High-resolution Fingerprint Images Research Articles

A Novel High-Resolution Fingerprint Representation Method

Current high-resolution fingerprints are almost entirely represented by sweat pores, resulting in information loss and weak robustness. This is caused by dividing fingerprint representation into pore detection and pore representation. This paper proposes a novel high-resolution fingerprint representation method for recognition based on only one fully convolutional network. By guiding the network to learn the most discriminative representation (i.e., sweat pores) and to reconstruct the original fingerprint image, pore maps and hidden features are provided simultaneously to represent the high-resolution fingerprint image for the subsequent direct matching process. The experimental results, which are evaluated on the public PolyU pore database, show that the best average <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R_{T}$ </tex-math></inline-formula> , which is 94.88%, can be obtained using our proposed method. In addition, the recognition results show that our proposed method achieves matching equal error rates (EERs) of 5.55% and 1.27% on the PolyU DBI and DBII databases, respectively, which is better than other pore detection methods when using the same matching method. Compared with the latest DeepPoreID method which split fingerprint representation into pore extraction and pore representation, our approach improves the EER by up to 50.98% when evaluated on an in-house database, further demonstrating the outstanding generalization ability of the proposed method.

Cross-Sensor Pore Detection in High-Resolution Fingerprint Images

With the emergence of high-resolution fingerprint sensors, there has been a lot of focus on level-3 fingerprint features, especially the pores, for the next generation automated fingerprint recognition systems (AFRS). Following the success of deep learning in various computer vision tasks, researchers have developed learning-based approaches for detection of pores in high-resolution fingerprint images. Generally, learning-based approaches provide better performance than hand-crafted feature-based approaches. However, domain adaptability of the existing learning-based pore detection methods has never been studied. In this paper, we study this aspect and propose an approach for pore detection in cross-sensor scenarios. For this purpose, we have generated an in-house 1000 dpi fingerprint dataset with ground truth pore coordinates (referred to as IITI-HRFP-GT), and evaluated the performance of the existing learning-based pore detection approaches. The core of the proposed approach for detection of pores in cross-sensor scenarios is DeepDomainPore, which is a residual learning-based convolutional neural network (CNN) trained for pore detection. The domain adaptability in DeepDomainPore is achieved by embedding a gradient reversal layer between the CNN and a domain classifier network. The proposed approach achieves state-of-the-art performance in a cross-sensor scenario involving public high-resolution fingerprint datasets with 88.12% true detection rate and 83.82% F-score.

Fast Pore Comparison for High Resolution Fingerprint Images Based on Multiple Co-Occurrence Descriptors and Local Topology Similarities

Pore-based fingerprint recognition has been researched for decades. Many algorithms have been proposed to improve the recognition accuracy of the system. However, the accuracies are always improved at the cost of speed. This article proposes a novel method to compare the pores in high-resolution fingerprint images using the popular coarse-to-fine strategy. A multiple spatial pairwise local co-occurrence descriptor is proposed to improve the calculation of the similarities between pores. It calculates multiple local co-occurrence statistics for each pore using its neighbors. The proposed method can establish correspondences between pores more accurately. The refinement of the correspondences is then achieved by using a local topology-preserving matching algorithm. The algorithm uses rotational invariant local structures and pore pair local topology similarities to calculate the cost of each correspondence. It can remove the mismatches more accurately and efficiently. The experimental results on two high-resolution fingerprint image databases show that the proposed algorithm perform well in both accuracy and speed comparing to the existing algorithms.

Fingerprint pores extraction by using automatic scale selection

Extraction of fingerprint sweat pores is a critical step in those applications which are based on highly secured features. Pores are varying in scale (size) and evenly distributed along the ridges. It is the main challenge to design a technique which determines the pores of different sizes in the fingerprint image. In this paper, pore extraction algorithm is proposed for high-resolution fingerprint images which utilised multiscale γ-normalised Laplacian of Gaussian (LoG) filter. A block-wise approach is implemented in which each region is filtered at multiple scale values. Scale space theory is applied and candidate pixels of high negative response are identified through local maxima approach. The efficacy of the proposed algorithm is tested by measuring average true detection rate (TDR) and average false detection rate (FDR). Results of the proposed algorithm achieve average TDR and average FDR values as 82.89% and 21.2% respectively which are better in comparison to the state-of-art techniques.

Fingerprint pores extraction by using automatic scale selection

Extraction of fingerprint sweat pores is a critical step in those applications which are based on highly secured features. Pores are varying in scale (size) and evenly distributed along the ridges. It is the main challenge to design a technique which determines the pores of different sizes in the fingerprint image. In this paper, pore extraction algorithm is proposed for high-resolution fingerprint images which utilised multiscale γ-normalised Laplacian of Gaussian (LoG) filter. A block-wise approach is implemented in which each region is filtered at multiple scale values. Scale space theory is applied and candidate pixels of high negative response are identified through local maxima approach. The efficacy of the proposed algorithm is tested by measuring average true detection rate (TDR) and average false detection rate (FDR). Results of the proposed algorithm achieve average TDR and average FDR values as 82.89% and 21.2% respectively which are better in comparison to the state-of-art techniques.

Fingerprint Pore Comparison Using Local Features and Spatial Relations

High-resolution fingerprint recognition has been a hot topic for many years. Compared with a traditional fingerprint image, a high-resolution fingerprint image can provide more features, such as pores and ridge contours. Introducing these features into fingerprint comparison and recognition can improve the recognition accuracy and reduce the risk of identification errors. This paper proposes a novel method for comparing pores on high-resolution fingerprint images. The method can be divided into two steps. In the first step, fingerprints are aligned using the pixel-category-distance-based data-driven descending algorithm. Traditionally, fingerprints are aligned based on feature points, such as minutiae and singular points. Such alignment methods are not suitable when dealing with partial fingerprints because small overlapping areas often do not contain enough features to guarantee a correct alignment. In this research, the ridges and valleys on fingerprints are used in combination with the orientation field for alignment. The proposed algorithm performs well when aligning both partial and full fingerprints. The common areas between the two images can be estimated based on the alignment result. In the second step, pores lying in the common areas are selected for comparison. To improve the comparison accuracy, pores are compared using local features and spatial relations. A graph comparison algorithm is designed in this step. The experimental results show that the proposed method is more accurate than other state-of-the-art pore comparison algorithms.

High resolution fingerprint recognition using pore and edge descriptors

Pores have been used for fingerprint recognition for many years. Introducing pores into fingerprint image comparison can improve the recognition accuracy. This paper proposes a novel method to compare pores on high resolution fingerprint images. The method consists of three steps. In the first step, pores on different images are clustered using a Root-SIFT descriptor. Then the pores in the same class will be compared using a rotational invariant edge descriptor and Hough transform. The descriptor consists of three parts: the length of the edge, the angles between the edge and the orientations of pores, and the angle between the orientations of pores. In the final step, one-to-one correspondences of pores are established based on the matched edges, and then refined using the spatial relations of the pores. To this end, a graph based refinement algorithm is designed. Experimental results on two high resolution fingerprint image databases show that the proposed algorithm is more accurate than other state-of-the-art pore comparison algorithms.

Pore detection in high-resolution fingerprint images using deep residual network

This letter presents a residual learning-based convolutional neural network, referred to as DeepResPore, for detection of pores in high-resolution fingerprint images. Specifically, the proposed DeepResPore model generates a pore intensity map from the input fingerprint image. Subsequently, the local maxima filter is operated on the pore intensity map to identify the pore coordinates. The results of our experiments indicate that the proposed approach is effective in extracting pores with a true detection rate of 94:49% on Test set I and 93:78% on Test set II of the publicly available PolyU HRF dataset. Most importantly, the proposed approach achieves state-of-the-art performance on both test sets.

Pore-based indexing for fingerprints acquired using high-resolution sensors

With the advent of high-resolution fingerprint sensors, there have been efforts to develop high-resolution fingerprint identification systems. In this paper, we present an indexing method for high-resolution fingerprints using pore-based features. In the proposed approach, the dynamic pore filtering method is employed to extract pores from high-resolution fingerprint images. The extracted pores are treated as keypoints, and a pore descriptor is computed for each of the keypoints. The pore descriptor thus obtained is used as a feature vector for indexing. Finally, a cluster-based retrieval scheme is employed for fast and effective retrieval of the candidate list. Performance of the proposed approach has been evaluated on the Hong Kong PolyU high-resolution fingerprint databases, DBI and DBII and in-house databases, IITI-HRFP and IITI-HRF. The proposed indexing approach achieves an improvement of 67%, 49%, 42% and 28% points in pre-selection error rate (for penetration rate of 10%) over the existing method that employs pore features for indexing on DBI, DBII, IITI-HRFP and IITI-HRF, respectively. Most importantly, our approach provides better performance than the state-of-the-art minutiae-based fingerprint indexing algorithm on DBI and IITI-HRFP, which contain partial fingerprints.

A New Framework for Quality Assessment of High-Resolution Fingerprint Images

The quality assessment of sets of features extracted from patterns of epidermal ridges on our fingers is a biometric challenge problem with implications on questions concerning security, privacy and identity fraud. In this work, we introduced a new methodology to analyze the quality of high-resolution fingerprint images containing sets of fingerprint pores. Our approach takes into account the spatial interrelationship between the considered features and some basic transformations involving point process and anisotropic analysis. We proposed two new quality index algorithms following spatial and structural classes of analysis. These algorithms have proved to be effective as a performance predictor and as a filter excluding low-quality features in a recognition process. The experiments using error reject curves show that the proposed approaches outperform the state-of-the-art quality assessment algorithm for high-resolution fingerprint recognition, besides defining a new method for reconstructing their friction ridge phases in a very consistent way.

FINGERPRINT MATCHING BASED ON PORE CENTROIDS

In recent years there has been exponential growth in the use of biometrics for user authentication applications. Automated Fingerprint Identification systems have become popular tool in many security and law enforcement applications. Most of these systems rely on minutiae (ridge ending and bifurcation) features. With the advancement in sensor technology, high resolution fingerprint images (1000 dpi) provide micro level of features (pores) that have proven to be useful features for identification. In this paper, we propose a new strategy for fingerprint matching based on pores by reliably extracting the pore features The extraction of pores is done by Marker Controlled Watershed segmentation method and the centroids of each pore are considered as feature vectors for matching of two fingerprint images. Experimental results shows that the proposed method has better performance with lower false rates and higher accuracy.

Level 3 friction ridge research

Forensic examiners in law enforcement analyse fingerprint microfeatures, such as sweat pores and ridge contours, to compare fingerprint samples when insufficient minutia points are present in the fingerprint image or poor image quality hampers minutiae analysis. Automation of such analysis has been inhibited by the low resolution of conventional fingerprint imaging and the lack of software capable of extracting and matching microfeature data. The declining cost of high resolution fingerprint capture technology has brought the need for software that takes advantage of the Level 3 feature set to the attention of the law enforcement practitioners, says Michael Chaberski, senior engineer at International Biometric Group (IBG). A software research toolkit for extraction of Level 3 features has now been made available to the public. Evaluation of the software over a dataset of high resolution fingerprint images has demonstrated that analysis of Level 3 features can reduce error rates in automated matching of fingerprint fragment images. Biometric engineers and forensic researchers are encouraged to use the toolkit to optimise microfeature analysis techniques for incorporation into the next generation of fingerprint software.