Automated Fingerprint Identification System (AFIS)
AFIS is a biometric identification system which uses the digital imaging technology to obtain, store and process the fingerprint data. AFIS has the ability to classify, match and store fingerprints and palm prints from both criminal and applicant records.
Development of AFIS has brought the revolution in the field of forensic fingerprint examination. It has helped not only in accurate analysis as well as time effective analysis.
The very first AFIS was created in 1974 by the Federal Bureau of Investigation (FBI). Earlier this system only contained the minutiae or important features of fingerprints because it was expensive to store the whole fingerprint image.
The processing of 1,00,000 prints took 30 minutes and now it’s even faster just in the blink of eyes. FBI uses the terms AFIS and IAFIS (Integrated Automated Fingerprint Identification System) interchangeably because of the longevity of FBI’s IAFIS.
Now the identification systems support palm prints, irises and faces along with the fingerprints, which is known as the Automated Biometric Identification System (ABIS). The first such Inovatrics AFIS was deployed in 2009.
Fingerprint identification is based on the minutiae or the location/direction of the ridge endings or bifurcations along the ridge path. The information elucidated from the friction ridges include- the flow of the ridges, presence or absence of features along the individual friction ridge paths and their sequences and the intricate detail of a single ridge. This information is called 3 level details.
An AFIS is designed to interpret the flow of the overall ridges to assign a fingerprint classification and then extract the minutiae detail– a subset of the total amount of information available yet enough information to effectively search a large repository of fingerprints.
The AFIS is a computer based system, hence it has two parts- hardware and software.
The hardware includes the sensors which are used to collect the digital images of the fingerprint. The types of sensors utilized in AFIS are:
- Optical Sensors– These sensors are the most commonly used because they just capture the optical image of the fingerprints.
- Ultrasound Sensors– These sensors employ high frequency ultrasound waves or optical devices that use prisms to detect the change in light reflectance related to fingerprints.
- Capacitance Sensors– The sensors determine each pixel value based on the capacitance measured which states that the capacitance of the valley is less significant than that of the friction ridges.
- Thermal Scanners– When a finger is swiped on the surface of the scanner, difference in the temperature over time is measured to create a digital image of the fingerprint.
The softwares employed in the AFIS is responsible for matching of the fingerprints. The matching techniques used are of two types- minutiae based matching and pattern based matching.
Minutiae based matching relies on the 3 level details of the friction ridges, whereas the pattern based matching helps in comparing two prints and to find the duplicates. The comparison of fingerprints is done by matching the templates present in the software. Templates are the mathematical representations of the stored fingerprints images.
The digital images of the fingerprints are processed by the computer algorithms which have been developed in the past few decades. These computer algorithms have improved the operational productivity of law enforcement agencies and reduced the number of fingerprint analysts needed.
AFIS Search Algorithm
The algorithms involved in conducting a successful AFIS examination include:
1. Digital Fingerprint Acquisition
The images of the fingerprints are captured using the sensors mentioned above. The parameters that characterize a digital fingerprint image are resolution area, number of pixels, geometric accuracy, contrast, and geometric distortion.
The sensors often capture a series of images instead of a single image of fingerprints. Depending on the application for which the scanner was designed, it may run one or more algorithms using either a resource-limited (memory and processing power) microprocessor on-board or by using an attached computer.
The various algorithms used are- Automatic fingerprint-capture algorithm, Image data-compression algorithm, Vitality detection algorithm, Fingerprint-matching algorithm, Image-processing algorithms and Cryptographic algorithms and protocol(s).
2. Image Enhancement
The images of fingerprints obtained may have different types of noises introduced during the acquisition process. These noises can be from the dust or dirt particles present on the fingers, poor quality of the image, incomplete prints, etc.
Image enhancement algorithms can locate these noised areas which yield the optimal matching over a large collection of fingerprints images. Also these noises are useful in feature detection and individualization in later stages.
3. Feature Extraction
Automatic feature-extraction algorithm is employed to imitate minutiae. The minutiae characteristics considered are the ridge endings and the bifurcations. Other characteristics are not included because they are difficult to extract.
The step involves a binarization algorithm which converts the grey-scale-enhanced fingerprint image into binary form-black pixels(ridges) and white pixels(valleys). Then a thinning algorithm is used to convert the binary images into single pixel width about the central ridge line.
Lastly a minutiae detection algorithm is employed to thinned image that locates x and y coordinates as well as orientation of the minutiae points.
Automatic matching algorithm is used for this process that works on the results of the feature extraction algorithm and finds the similarities or differences between the sets of fingerprints. This algorithm can perform comparison at the rate of 10,000 per second and the results can be sorted on the basis of similarities.
Automatic fingerprint-matching algorithms may yield imperfect results because of the difficult problem posed by large interclass variations (variability in different impressions of the same finger) present in the fingerprints such as: displacement, rotation, partial overlap, nonlinear distortion because of pressing of the elastic three-dimensional finger onto a rigid two dimensional imaging surface, pressure, skin conditions, noise introduced by the imaging environment, and errors introduced by the automatic feature-extraction algorithms.
A robust fingerprint-matching algorithm must be able to deal with all these intraclass variations in the various impressions of the same finger.
5. Indexing and Retrieval
The above mentioned processes are very time-consuming therefore indexing and retrieval algorithms are introduced to make the search faster. Indexing is done by using the automatic fingerprint classification algorithms. A retrieval strategy is also required depending upon the applications such as accuracy and efficiency, matching, human review, etc. As soon as a match is found in the database, the search is automatically stopped.
The Indian Version of Automated Fingerprint Identification System (AFIS) is called FACTS, co-developed by NCRB and CMC Ltd., India. The system uses Image Processing and Pattern Recognition techniques to capture, encode, store and match fingerprints, including comparison of chance prints. This system is utilized by the Central Fingerprints bureau of India.