excessive lighting, dirty sensor, or subject handicaps.
Source: http://biometrics.gov/Documents/FAQ.pdf )