Fingerprint Recognition

Fingerprint recognition

Introducing fingerprint system biometrics.

How it works

Fingerprint systems analyze the locations of “minutiae” – the endings and bifurcations of the friction ridges on the pad of your finger. Often, additional information, such as the number of ridges between minutiae points, is also used.
A number of methods exist to capture fingerprints: optical capture uses visible light, capacitive sensors use electrical current conducted through the finger, and ultrasound uses high frequency sound waves.
Contact sensors capture an image of the ridge pattern in contact with the sensor, while contactless sensors effectively take an image (2D or 3D, depending on the system) of the ridge pattern while the finger is held a distance away from the sensor.

Artefacts

More determined attackers may attempt to produce an artefact – a false fingerprint – which matches the finger of an enrolled user.
Once a high quality artefact has been produced, the probability of defeating the system increases significantly. Instructions for making artefacts of reasonable quality can be readily found on the internet. This does not make an attacker’s life easy, but this is a vulnerability particular to fingerprint biometrics.
Obviously, the specific artefact must be recognisable by the type of fingerprint capture sensor it is used against. For example, a capacitive system will require the artefact to have similar conductivity properties to human skin in order to be detected.
It is clearly easy to obtain a fingerprint image with the co-operation of an enrolled data subject but it is also possible to obtain such an image covertly. This is because one major vulnerability of fingerprint biometrics is that latent fingerprints are sometimes left when a finger comes into contact with a surface (indeed, this is the whole point of forensic applications of fingerprinting). Sometimes, this makes it possible to obtain a fingerprint image from which an artefact can be produced.

Introduction

A fingerprint is the representation of the dermal ridges of a finger. Dermal ridges form through a combination of genetic and environmental factors; the genetic code in DNA gives general instructions on the way skin should form in a developing fetus, but the specific way it forms is a result of random events such as the exact position of the fetus in the womb at a particular moment. This is the reason why even the fingerprints of identical twins are different [2]. Fingerprints are fully formed at about 7 months of fetus development and finger ridge configurations do not change throughout the life of an individual,…

Literature survey

Fingerprint recognition is the procedure of comparing known and unknown fingerprints to prove that the it is from the same person or not. Today, many approaches, techniques, and systems are used to match fingerprints and solve related problems. This section is focused on analyzing and categorizing different author’s work in the fingerprint recognition area. Table 1 provides a summary of various papers in the current literature. First column determines the Reference of the papers by author names and year of publication. Second column gives the summary of the work in the corresponding paper, and the third column describes the implemented approaches used to solve fingerprint recognition issues. The author names and the year of publication will be used as an identifier for the rest of the tables in the chapter showing other details of the referred literature.

Data analysis

This section analyses the fingerprint recognition data resulting from the literature survey in Section 2. In general, fingerprint recognition processes can be done using multiple procedures. First, decompose raw human fingerprint sample to create digit presentation of the same sample. On the next step, preprocessing is done for the raw input image by filtering and improving fingerprint image to produce suitable output image for feature extraction which extracts the unique features of the fingerprint from the digital representation sample. These extracted features are saved in the fingerprint database as features. Final step is to match the input fingerprint with fingerprint template stored in the database to find the similarities. The outcome of these procedures is deciding if the person is identified or not. Figure 2 describes the sequence of biometric or fingerprint system. The fingerprint procedures involve many different approaches and algorithms that are used to enhance and improve the low quality of fingerprint images. If the fingerprint image is on good quality, then there are no issues and will appear while matching. Table 1 presents the approaches that are used by different authors. Figure 3 presents the most used approaches. Different matching approaches are used in 15 papers which can be considered as the commonly used approaches. Then minutiae extraction techniques are used in around 10 papers. Post processing and histogram equalization are used in 2 papers. There are some other approaches used only once in some of the papers.

Finger detection and segmentation

Unconstrained capturing systems, which do not have a finger guidance based on dedicated hardware or an on-screen guidance, require a finger detection. Such an algorithm detects the position and orientation of the finger and forms the basis for an automatic capturing system. The image is then segmented and cut to the fingerprint containing area. Four different approaches can be distinguished, whereas in practice implementations often apply a combination of them:

• Sharpness: Sharpness-based approaches exploit the difference between the focused sharp finger area and the blurred background. This effect is most suitable on images acquired with a very small finger-to-sensor distance and a wide open aperture. The early work of Lee et al. presented a fixed focus real-time scheme, which selected the best focused and oriented image out of a series. The authors investigated on the suitability of general purpose focus measuring algorithms. Their experiment showed that the Variance-Modified-Laplacian of Gaussian (VMLOG) algorithm is best suited for the touchless fingerprint capturing device they used. The authors also compared a finger moving method with a fixed lens to a lens-moving method with a fixed distance between sensor and finger. They concluded that the former method is preferable which is questionable from today’s perspective. A subsequent work by the same authors compared three segmentation approaches. One of them was sharpness-based and used the Tenengrad method in the frequency domain. Here, a Sobel operator was used to calculate the horizontal and vertical gradients in the image. A certain threshold was established to separate the sharp foreground from the background area. Lee et al. aimed at selecting the best focused image out of a video stream. The authors proposed an algorithm based on a Gaussian filter to segment the sharp regions of an image which corresponded to the finger region.
• Shape: The shape of a finger is highly common for all finger position codes (i.e., various finger instances from thumb finger to little finger), which enables a detection via shape. proposed a conjunction of a shape- and color-based finger detection using edge pairing. The authors applied machine learning-based algorithms to the binarized image in the LUV color model. They also used Histogram of Oriented Gradient (HOG) features with rich feature descriptors as baseline and compared their results with them.
• Contrast and color: Especially, if a certain illumination is used, a determination based on the contrast or color is an efficient mechanism for finger detection. Based on findings of Hiew et al. for the segmentation in skin and background area, an analysis of the YCbCr color space represents the most promising approach. The result is a binary image with a separation between finger image area and background. The above approach is widely adopted, modified to meet different prerequisites, and further investigated by many authors. Ravi and Sivanath showed that extending the Cr component with information of the HSV and nRGB color space enables a precise isolation of a finger. The authors used a certain threshold for every color channel and merged the results. Wang et al. presented comprehensive research on different finger illuminations and color models. For this reason, the authors captured images with green, red, and blue illumination and compared the YCbCr color model with YIQ and HSV. Alternatively, other color models such as CMYK (magenta channel) and CIELAB were also investigated. This approach was adopted in many other preprocessing workflows similar to. Because of prerequisites during the capturing process, most approaches considered only the largest segmented area as fingerprint. The color-based segmentation is often combined with an adaptive thresholding, e.g., based on Otsu image thresholding. Hier et al. also determined the mean and covariance on the CbCr channels to improve the segmentation accuracy. Another approach by Lee et al. exploited skin color properties with help of guided machine learning. This approach was shown to reveal competitive results but is more complex compared to others. As a second scheme, the authors suggested a region growing approach. Using an initial seed and a similarity measure with a certain threshold the tested pixels were added to the seed. This approach is also suitable for ROI extraction. With the mean shift segmentation Ramachandra et al. proposed another contrast-based approach. The algorithm filters the input image in the spatial domain and segments it by fusing the convergence points in homogeneous regions. With this elaborated approach, the authors were able to achieve accurate results in challenging environments. Priesnitz et al. presented a deep learning-based semantic segmentation scheme for the hand area as well as fingertips. The authors used a general purpose hand gesture dataset to test their algorithm against a color-based baseline segmentation algorithm. The proposed method showed accurate results especially in challenging environmental conditions. It should be critically noted that none of the discussed approaches conducted a wider analysis on different skin color types, e.g., as defined in.
• Image depth information: Jonietz and Jivet presented a segmentation approach using the information of a depth sensor combined with an RGB image captured by smartphones. The authors were able to extract the slap hand from a busy background and proposed further processing. Exploiting the images’ depth information the system worked especially well in the presence of objects of similar color, e.g., when two hands were placed on top of each other.