Minutiae Extraction Algorithm Research Articles

A multi-task fully deep convolutional neural network for contactless fingerprint minutiae extraction

With the outbreak and wide spread of novel coronavirus (COVID-19), contactless fingerprint recognition has attracted more attention for personal recognition because it can provide significantly higher user convenience and hygiene than the traditional contact-based fingerprint recognition. However, it is still challenging to achieve a highly accurate recognition due to the low ridge-valley contrast and pose variances of contactless fingerprints. Minutiae points are a kind of ridge flow discontinuities, and robust and accurate extraction is an important step for most automatic fingerprint recognition algorithms. Most of existing methods are based on two stages which locate the minutiae points first and then compute their directions. The two-stage method cannot make full use of location and direction information. In this paper, we propose a multi-task fully deep convolutional neural network for jointly learning the minutiae location detection and its corresponding direction computation which operates directly on the whole gray scale contactless fingerprints. The proposed method consists of offline training and online testing stages. In the training stage, a fully deep convolutional neural network is built for the tasks of minutiae detection and its direction regression, with an attention mechanism to make the direction regression branch concentrate on the minutiae points. A new loss function is proposed to jointly learn the tasks of minutiae detection and its direction regression from the whole fingerprints. In the testing stage, the trained network is applied on the whole contactless fingerprint to generate the minutiae location and direction maps. The proposed multi-task leaning method performs better than the individual single task and it operates directly on the raw gray-scale contactless fingerprints without preprocessing. The results on three contactless fingerprint datasets show the proposed algorithm performs better than other minutiae extraction algorithms and the commercial software.

PENINGKATAN KUALITAS CITRA SIDIK JARI DENGAN ALGORITMA MINUTIAE EXTRACTION DAN LEARNING VECTOR QUANTIZATION

Sistem pengenalan sidik jari bertujuan untuk mengindentifikasi seseorang. Kendala utama dalam pengenalan sidik jari seseorang, adalah karena citranya memiliki kualitas yang rendah. Kualitas tersebut disebabkan oleh jenis kulit yang berminyak, kering, kotor dan jenis scanner fingerprint yang digunakan. Untuk itu dilakukan peningkatan dengan tujuan memperbaiki citra sidik jari sebagai faktor utama penentu tingkat akurasi hasil pengenalan citra sidik jari. Agar citra sidik jari yang tidak jelas mudah diinterpretasi oleh manusia maupun mesin, maka perlu peningkatan kualitas citra tersebut dengan cara memperjelas garis sidik jarinya. Penelitian ini bertujuan untuk peningkatan kualitas citra sidik jari dengan Algoritma Minutiae Extraction dan metode Learning Vector Quantization (LVQ) sebagai pengujian. Pengujian ini dilakukan dengan menggunakan 4 citra sebagai pelatihan pada setiap kelasnya. Adapun jumlah kelas pada pengujian ini seluruhnya 10 kelas dengan tiap kelas terdiri dari 10 citra. Pada pengujian 75 data citra sidik jari diperoleh tingkat akurasi 83.3333%.

Spectroscopic characterization of Er,Yb:Y2Ti2O7 phosphor for latent fingerprint detection

Er3+ doped, Yb3+ doped, and Er3+/Yb3+ co-doped Y2Ti2O7 phosphors with various concentrations of Er3+ (12–20%), Yb3+ (1-10 at%), and Er3+Yb3+ (1%, and 1,2,3%, respectively) were prepared by solid-state reaction. The phase structure and purity of all prepared phosphors were studied by X-ray diffraction analysis followed by measurement of the hydrodynamic diameter of each sample by Dynamic light scattering. The formation of the pyrochlore structure was confirmed by the observation of relative vibrations by Fourier Transform Infrared Spectroscopy. Moreover, photoluminescence spectra of different co-doped Y2Ti2O7 compounds are presented to check the energy transfer processes of Er3+ and Yb3+ ions. Finally, phosphors were used for the detection of latent fingermarks on various surfaces and a fingerprint minutia extraction algorithm was used for the analysis of extracted minutiae. The analyses confirm that the co-doped phosphors can be useful for the visualization of latent fingerprints once a good detection of their minutiae is obtained.

Blurred fingerprint image enhancement: algorithm analysis and performance evaluation

A conventional automatic fingerprint matching process uses similarity score to quantify similarity between fingerprint images to be matched, and the similarity score can be determined with a minutiae extraction algorithm (MEA) which extracts minutiae from fingerprint images. The performance of MEA relies on the quality of fingerprint images. In case of blurred fingerprint images, it becomes difficult to obtain a reliable similarity score. As the result, an image enhancement algorithm should be incorporated with MEA when the fingerprint image is blurred. In this study, Volterra filter is proposed to enhance blurred fingerprints and compared against different enhancement algorithms. Experimental results show that Volterra filter outperforms other techniques such as Laplacian, Wiener, and Gabor filters for enhancing blurred images and its calculation complexity is moderate among techniques considered in this study.

Massively parallel palmprint identification system using GPU

Automated human authentication is becoming increasingly important in today’s world due to increased need of security and surveillance applications deployed in almost all premises and installations. In this regard, palmprint biometric based identification has gained a lot of attention in recent years. However, due to large size of palmprint images and presence of principal lines, wrinkles, creases, and other noises, there are large number of inaccurate minutiae present. The computational requirement of palmprint identification is also quite large and it takes a lot of time to find identity of a palmprint in large database. In this study, a novel palmprint identification solution has been proposed that increases the accuracy of minutia detection based on improved frequency estimation and a novel region-quality based minutia extraction algorithm. Furthermore, a novel, efficient and highly accurate minutiae based encoding and matching algorithm is proposed that is designed to achieve maximum parallelism, and it is further accelerated using graphical processing unit. The results of the proposed palmprint identification demonstrate high accuracy and much faster identification speeds in comparison with current state of the art. Therefore, it can be considered as a robust, efficient and practical solution for palmprint based identification systems.

Towards Accurate Estimation of Fingerprint Ridge Orientation Using BPNN and Ternarization

Accurate estimation of ridge orientation is a crucial step in fingerprint image enhancement because the performance of a minutiae extraction algorithm and matching heavily relies on the quality of the input fingerprint images, which in turn relies on proper estimation of ridge orientation. When ridge structure is not clear in a noisy fingerprint image, ridge orientation estimation becomes tough and it is considered as one of the most challenging tasks in fingerprint image enhancement process. A new methodology based on neural network approach and Ternarization for ridge orientation estimation is proposed in this paper. In the present work a trained Back Propagation Neural Network (BPNN) is used for accurate ridge orientation. The advantage with the Ternarization process is that it eradicates the false ridge orientation for which the neural network wrongly responds with the larger value and at the same time, it keeps the correct ridge orientation blocks intact without making them blur. This helps in qualitative extraction of minutiae points from the fingerprint image. The experimental results have shown that the proposed method for estimating ridge orientation works far better than the traditional gradient based approach.

Impact of Algorithms for the Extraction of Minutiae Points in Fingerprint Biometrics

Problem statement: As the importance of automatic personal identificat ion applications increases, biometrics particularly fin gerprint identification is the most consistent and greatly acknowledged technique. A very important st ep in automatic fingerprint recognition system is to extract the minutiae points from the i nput fingerprint images automatically and quickly. Approach: Fingerprints from the database FVC2002 (DB1-a) is used for experimental purpose. The minutiae points from 100 fingerprints were detected. It is proposed to use Minutiae Detection using Crossing Numbers (MDCN) and Minutiae Detection using Midpoint Ridge Contour Method (MDMRCM). Finally the performance of minutiae extraction algorithms using the number of minutiae detected in both the cases w ere analysed. Results: The result shows that the avearge performance of MDCN method for minutiae points detection is 88% and for MDMRCM method is 92%. Conclusion: The performance of MDMRCM is better than MDCN method. MDMRCM method extract more minutiae points than MDCN method. It consumes lesser time to get the output and the false minutiae points were not d etected. And hence MDMRCM method is considered to be a superior than MDCN method.

Adaptable Fingerprint Minutiae Extraction Algorithm Based-on Crossing Number Method for Hardware Implementation using FPGA Device

In this article, a main perspective of developing and implementing fingerprint extraction and matching algorithms as a part of fingerprint recognition system is focused. First, developing a simple algorithm to extract fingerprint features and test this algorithm on PC. The second thing is implementing this algorithm into FPGA devices. The major research topics on which the proposed approach is developing and modifying fingerprint extraction feature algorithm. This development and modification are using crossing number method on pixel representation value ’0’. In this new proposed algorithm, it is no need a process concerning ROI segmentation and no trigonometry calculation. And specially in obtaining their parameters using Angle Calculation Block avoiding floating points calculation. As this method is local feature that usually involve with 60-100 minutiae points, makes the template is small in size. Providing FAR, FRR and EER, performs the performance evaluation of proposed algorithm. The result is an adaptable fingerprint minutiae extraction algorithm into hardware implementation with 14.05 % of EER, better than reference algorithm, which is 20.39 % .The computational time is 18 seconds less than a similar method, which takes 60-90 seconds just for pre-processing step. The first step of algorithm implementation in hardware environment (embedded) using FPGA Device by developing IP Core without using any soft processor is presented.

Research of Automatic Fingerprint Recognition Essential Algorithms

Fingerprint recognition has wide application prospect in all fields which contain identity authentication. Construction of accurate and reliable，safe and Practical automatic fingerprint identification system(AFIS) has become researc hotspot. Although theoretical research and application developmen of AFIS have got a significant Progress，accuracy of the algorithm and proeessing speeds till need to be improved. In this paper, fingerprint image preprocessing algorithms，fingerprint singular Points and minutiae extraction algorithm and fingerprint matching algorithm are analyzed and discussed in detail.

Fingerprint minutiae extraction based on principal curves

It is important to extract minutiae of a fingerprint for the implementation of an auto fingerprint identification system. In this paper, the principal graph algorithm proposed by Kegl is used to obtain principal curves, which can be served as the skeletons of a fingerprint. Based on the obtained principal curves, a minutiae extraction algorithm is proposed to extract minutiae of the fingerprint. The experimental results indicate that principal curves obtained from the principal graph algorithm are smoother than the ones obtained from thinning algorithm, and the minutiae extracted by the proposed algorithm are more efficient.

An application of the onion peeling algorithm for fingerprint verification purposes

In this paper, we apply digital image processing techniques using the onion algorithm of computational geometry to develop fingerprint verification. This paper describes the design and implementation of a fingerprint verification system, which operates in two stages: (i) pre-processing stage (ii) feature extraction using a Computational Geometry Algorithm (CCA). This method may be characterized as an alternative method to well-known minutiae extraction algorithms. In particular, the proposed method is based on specific features, which depend exclusively on the pixels brightness degree of the fingerprint image. These were extracted from a specific geometric area (convex layer) in which the dominant brightness value of the fingerprint ranges. The proposed algorithm is also compared to a well-known commercial verification system which is based on a minutiae extraction algorithm proposed by Jain et al. In the experimental part 2256 verification on tests for each of the two methods took place. The results of this comparison showed that the proposed method yields correct positive and correct negative verification scores greater than 99%. In particular, the proposed CGA method produced extremely reliable results even in cases where the tested fingerprints were complete specimens yet the position or pressure applied was not consistent. The computational complexity of the proposed algorithm may also he characterized as extreme competitive.

Fingerprint minutiae extraction from skeletonized binary images

Fingerprint comparison is usually based on minutiae matching. The minutiae considered in automatic identification systems are normally ridge bifurcations and terminations. In this paper we present a set of algorithms for the extraction of fingerprint minutiae from skeletonized binary images. The goal of the present work is the extraction of the real 40–60 minutiae of a fingerprint image from the 2000–3000 contained in typical skeletonized and binarized images. Besides classical methodologies for minutiae filtering, a new approach is proposed for bridge cleaning based on ridge positions instead of classical methods based on directional maps. Finally, two novel criteria and related algorithms are introduced for validating the endpoints and bifurcations. Statistical analysis of the results obtained by the proposed approach shows efficient reduction of spurious minutiae. The use of the fingerprint minutiae extraction algorithms has also been considered in a fingerprint identification system in terms of timing and false reject or acceptance rates. The presented minutiae extraction algorithm performs correctly in dirty areas and on the background as well, making computationally expensive segmentation algorithms unnecessary. The results are confirmed by visual inspections of validated minutiae of the NIST sdb 4 reference fingerprint image database.

On-line fingerprint verification

Fingerprint verification is one of the most reliable personal identification methods. However, manual fingerprint verification is incapable of meeting today's increasing performance requirements. An automatic fingerprint identification system (AFIS) is needed. This paper describes the design and implementation of an online fingerprint verification system which operates in two stages: minutia extraction and minutia matching. An improved version of the minutia extraction algorithm proposed by Ratha et al. (1995), which is much faster and more reliable, is implemented for extracting features from an input fingerprint image captured with an online inkless scanner. For minutia matching, an alignment-based elastic matching algorithm has been developed. This algorithm is capable of finding the correspondences between minutiae in the input image and the stored template without resorting to exhaustive search and has the ability of adaptively compensating for the nonlinear deformations and inexact pose transformations between fingerprints. The system has been tested on two sets of fingerprint images captured with inkless scanners. The verification accuracy is found to be acceptable. Typically, a complete fingerprint verification procedure takes, on an average, about eight seconds on a SPARC 20 workstation. These experimental results show that our system meets the response time requirements of online verification with high accuracy.