Automatic Fingerprint Identification Research Articles

Implementation Of Resolution No. 4/2016 Of The ICPO-INTERPOL Concerning Biometric Data Sharing: Between Countermeasures Against Terrorist Foreign Fighters (FTFS) And Protection Of The Privacy Of Indonesian Citizens

This study aims to identify and explore the challenges in the implementation of Resolution No. 4/2016 of the ICPO-INTERPOL concerning sharing and exchanging biometric data among the members of ICPO-INTERPOL in order to counter terrorist foreign fighters (FTFs). This research also aims to elaborate and describe the mechanism of collecting, recording, storing, and exchanging biometric data conducted by the Indonesian government. The mechanism of collecting, recording, and storing biometric data works through 3 main doors, namely: 1) in the process of making electronic Resident's ID Cards (e-ID Cards); 2) in the process of making SKCK (Certificates of Police Record); 3) in the process of making e-Passports. In the implementation of Resolution No. 4/2016 of ICPO-INTERPOL, the most obvious obstacles and challenges are the absence of regulations concerning the protection of personal data, and also the fact that the biometric data system itself is still relatively new and the database is not fully developed. Until today, the INTERPOL National Central Bureau (NCB) for Indonesia does not have its own biometric database system; instead they are using the database that is centralized at Pusinafis Polri (the Indonesian National Police's Center of Automatic Fingerprint Identification System). The results of the study reveal that the biometric data recorded, collected, and stored are big data, but so far in supporting law enforcement and crime prevention processes the data have only been used as comparative data. In addition, there have also been found indications of violations of personal data and privacy, for example in relation to the absence of mechanism for data retention, consent, processing, notification, and disclosure.

Automated Latent Fingerprint Recognition.

Latent fingerprints are one of the most important and widely used evidence in law enforcement and forensic agencies worldwide. Yet, NIST evaluations show that the performance of state-of-the-art latent recognition systems is far from satisfactory. An automated latent fingerprint recognition system with high accuracy is essential to compare latents found at crime scenes to a large collection of reference prints to generate a candidate list of possible mates. In this paper, we propose an automated latent fingerprint recognition algorithm that utilizes Convolutional Neural Networks (ConvNets) for ridge flow estimation and minutiae descriptor extraction, and extract complementary templates (two minutiae templates and one texture template) to represent the latent. The comparison scores between the latent and a reference print based on the three templates are fused to retrieve a short candidate list from the reference database. Experimental results show that the rank-1 identification accuracies (query latent is matched with its true mate in the reference database) are 64.7 percent for the NIST SD27 and 75.3 percent for the WVU latent databases, against a reference database of 100K rolled prints. These results are the best among published papers on latent recognition and competitive with the performance (66.7 and 70.8 percent rank-1 accuracies on NIST SD27 and WVU DB, respectively) of a leading COTS latent Automated Fingerprint Identification System (AFIS). By score-level (rank-level) fusion of our system with the commercial off-the-shelf (COTS) latent AFIS, the overall rank-1 identification performance can be improved from 64.7 and 75.3 to 73.3 percent (74.4 percent) and 76.6 percent (78.4 percent) on NIST SD27 and WVU latent databases, respectively.

System AFIS w polskiej Policji – wczoraj, dzisiaj, jutro

The Automated Fingerprint Identification System (AFIS) has been in operating in Poland for 18 years. During this period, it has undergone many modernizations and transformations. The article presents its evolution in the context of changes taking place in the European Union. This applies both to the legislative developments in the area of freedom, security and justice as well as to the technical solutions being implemented. An attempt was also made to forecast the possibility of further development of AFIS from the perspective of large-scale systems using the latest biometric mechanisms available on the IT market.

Collaborative filtering model for enhancing fingerprint image

Fingerprint enhancement plays a very important role in automatic fingerprint identification system. In order to ensure reliable fingerprint identification and improve fingerprint ridge structure, a novel method based on the collaborative filtering model for fingerprint enhancement is proposed. The proposed method consists of two stages. First, the original fingerprint is pre-enhanced by using Gabor filter and linear contrast stretching. Next, the pre-enhanced fingerprint is partitioned into patches in spatial domain, and then the patches are enhanced based on spectra diffusion by using the two-dimensional (2D) angular-pass filter and the 2D Butterworth band-pass filter. The proposed method takes full advantage of the ridge information and spectra diffusion with higher quality to recover the lost ridge information. To evaluate proposed method, the databases FVC2004 are employed, and the comparison experiments are carried out using various methods. Comparative experimental results show that the proposed algorithm outperforms the existing state-of-the-art methods on fingerprint enhancement.

A novel monodisperse SiO2@C-dot for the rapid and facile identification of latent fingermarks using self-quenching resistant solid-state fluorescence.

Solid powder fluorescence shows great potential for application in medicine, biology, and engineering, especially in the identification of latent fingermarks in forensic science. However, conventional developing methods suffer from some drawbacks, such as low contrast, low sensitivity, low selectivity, and high toxicity. To conquer these challenges, novel SiO2@C-dot microspheres were prepared via a facile one-pot hydrothermal method by using citric acid as a carbon source and aminosilane as a nitrogen source. Interestingly, the results showed that the resultant powders possess good monodispersity, high fluorescence emission, and resistance to self-quenching. Additionally, the mechanism for the solid-state fluorescence of SiO2@C-dot compounds was also investigated. More importantly, the fingermarks on various surfaces, including transparent glasses, ceramic tiles, transparent plastics, aluminum alloys, plastic cards, painted woods, artificial leathers, and Chinese paper money, developed by the powders have indicated well-defined papillary ridges under a 365 nm UV lamp. The novel strategy of using monodisperse SiO2@C-dot microspheres as a fluorescent label for developing latent fingermarks showed greater advantages compared to conventional methods, which was also demonstrated using the automatic fingerprint identification system. It is simple, rapid, low-cost, nontoxic, and effective, and is expected to be a promising alternative for the development of latent fingerprints in forensic science.

Latent Fingerprint Value Prediction: Crowd-Based Learning

Latent fingerprints are one of the most crucial sources of evidence in forensic investigations. As such, development of automatic latent fingerprint recognition systems to quickly and accurately identify the suspects is one of the most pressing problems facing fingerprint researchers. One of the first steps in manual latent processing is for a fingerprint examiner to perform a triage by assigning one of the following three values to a query latent: Value for Individualization (VID), Value for Exclusion Only (VEO), or No Value (NV). However, latent value determination by examiners is known to be subjective, resulting in large intra-examiner and inter-examiner variations. Furthermore, in spite of the guidelines available, the underlying bases that examiners implicitly use for value determination are unknown. In this paper, we propose a crowdsourcing based framework for understanding the underlying bases of value assignment by fingerprint examiners, and use it to learn a predictor for quantitative latent value assignment. Experimental results are reported using four latent fingerprint databases, two from forensic casework (NIST SD27 and MSP) and two collected in laboratory settings (WVU and IIITD), and a state-of-the-art latent automated fingerprint identification system (AFIS). The main conclusions of this paper are as follows: 1) crowdsourced latent value is more robust than prevailing value determination (VID, VEO, and NV) and latent fingerprint image quality for predicting AFIS performance; 2) two bases can explain expert value assignments, which can be interpreted in terms of latent features; and 3) our value predictor can rank a collection of latents from most informative to least informative.

A Case of Three Deltas in a Fingerprint

Fingerprints begin forming at about the 6th to the 13th week of gestation. A number of factors determine the print pattern in the womb, including the density of the amniotic fluid surrounding the foetus, the size of the foetus, the friction in the womb, the location in the womb amongst others. Once developed the pattern remains constant throughout life. Basically there are three main patterns; The Loop, which rise up and loop back around, continuing on the same direction it started from and it accounts for about 70% of all fingerprints, Arches look like waves that rise and fall on the same fingerprint pattern, accounting for 5% whiles the Whorls appear as circular patterns accounting for 25%. The loop has only one delta, the Arch no delta with the Whorl pattern having two deltas. In the case presented here, a young man of 30 years, who is physically fit and normal without any significant clinical condition apart from a developmental defect of the right thumb which makes it different from the left thumb. From the ten fingerprint patterns taken with the aid of a scanner from the subject, only the abnormal right thumb of the subject with a whorl fingerprint pattern has three deltas which are extremely uncommon and quite different to the traditional, widely known two deltas seen in all whorl patterns in fingerprints. Fingerprint deltas are only present in loops and whorls. There are basically four types of fingerprint whorls. The plain with two deltas, central pocket with two deltas, the double loop whorls with two deltas and accidental whorls which have two or more deltas. Theoretically, less than 1 in 1000 people has these extremely rare fingerprints. The three deltas in a fingerprint whorl pattern may exist in accidental whorls, but no mention is made of it in plain whorls which make this case perhaps the first ever of a known plain whorl with three deltas. This feature is very uncommon in normal patterns. In this case the thumb of this young man has developed abnormally in the womb and has a whorl pattern with three deltas. It is imperative this pattern is taken into consideration when evaluating or interpreting fingerprints. Though the number may be statistically small, it is still essential this is taken into account in manual and especially when using automatic fingerprint identification software to evaluate known and unknown fingerprints.

Cross-Sensor Fingerprint Matching Method Based on Orientation, Gradient, and Gabor-HoG Descriptors With Score Level Fusion

The fingerprint is one of the oldest and most widely used biometric modality for person identification. Existing automatic fingerprint matching systems perform well when the same sensor is used for both enrollment and verification (regular matching). However, their performance significantly deteriorates when different sensors are used (cross-matching, fingerprint sensor interoperability problem). We propose an automatic fingerprint verification method to solve this problem. It was observed that the discriminative characteristics among fingerprints captured with sensors of different technology and interaction types are ridge orientations, minutiae, and local multi-scale ridge structures around minutiae. To encode this information, we propose two minutiae-based descriptors: histograms of gradients obtained using a bank of Gabor filters and binary gradient pattern descriptors, which encode multi-scale local ridge patterns around minutiae. In addition, an orientation descriptor is proposed, which compensates for the spurious and missing minutiae problem. The scores from the three descriptors are fused using a weighted sum rule, which scales each score according to its verification performance. Extensive experiments were conducted using two public domain benchmark databases (FingerPass and Multi-Sensor Optical and Latent Fingerprint) to show the effectiveness of the proposed system. The results showed that the proposed system significantly outperforms the state-of-the-art methods based on minutia cylinder-code (MCC), MCC with scale, VeriFinger—a commercial SDK, and a thin-plate spline model.

A Critical Study on Fingerprint Image Sensing and Acquisition Technology

Automatic Fingerprint Recognition System (AFIS) mainly depends on the quality of the fingerprint captured during the enrollment process, even though a lot of techniques developed in literature for fingerprint matching, all most all system is influenced or affected by the quality of acquisition method. Automated fingerprint identification system requires fingerprint images in a special format. Normally it can't receive and process the photographic image or photo taken from virtual camera or cell camera. There are many special acquisition or sensing strategies to extract the ridge-and-valley structure of finger skin or fingerprint. Traditionally, in law or regulation enforcement packages, fingerprints were especially received offline. Fingerprint acquisition can be specially classified into groups as an offline and live scan. An offline acquisition technique gets input through inked affect of the fingertip on paper and digitized with the aid of the paper with an optical scanner or video digital camera. The live acquisition is received through the sensor that is having the ability to directly digitize the sensing tip of the finger. As the fingerprint sensing, image processing, signal processing, and communication technology advance, an increasing number of new technologies in this acquisition technology are arriving at the main facet. In this paper, we discuss different types of fingerprint acquisition technologies, which involve optical, ultrasonic, capacitance, passive capacitance, and active capacitance. This paper helps to identify new fingerprint acquisition technology.

A Critical Study on Fingerprint Image Sensing and Acquisition Technology

Automatic Fingerprint Recognition System (AFIS) mainly depends on the quality of the fingerprint captured during the enrollment process, even though a lot of techniques developed in literature for fingerprint matching, all most all system is influenced or affected by the quality of acquisition method. Automated fingerprint identification system requires fingerprint images in a special format. Normally it can't receive and process the photographic image or photo taken from virtual camera or cell camera. There are many special acquisition or sensing strategies to extract the ridge-and-valley structure of finger skin or fingerprint. Traditionally, in law or regulation enforcement packages, fingerprints were especially received offline. Fingerprint acquisition can be specially classified into groups as an offline and live scan. An offline acquisition technique gets input through inked affect of the fingertip on paper and digitized with the aid of the paper with an optical scanner or video digital camera. The live acquisition is received through the sensor that is having the ability to directly digitize the sensing tip of the finger. As the fingerprint sensing, image processing, signal processing, and communication technology advance, an increasing number of new technologies in this acquisition technology are arriving at the main facet. In this paper, we discuss different types of fingerprint acquisition technologies, which involve optical, ultrasonic, capacitance, passive capacitance, and active capacitance. This paper helps to identify new fingerprint acquisition technology.

Fast exact fingerprint indexing based on Compact Binary Minutia Cylinder Codes

Abstract With explosive growth in fingerprint databases, Automatic Fingerprint Identification System has become more challenging than ever. Consequently, it is necessary to develop a fast and exact fingerprint indexing to meet the efficiency and accuracy. In this paper, learning Compact Binary Minutia Cylinder Code (CBMCC) is proposed as an effective and discriminative feature representation and Multi-Index Hashing (MIH) is suitably adopted to accelerate the exact search in fingerprint indexing field for the first time. Firstly, we analyze Minutia Cylinder Code to find that it is strongly bit-correlated and awfully unbalanced. Accordingly, we propose an optimization model to learn CBMCC with the balanced independent property and the minimal binary quantization loss. Finally, MIH method further speeds up the exact search in Hamming space by building multiple hash tables on binary code substrings. The performance test shows that CBMCC is effective and discriminative as it has the maximum intra-bit variance while the minimum inter-bit correlation. Furthermore, numerous experiments on public databases demonstrate that CBMCC–MIH is quite outstanding for fingerprint indexing since it achieves an extremely small error rate with a fairly low penetration rate.

Egyes kognitív, emberi tényezők szerepe a szakértőivélemény-alkotásban

The authors provide an overview ofhow cognitive biases may affect forensic examiners, in particular in using Automated Fingerprint Identification Systems.

Two Dimensional Clipping Based Segmentation Algorithm for Grayscale Fingerprint Images

One of the huge methods in Automated Fingerprint Identification System (AFIS) is the segment or separation of the fingerprint. The process of decomposing an image into exclusive components is referred as segmentation. Fingerprint segmentation is the one of the predominant process involved in fingerprint pre-processing and it refers to the method of dividing or separating the image into disjoint areas as the foreground and the background region. The foreground also called as Region of Interest (ROI) due to the fact only the region which contains ridge and valley structure is used for processing, whilst the background carries noisy and irrelevant content material and so that it will be discarded in later enhancement or orientation or classification method. The challenge proper right here is to decide which a part of the image belongs to the foreground, retrieved as an input from the fingerprint sensor device or from benchmark datasets and which part belongs to the background. A 100% correct segmentation is continually very tough, specifically inside the very poor quality image or partial image together with the presence of latent. In this paper, we discuss a modified clipped based segmentation algorithm by adopting threshold value and canny edge detection techniques. We segment the background image is x and y dimensions or in other words left the edge, right edge, top edge and bottom edge of the image. For the purpose of analyzing the algorithm FVC ongoing 2002 benchmark dataset is considered. The entire algorithm is implemented using MATLAB 2015a. The algorithm is able to find affectively ROI of the fingerprint image or separates the foreground region from the background area of the fingerprint image very effectively. In high configuration system proposed algorithm achieves execution time of 1.75 seconds.

Two Dimensional Clipping Based Segmentation Algorithm for Grayscale Fingerprint Images

One of the huge methods in Automated Fingerprint Identification System (AFIS) is the segment or separation of the fingerprint. The process of decomposing an image into exclusive components is referred as segmentation. Fingerprint segmentation is the one of the predominant process involved in fingerprint pre-processing and it refers to the method of dividing or separating the image into disjoint areas as the foreground and the background region. The foreground also called as Region of Interest (ROI) due to the fact only the region which contains ridge and valley structure is used for processing, whilst the background carries noisy and irrelevant content material and so that it will be discarded in later enhancement or orientation or classification method. The challenge proper right here is to decide which a part of the image belongs to the foreground, retrieved as an input from the fingerprint sensor device or from benchmark datasets and which part belongs to the background. A 100% correct segmentation is continually very tough, specifically inside the very poor quality image or partial image together with the presence of latent. In this paper, we discuss a modified clipped based segmentation algorithm by adopting threshold value and canny edge detection techniques. We segment the background image is x and y dimensions or in other words left the edge, right edge, top edge and bottom edge of the image. For the purpose of analyzing the algorithm FVC ongoing 2002 benchmark dataset is considered. The entire algorithm is implemented using MATLAB 2015a. The algorithm is able to find affectively ROI of the fingerprint image or separates the foreground region from the background area of the fingerprint image very effectively. In high configuration system proposed algorithm achieves execution time of 1.75 seconds.

Fast pore matching method based on deterministic annealing algorithm

High-resolution fingerprint identification system (HRFIS) has become a hot topic in the field of academic research. Compared to traditional automatic fingerprint identification system, HRFIS reduces the risk of being faked by using level 3 features, such as pores, which cannot be detected in lower resolution images. However, there is a serious problem in HRFIS: there are hundreds of sweat pores in one fingerprint image, which will spend a considerable amount of time for direct fingerprint matching. The authors propose a method to match pores in two fingerprint images based on deterministic annealing algorithm. In this method, fingerprints are aligned using singular points. Then minutiae are matched based on the alignment result. To reduce the impact of deformation, they build a convex hull for each of these fingerprints. Pores in these convex hulls are used for matching. In the experiments, their method is compared with random sample consensus method, minutia and ICP-based method, and direct pore matching method. The results show that the proposed method is more efficient.

Vacuum Vaporization Technique for Latent Fingerprints Development on Thermal Papers using Lawsone Natural Products

The vacuum vaporization technique is widely used to develop of visualized latent fingerprints on substrate surface for forensics investigation. In this study, we reported the first utilization of lawsone in the vacuum vaporization technique. The lawsone was sublimation in vacuum and showed the detected latent fingerprints on thermal papers. The method involves hanging the thermal paper samples 5, 10, 15 cm above a heating source with dispersed lawsone solids in a vacuum chamber. The optimized condition for lawsone sublimation are 50, 100, 150 mg with low-vacuum (0.1 mbar) and vaporizing temperature at 40-60°C. The sample fingerprints were left for 1, 3, 7 and 30 days before examination comparison between lawsone and fingerprint ink pad using an Automated Fingerprint Identification (AFIS). The resulted showed that using 100 mg lawsone sublimation on thermal paper at the range of 10 cm evidenced the clear, detectable minutiae which can be used for visualization and identification of latent prints without the background black staining known. Thus, this study might be interested application for developing latent fingerprints as a solvent free technique and non-hazardous materials.

Fingerprint Image Segmentation: A Review of State of the Art Techniques

In Automatic Fingerprint Identification System (AFIS), pre-processing of the image is a crucial process in deciding the quality and performance of the system. Pre-processing is consists many stages as Segmentation, Enhancement, Binarisation, and Thinning. In this segmentation is one of the steps of pre-processing which differentiate foreground and background region of fingerprint images. Segmentation is the separation of the fingerprint region or extraction of the presence of ridges from the background of the initial image. Segmentation is necessary because it constructs the region of interest from the input image, reduces the processing time, increases the recognition or matching process performance, and reduces the probability of false feature extraction. A 100% accurate segmentation is always very difficult, especially in the very poor quality image or partial image filled with noise such as the presence of latent. Fingerprints are made of Ridge and Valley structure and their features are classified in three levels as Level 1, Level 2, and Level 3. Level 1 Features are singular macro details like ridge pattern and ridge flows. Level 2 is ridge local features like ridge bifurcation and ridge ending or simply minutiae points or ridge orientation. Level 3 is micro details like sweat pores, incipient ridges. This paper provides an overview of the state of the art techniques of fingerprint image segmentation and contribution of other researchers on segmentation. This paper also discusses a different class of segmentation algorithms with its measuring parameters, computational complexity, advantages, limitations, and applications.

Fingerprint Image Segmentation: A Review of State of the Art Techniques

In Automatic Fingerprint Identification System (AFIS), pre-processing of the image is a crucial process in deciding the quality and performance of the system. Pre-processing is consists many stages as Segmentation, Enhancement, Binarisation, and Thinning. In this segmentation is one of the steps of pre-processing which differentiate foreground and background region of fingerprint images. Segmentation is the separation of the fingerprint region or extraction of the presence of ridges from the background of the initial image. Segmentation is necessary because it constructs the region of interest from the input image, reduces the processing time, increases the recognition or matching process performance, and reduces the probability of false feature extraction. A 100% accurate segmentation is always very difficult, especially in the very poor quality image or partial image filled with noise such as the presence of latent. Fingerprints are made of Ridge and Valley structure and their features are classified in three levels as Level 1, Level 2, and Level 3. Level 1 Features are singular macro details like ridge pattern and ridge flows. Level 2 is ridge local features like ridge bifurcation and ridge ending or simply minutiae points or ridge orientation. Level 3 is micro details like sweat pores, incipient ridges. This paper provides an overview of the state of the art techniques of fingerprint image segmentation and contribution of other researchers on segmentation. This paper also discusses a different class of segmentation algorithms with its measuring parameters, computational complexity, advantages, limitations, and applications.

Fingerprint enhancement rooted in the spectra diffusion by the aid of the 2D adaptive Chebyshev band-pass filter with orientation-selective

2D adaptive Chebyshev band-pass filter (ACBF) with orientation-selective, a novel fingerprint enhancement filter, is designed in this paper. The fingerprint enhancement is deeply rooted in the spectra diffusion by performing the 2D ACBF with orientation-selective in the frequency domain. The process of the enhancement is to have two phases: fingerprint is first enhanced by using Gabor filter and histogram equalization (HE), and then the pre-enhanced fingerprint is enhanced based on spectra diffusion by using the 2D ACBF with orientation-selective in frequency domain. In the first stage, the fingerprint quality can be improved in some extent. In the second stage, first, the qualities of patches are evaluated by the coherence of point orientations. Second, the adaptive parameters of the 2D ACBF are estimated, further, the 2D ACBF with orientation-selective is designed. Finally, the fingerprint image is enhanced based on spectra diffusion by using the 2D ACBF with orientation-selective. Experimental results on the database of FVC2000 and FVC2004 show that the proposed method achieves better results in comparison with other methods, and can significantly improves the performance of automatic fingerprint identification system (AFIS).

Extreme compression of fingerprint image databases using the model-based transform

In this paper, a model-based compression algorithm is proposed to compress the fingerprint image data. The proposed model is based on parallel lines with identical orientations, arbitrary widths, and similar gray-level values positioned on a rectangle with a constant gray-level value as the background. This algorithm is referred to as Parallel Stroked Multi Line (PSML). A compression algorithm is developed based on Adaptive Geometrical Wavelet which employs PSML to preserve the fingerprint structure and minutiae. The proposed PSML algorithm has significant advantages over Wedgelets Transform and JPEG2000 in terms of PSNR value, visual quality of the compressed images, and compression effect on Automatic Fingerprint Identification Systems (AFIS). On the U.are.U 400 database, the mean EER rate for uncompressed images is 4.54%, whereas at extreme compression rates, like 267:1, this value is 49.41% and 6.22% for JPEG2000 and PSML, respectively. The results show a significant improvement compared to the standard JPEG2000 algorithm.