Search

Matching contactless fingerprints or finger photos to contact-based fingerprint impressions has received increased attention in the wake of COVID-19 due to the superior hygiene of the contactless acquisition and the widespread availability of low cost mobile phones capable of capturing photos of fingerprints with sufficient resolution for verification purposes. This paper presents an end-to-end automated system, called C2CL, comprised of a mobile finger photo capture app, preprocessing, and matching algorithms to handle the challenges inhibiting previous cross-matching methods; namely i) low ridge-valley contrast of contactless fingerprints, ii) varying roll, pitch, yaw, and distance of the finger to the camera, iii) non-linear distortion of contact-based fingerprints, and vi) different image qualities of smartphone cameras. Our preprocessing algorithm segments, enhances, scales, and unwarps contactless fingerprints, while our matching algorithm extracts both minutiae and texture representations. A sequestered dataset of 9,888 contactless 2D fingerprints and corresponding contact-based fingerprints from 206 subjects (2 thumbs and 2 index fingers for each subject) acquired using our mobile capture app is used to evaluate the cross-database performance of our proposed algorithm. Furthermore, additional experimental results on 3 publicly available datasets show substantial improvement in the state-of-the-art for contact to contactless fingerprint matching (TAR in the range of 96.67% to 98.30% at FAR=0.01%).

Detecting the singular point accurately and efficiently is one of the most important tasks for fingerprint recognition. In recent years, deep learning has been gradually used in the fingerprint singular point detection. However, the existing deep learning-based singular point detection methods are either two-stage or multi-stage, which makes them time-consuming. More importantly, their detection accuracy is yet unsatisfactory, especially for the low-quality fingerprint. In this paper, we make a Real One-Stage Effort to detect fingerprint singular points more accurately and efficiently, and therefore, we name the proposed algorithm ROSE for short, in which the multi-scale spatial attention, the Gaussian heatmap and the variant of focal loss are integrated together to achieve a higher detection rate. Experimental results on the datasets FVC2002 DB1 and NIST SD4 show that our ROSE outperforms the state-of-the-art algorithms in terms of detection rate, false alarm rate and detection speed.

Representing fingerprint templates in binary form can provide outstanding merits compared to the conventional minutiae-based fingerprint recognition system. The existing fixed-length fingerprint feature extraction methods either suffer from redundant feature magnitude or lack of template security. In this letter, we present a compact (128 bytes) and cancelable fingerprint binary codes generation scheme which enables accurate and efficient comparison as well as high security. This binary representation is also available for advanced encryption schemes (e.g., fuzzy commitment). Specifically, a kernel learning-based real-valued fingerprint feature is converted into compact and cancelable binary code via one permutation hashing. A partial Haar transform is deployed to further strengthen the irreversibility of the whole system. Experimental results on six benchmark datasets FVC2002 and FVC2004 coupled with security analysis demonstrate the superiority of the proposed method compared with several state-of-the-arts.

The inspection of conductive particles after Anisotropic Conductive Film (ACF) bonding is a common and crucial step in the TFT-LCD manufacturing process since the number of high-quality conductive particles is a key indicator of ACF bonding quality. However, manual inspection under microscope is a time-consuming, tedious, and error-prone. Therefore, there is an urgent demand in industry for the automatic conductive particle inspection system. It is challenging for automatic conductive particle quality inspection due to the existence of complex background noise and diversified particle appearance, including shape, size, clustering and overlapping, etc. As a result, it lacks an effective automatic detection method to handle all the complex particle patterns. In this paper, we propose a U-shaped deep residual neural network (i.e., U-ResNet), which can learn features of particle from massively labeled data. The experimental results show that the proposed method achieves high detection accuracy and recall rate, which exceedingly outperforms the previous work. Also, our system is very efficient and can work in real time.

Herein we report the combination of enzyme-linked immunoassay and pattern recognition analysis for extracting both chemical and spatial information from latent fingermarks (LFMs). The development approach basically involves two steps, namely, specific recognition of protein and polypeptide secretions present in the ridge residues of LFMs by horseradish peroxidase (HRP)-labeled antibodies and the HRP-catalyzed chemiluminescent (CL) reaction between luminol and H2O2. The emitted light can spatially resolve the ridges, generating a bright image against the dark object surface for visualization of an LFM. Meanwhile, thanks to the molecular specificity of the immunoassay step, the emission also provides us additional information on the existence of specific substances in LFMs. The developed LFMs are further processed by a set of digital image processing procedures. Quantitative analysis based on minutia features shows that even poorly developed fingermarks can be matched successfully. This work offers the promise of facilitating cross-disciplinary studies between data-processing approaches and fingermark development techniques, such as the extraction of more information from LFM evidence, as well as the establishment of evaluation criteria for an enhancement technique.

Partial fingerprint verification is a challenging task because of the few features contained in small area as well as the large rotation angle and translation between query images and template images. In this paper, we propose a new framework of partial fingerprint verification based on spatial transformer networks (STN) model, where a transform model, i.e., AlignNet network, is proposed to estimate the alignment parameters, and the verification is modeled as a binary classification task. The experimental results on the simulated datasets created from FVC2004 and the real-world dataset FVC2006 DB1 show that our method is invariant to rotation, and also robust to different kinds of scanners, and dramatically outperforms the rank-1 entry of FVC2006 participants. The EER on FVC2006 DB1 of the proposed algorithm is 3.587% compared to that of 5.564%, the best of FVC2006 DB1 entries.

Tissue/region segmentation of pathology images is essential for quantitative analysis in digital pathology. Previous studies usually require full supervision (e.g., pixel-level annotation) which is challenging to acquire. In this paper, we propose a weakly-supervised model using joint Fully convolutional and Graph convolutional Networks (FGNet) for automated segmentation of pathology images. Instead of using pixel-wise annotations as supervision, we employ an image-level label (i.e., foreground proportion) as weakly-supervised information for training a unified convolutional model. Our FGNet consists of a feature extraction module (with a fully convolutional network) and a classification module (with a graph convolutional network). These two modules are connected via a dynamic superpixel operation, making the joint training possible. To achieve robust segmentation performance, we propose to use mutable numbers of superpixels for both training and inference. Besides, to achieve strict supervision, we employ an uncertainty range constraint in FGNet to reduce the negative effect of inaccurate image-level annotations. Compared with fully-supervised methods, the proposed FGNet achieves competitive segmentation results on three pathology image datasets (i.e., HER2, KI67, and H&E) for cancer region segmentation, suggesting the effectiveness of our method. The code is made publicly available at https://github.com/zhangjun001/FGNet.

Fingerprint is a highly discriminative biometric modality and has gained a lot of interest in both forensic and civil applications. However, it is well known that fingerprint template stored in plaintext is vulnerable to attack. A secure fingerprint template has to be both non-invertible and non-linkable. Minutia cylinder-code (MCC) is a fixed-length and highly discriminative type of minutia descriptor. However, most of the current MCC based fingerprint matching algorithms do not possess the non-linkable property. In this paper, a secured fingerprint MCC matching scheme is proposed by utilizing l1-minimization, where the enrolled fingerprint MCC template is stored in cyphertext form (i.e., E-MCC) and is recognizable only when a close enough query fingerprint presented to the system. Our experimental results on FVC2002 DB1, FVC2002 DB2 and FVC2004 DB1 databases show that the proposed system is highly secure and accurate. The GAR with FAR = 0 on FVC2002 DB1, FVC2002 DB2 and FVC2004 DB1 are 91.4%, 84.0% and 65.6%, respectively, with a security level of 33 bits. The performance of the proposed encrypted domain matching algorithm outperforms state-of-the-art fingerprint encryption algorithms.

As a fundamental sensor for autonomous driving, light detection and ranging (LIDAR) has gained increasing attentions in recent years. Optical phased array (OPA) LIDAR as a solid-state solution with the advantages of durability and low cost has been actively researched in both the academic and industry fields. Beam steering is a critical problem in OPA LIDAR where the beam can be controlled by software instantaneously. In this paper, we propose an object guided beam steering algorithm where the beams are allocated according to the detected objects in current frame of image. A series of rules are designed to assign different weights to different regions in the scene. We evaluated the algorithm in a simulated environment and the experimental results demonstrated the effectiveness of the proposed algorithm.

This paper proposes a trace rule based self-organized map (SOM) model built upon a sparse 2-stage deep belief network (DBN). The combination of SOM and sparse DBN forms a hierarchical network where DBN serves as a V2 features detector while SOM layer learns to extract transformation invariant features guided by trace learning rule during training phase. The performance of our proposed method is evaluated by stimulus specific information (SSI) measuring and comparison with classic algorithms. It is demonstrated that trace rule based SOM model can generate more neurons with high SSI value which is beneficial to convey more useful and discriminative information for further object recognition.

Fingerprint features can be divided into three major categories based on the granularity at which they are extracted: level 1, level 2, and level 3 features. Orientation field, ridge frequency field, and minutiae set are three fundamental components of fingerprint, where the orientation field and ridge frequency field are regarded as level 1 features and minutiae set as level 2 features. It is generally believed that level 1 features, especially orientation field, can be reconstructed from level 2 features, i.e., minutiae. However, it is still a question that if minutiae can be extracted from level 1 features. In this paper, we analyze the relations between level 1 and level 2 features using the frequency modulation (FM) model and propose an approach to extract minutiae from level 1 features (i.e., orientation field and frequency field). The proposed algorithm is evaluated on NIST SD27 and FVC2002 DB1 databases. The true detection rate (TDR) and false detection rate (FDR) of minutiae detection on NIST SD27 and FVC2002 DB1 are about 45% and 30% compared with manually marked minutiae, respectively, with level 1 features extracted at a block size of 16 pixels. When pixelwise orientation and frequency fields are available, TDR and FDR can reach 70% and 25%, respectively. With a smaller block size, the minutiae recovering accuracy can be even higher. Our quantitative and experimental results show the deep relationship between level 1 and level 2 features of a fingerprint.

The inspection of conductive particles after Anisotropic Conductive Film (ACF) bonding is a common and crucial step in the TFT-LCD manufacturing process since quality of conductive particles is an indicator of ACF bonding quality. Manual inspection under microscope is a time consuming and tedious work. There is a demand in industry for automatic conductive particle inspection system. The challenge of automatic conductive particle quality inspection is the complex background noise and diversified particle appearance, including shape, size, clustering and overlapping etc. As a result, there lacks effective automatic detection method to handle all the complex particle patterns. In this paper, we propose a U-shaped deep residual neural network (U-ResNet), which can learn features of particle from massive labeled data. The experimental results show that the proposed method achieves high accuracy and recall rate, which exceedingly outperforms the previous work.

Orientation field estimation is a key step in fingerprint feature extraction and recognition. A complete orientation field estimation algorithm usually consists of two steps, i.e. initial orientation field estimation and post regularisation. In this Letter, a multi-target regression model to regularise the initial orientation field is proposed. A large number of orientation patches with simulated noises, together with their regression targets are fed to a deep neural networks to train a multi-target regression model. For a given initial orientation field at testing stage, a refined orientation field is obtained by applying the regression model in patch-wise and then combining all predicted patches. Experimental results on FVC2002, FVC2004 and FVC2006 databases show remarkable performance compared with state of the art algorithms. Our algorithm is also highly efficient and easy to implement.

Latent fingerprint matching has played a critical role in identifying suspects and criminals. However, compared to rolled and plain fingerprint matching, latent identification accuracy is significantly lower due to complex background noise, poor ridge quality and overlapping structured noise in latent images. Accordingly, manual markup of various features (e.g., region of interest, singular points and minutiae) is typically necessary to extract reliable features from latents. To reduce this markup cost and to improve the consistency in feature markup, fully automatic and highly accurate ("lights-out" capability) latent matching algorithms are needed. In this paper, a dictionary-based approach is proposed for automatic latent segmentation and enhancement towards the goal of achieving "lights-out" latent identification systems. Given a latent fingerprint image, a total variation (TV) decomposition model with L1 fidelity regularization is used to remove piecewise-smooth background noise. The texture component image obtained from the decomposition of latent image is divided into overlapping patches. Ridge structure dictionary, which is learnt from a set of high quality ridge patches, is then used to restore ridge structure in these latent patches. The ridge quality of a patch, which is used for latent segmentation, is defined as the structural similarity between the patch and its reconstruction. Orientation and frequency fields, which are used for latent enhancement, are then extracted from the reconstructed patch. To balance robustness and accuracy, a coarse to fine strategy is proposed. Experimental results on two latent fingerprint databases (i.e., NIST SD27 and WVU DB) show that the proposed algorithm outperforms the state-of-the-art segmentation and enhancement algorithms and boosts the performance of a state-of-the-art commercial latent matcher.

With the emergence and popularity of identity verification means by biometrics, the biometric system which can assure security and privacy has received more and more concentration from both the research and industry communities. In the field of secure biometric authentication, one branch is to combine the biometrics and cryptography. Among all the solutions in this branch, fuzzy commitment scheme is a pioneer and effective security primitive. In this paper, we propose a novel binary length-fixed feature generation method of fingerprint. The alignment procedure, which is thought as a difficult task in the encrypted domain, is avoided in the proposed method due to the employment of minutiae triplets. Using the generated binary feature as input and based on fuzzy commitment scheme, we construct the biometric cryptosystems by combining various of error correction codes, including BCH code, a concatenated code of BCH code and Reed-Solomon code, and LDPC code. Experiments conducted on three fingerprint databases, including one in-house and two public domain, demonstrate that the proposed binary feature generation method is effective and promising, and the biometric cryptosystem constructed by the feature outperforms most of the existing biometric cryptosystems in terms of ZeroFAR and security strength. For instance, in the whole FVC2002 DB2, a 4.58% ZeroFAR is achieved by the proposed biometric cryptosystem with the security strength 48 bits.

This letter develops a novel method for fingerprint singular point detection based on a new singularity representation of ridge-valley region called orientation entropy. The candidate singular point is obtained by the multiple-scale analysis of orientation entropy and some post processing steps are proposed to filter the spurious core and delta points. An iteration compensation scheme is proposed to search the precise location for core points against the offset further. Performance of the proposed method has been evaluated on the dataset of FVC2002 DB1. Experimental results show that the multiple-scale orientation entropy is correct and effective for singular detection and the location compensation scheme reduces the distance between the detection result and the truth singular point.

Biometric cryptosystem has gained increasing attention in recent years. One of the difficulties in this field is how to perform biometric matching under template protection. In this paper, we propose a key binding system based on n-nearest minutiae structures of fingerprint. Unlike the traditional fingerprint recognition method, the matching of nearest structures are totally performed in the encrypted domain, where the template minutiae are protected. Three levels of secure sketch are applied to deal with error correction and key binding: (1) The wrap-around construction is used to tolerate random errors that happens on paired minutiae; (2) the PinSketch construction is used to recover nearest structures which are disturbed by burst errors; and (3) Shamir's secret sharing scheme is used to bind and recover a key based on template minutia structures. The experimental results on FVC2002 DB1 and DB2 and security analysis show that our system is efficient and secure.

Fingerprint segmentation is one of the most important preprocessing steps in an automatic fingerprint identification system (AFIS). Accurate segmentation of a fingerprint will greatly reduce the computation time of the following processing steps, and the most importantly, exclude many spurious minutiae located at the boundary of foreground. In this paper, a new fingerprint segmentation algorithm is presented. First, two new features, block entropy and block gradient entropy, are proposed. Then, an AdaBoost classifier is designed to discriminate between foreground and background blocks based on these two features and five other commonly used features. The classification error rate (Err) and McNemar's test are used to evaluate the performance of our method. Experimental results on FVC2000, FVC2002 and FVC2004 show that our method outperforms other methods proposed in the literature both in accuracy and stability.

Key generation from biometrics has been studied intensively in recent years, linking a key with certain biometric enhances the strength of identity authentication. But the state-of-the-art key generation systems are far away from practicality due to low accuracy. The special manner of biometric matching makes a single feature based key generation system difficult to obtain a high recognition accuracy. Integrating more features into key generation system may be a potential solution to improve the system performance. In this paper, we propose a fingerprint based key generation system under the framework of fuzzy extractor by fusing two kinds of features: minutia-based features and image-based features. Three types of sketch, including minutiae based sketch, modified Biocode based sketch, and combined feature based sketch, are constructed to deal with the feature differences. Our system is tested on FVC2002 DB1 and DB2, and the experimental results show that the fusion scheme effectively improves the system performance compared with the systems based only on minutiae or modified Biocode.

Latent fingerprints serve as an important source of forensic evidence in a court of law. Automatic matching of latent fingerprints to rolled/plain (exemplar) fingerprints with high accuracy is quite vital for such applications. However, latent impressions are typically of poor quality with complex background noise which makes feature extraction and matching of latents a significantly challenging problem. We propose incorporating top-down information or feedback from an exemplar to refine the features extracted from a latent for improving latent matching accuracy. The refined latent features (e.g. ridge orientation and frequency), after feedback, are used to re-match the latent to the top $K$ candidate exemplars returned by the baseline matcher and resort the candidate list. The contributions of this research include: (i) devising systemic ways to use information in exemplars for latent feature refinement, (ii) developing a feedback paradigm which can be wrapped around any latent matcher for improving its matching performance, and (iii) determining when feedback is actually necessary to improve latent matching accuracy. Experimental results show that integrating the proposed feedback paradigm with a state-of-the-art latent matcher improves its identification accuracy by 0.5-3.5 percent for NIST SD27 and WVU latent databases against a background database of 100k exemplars.

Latent fingerprints which are lifted from surfaces of objects at crime scenes play a very important role in identifying suspects in the crime scene investigations. Due to poor quality of latent fingerprints, automatic processing of latents can be extremely challenging. For this reason, latent examiners need to be involved in latent identification. To expedite the latent identification and alleviate subjectivity and inconsistency in latent examiners’ feature markups and decisions, there is a need to develop latent fingerprint identification systems that can operate in the “lights-out” mode. One of the most important steps in “lights-out” systems is to determine the quality of a given latent to predict the probability that the latent can be identified in a fully automatic manner. In this paper, we (i) propose a definition of latent value determination as a way of establishing the quality of latents based on a specific matcher’s identification performance, (ii) define a set of features based on ridge clarity and minutiae and evaluate them based on their capability to determine if a latent is of value for individualization or not, and (iii) propose a latent fingerprint image quality (LFIQ) that can be useful to reject the latents which cannot be successfully identified in the “lights-out” mode. Experimental results show that the most salient latent features include the average ridge clarity and the number of minutiae. The proposed latent quality measure improves the rank-100 identification rate from 69 % to 86 % by rejecting 50 % of latents deemed as poor quality. In addition, the rank-100 identification is 80 % when rejecting 80 % of the latents in the databases assessed as ‘NFIQ = 5’; however, the same identification rate can be achieved by rejecting only 21 % of the latents with low LFIQ.

With the availability of live-scan palmprint technology, high resolution palmprint recognition has started to receive significant attention in forensics and law enforcement. In forensic applications, latent palmprints provide critical evidence as it is estimated that about 30 percent of the latents recovered at crime scenes are those of palms. Most of the available high-resolution palmprint matching algorithms essentially follow the minutiae-based fingerprint matching strategy. Considering the large number of minutiae (about 1,000 minutiae in a full palmprint compared to about 100 minutiae in a rolled fingerprint) and large area of foreground region in full palmprints, novel strategies need to be developed for efficient and robust latent palmprint matching. In this paper, a coarse to fine matching strategy based on minutiae clustering and minutiae match propagation is designed specifically for palmprint matching. To deal with the large number of minutiae, a local feature-based minutiae clustering algorithm is designed to cluster minutiae into several groups such that minutiae belonging to the same group have similar local characteristics. The coarse matching is then performed within each cluster to establish initial minutiae correspondences between two palmprints. Starting with each initial correspondence, a minutiae match propagation algorithm searches for mated minutiae in the full palmprint. The proposed palmprint matching algorithm has been evaluated on a latent-to-full palmprint database consisting of 446 latents and 12,489 background full prints. The matching results show a rank-1 identification accuracy of 79.4 percent, which is significantly higher than the 60.8 percent identification accuracy of a state-of-the-art latent palmprint matching algorithm on the same latent database. The average computation time of our algorithm for a single latent-to-full match is about 141 ms for genuine match and 50 ms for impostor match, on a Windows XP desktop system with 2.2-GHz CPU and 1.00-GB RAM. The computation time of our algorithm is an order of magnitude faster than a previously published state-of-the-art-algorithm.

Traditional minutiae matching algorithms assume that each minutia has the same discriminability. However, this assumption is challenged by at least two facts. One of them is that fingerprint minutiae tend to form clusters, and minutiae points that are spatially close tend to have similar directions with each other. When two different fingerprints have similar clusters, there may be many well matched minutiae. The other one is that false minutiae may be extracted due to low quality fingerprint images, which result in both high false acceptance rate and high false rejection rate. In this paper, we analyze the minutiae discriminability from the viewpoint of global spatial distribution and local quality. Firstly, we propose an effective approach to detect such cluster minutiae which of low discriminability, and reduce corresponding minutiae similarity. Secondly, we use minutiae and their neighbors to estimate minutia quality and incorporate it into minutiae similarity calculation. Experimental results over FVC2004 and FVC-onGoing demonstrate that the proposed approaches are effective to improve matching performance.

Recent progress in fingerprint reconstruction has shown that most of the fingerprint information can be restored using only the minutia set. During the reconstruction procedures, orientation field reconstruction is a critical step. Proposed is a Gaussian weighted method for fingerprint orientation field reconstruction from the minutia template only. In the method, prior information about ridge flow characteristics is considered to more accurately model the ridge orientation. Experimental results show that our method can obtain an accurate orientation field in terms of the accuracy of the orientation field based fingerprint classification and the performance of the orientation descriptor based fingerprint matching.