Performance evaluation of 2D to 3D fingerprint recognition

In this paper, we propose an innovative approach to improve the performance of an Automatic Fingerprint Identification System (AFIS). The method is based on the design of a Possibilistic Fingerprint Quality Assessment (PFQA) filter where ground truths of fingerprint images of effective and ineffective quality are built by learning. The first approach, QS_I, is based on the AFIS decision for the image without considering its paired image to decide its effectiveness or ineffectiveness. The second approach, QS_PI, is based on the AFIS decision when considering the pair (effective image, ineffective image). The two ground truths (effective/ineffective) are used to design the PFQA filter. PFQA discards the images for which the AFIS does not generate a correct decision. The proposed intervention does not affect how the AFIS works but ensures a selection of the input images, recognizing the most suitable ones to reach the AFIS’s highest recognition rate (RR). The performance of PFQA is evaluated on two experimental databases using two conventional AFIS, and a comparison is made with four current fingerprint image quality assessment (IQA) methods. The results show that an AFIS using PFQA can improve its RR by roughly 10% over an AFIS not using an IQA method. However, compared to other fingerprint IQA methods using the same AFIS, the RR improvement is more modest, in a 5–6% range.

Removal of digitization errors in fingerprint ridgelines using B-splines

Fingerprint segmentation is an important pre-processing step in automatic fingerprint identification system. Traditional fingerprint segmentation methods either highly depend on empirical thresholds sophistically chosen by experts or a learned model trained by elements generated from manually segmented fingerprints. It is manpower and time consuming. They always try their best to tune their fingerprint segmentation methods to be universal to all unseen fingerprints. However, one fingerprint may have a significantly distinct distribution from another in feature space because fingerprint acquisition is affected by several factors, such as pressure, the types of sensors, finger tip condition (dry, wet etc.). As a result, the delicate threshold and the well trained model may not be suitable to the new input fingerprints from a new finger or a new person. And it makes worse when automatic fingerprint identification systems meet sensor interoperability. To solve the problem, we propose a personalized fingerprint segmentation method: Automatic Labeling based Linear Neighborhood Propagation (ALLNP), which learns a segmentation model special for each input fingerprint image based on the input image only. The proposed method is tested with typical fingerprint images from four heterogeneous data bases of FVC2000. Experimental results show its effectiveness and encouraging strength when fingerprint segmentation meets sensor interoperability.

Sweat pores on the human fingertip have meaningful patterns that enable individual identification. Although conventional automatic fingerprint identification systems (AFIS) have mainly employed the minutiae features to match fingerprints, there has been minimal research that uses sweat pores to match fingerprints. Recently, high-resolution optical sensors and pore-based fingerprint systems have become available, which motivates research on pore analysis. However, most existing pore-based AFIS methods use the minutia-ridge information and image pixel distribution, which limit their applications. In this context, this paper presents a stable pore matching algorithm which effectively removes both the minutia-ridge and fingerprint-device dependencies. Experimental results show that the proposed pore matching algorithm is more accurate for general fingerprint images and robust under noisy conditions compared with existing methods. The proposed method can be used to improve the performance of AFIS combined with the conventional minutiae-based methods. Since sweat pores can also be observed using various systems, removing of the fingerprint-device dependency will make the pore-based AFIS useful for wide applications including forensic science, which matches the latent fingerprint to the fingerprint image in databases.

Human finger is a three-dimensional object. More real and more fingerprint features will be provided if 3D fingerprint images are available. This chapter thus explores 3D fingerprint features and their applications for personal identification. We define the 3D finger structural features, such as curve-skeleton, sectional curvatures as Level Zero Fingerprint Features in this chapter and investigate their distinctiveness for personal identification. These features are also used to assist fingerprint matching and make contribution to fingerprint recognition by combining with 2D fingerprint features. A series of experiments is conducted to evaluate 3D fingerprint recognition technique based on our established database with 541 fingers. Results show that an accuracy of 84.7 % can be achieved when using 3D curve-skeleton for recognition. The sectional curvatures can be used for human gender classification and an accuracy of 81 % is obtained in our database. An EER of 3.4 % is realized by including Level Zero Features into fingerprint recognition which demonstrates the effectiveness of 3D fingerprint recognition.

Fingerprint recognition systems have important applications for privacy and security. This has led to more studies and technologies that improve on the security and accuracy of fingerprint identification and verification systems. Such improvements and studies involve the application of three-dimensional (3D) fingerprint systems, where the details of the finger are captured using 3D technologies and the captured 3D fingerprints are converted into two-dimensional (2D) fingerprints. This paper presents a brief survey on different methods that are used to unwrap 3D fingerprint images into 2D fingerprint images, compare them on the effects of distortion and analyses two promising methods. The aim of this survey is to investigate complexity and properties of non-parametric methods so that they can be easily applied on different fingerprint identification and verification systems.

The accuracy of Automatic Fingerprint Identification Systems (AFIS) is dependent on many variables ranging from the quality of the friction skin surface itself, to the ability of the image acquisition device to accurately image the fingerprint, to the feature extraction and matching software to detect the feature set and declare a correlation (a match/no match) based on some criteria. The genesis of these systems exclusively used rolled impression fingerprint imagery. As AFIS developers attempted to reduce the cost and improve the usability of these systems for commercial applications, plain impression imagery was adopted and total scanned image area was significantly reduced. This paper will quantify the effects of reduced image area on overall system accuracy in a single finger plain impression environment.

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.

SummaryWith the improvement of informatization and the development of computer technology, identity recognition with fingerprint has been the growing trend, but the stained fingerprint will make recognition difficult. To solve the above problem, this paper briefly introduced the traditional point matching fingerprint recognition algorithm and the damaged fingerprint recognition method based on the convolution neural network (CNN). Then in MATLAB software, the damaged fingerprint recognition method based on CNN was simulated and compared with the traditional point matching recognition method and traditional CNN recognition method. The results showed that the improved CNN recognition method iterated fewer times and achieved smaller training error during the training; the improved CNN method had lower false recognition rate and rejection rate in identifying the unknown fingerprint; the traditional point matching method spent the most time in identifying the unknown fingerprint, followed by the traditional CNN method and the improved CNN recognition method. This study used CNN for fingerprint recognition and improved CNN to improve its recognition accuracy for the damaged fingerprint. The improved CNN can effectively enhance the recognition accuracy of the damaged fingerprint, which provides a useful reference for the improvement of the accuracy and applicability of the fingerprint recognition system.

Post-mortem fingerprints are a valuable biometric used to aid in the identification of a deceased individual. However, fingerprints from the deceased undergo decomposition leading to indefinite structure when compared to ante-mortem fingerprints. Moreover, the performance of the existing two-dimensional (2D) fingerprint recognition systems is still below the expected potential. These problems arise because fingerprints are generally captured by manipulating a finger against a plane. In post-mortem fingerprint recovery, the decedent's finger must go through several reconditioning processes to prevent the rapid onslaught of decomposition. To address these deficiencies associated with the 2D systems, three-dimensional (3D) scanning systems have been employed to capture fingerprints. The 3D technology is still in its transient phase and is limited primarily by 1) the lack of existing 3D databases; 2) the deficiency of 3D-to-2D fingerprint image mapping algorithms, 3) the incapacity to model and recreate the 2D fingerprint capturing procedure to improve 3D-2D fingerprint verification; and 4) the inability to apply traditional fingerprint unrolling techniques on post-mortem 3D fingerprints. This paper presents a novel method to perform post-mortem 3D fingerprint unrolling and pressure simulation to produce fingerprint images that are compatible with 2D fingerprint recognition systems. The thrust of this paper strives to: 1) develop a correspondence between 3D touchless and contact-based 2D fingerprint images; 2) model fingerprints with deformities to provide a viable fingerprint image for matching and; 3) develop a mosaic pressure simulation (MPS) algorithm to recreate the effects of 2D fingerprint capturing procedure.

Fingerprint recognition has widespread security applications owing to its uniqueness, permanence, and simplicity in capture. However, conventional fingerprint authentication systems face high false acceptance and rejection rates and susceptibility to spoofing attacks. To address these issues, this study proposes a deep learning-based fingerprint authentication system using a Convolutional Neural Network (CNN) with five convolution layers to derive robust spatial features. The model was trained and cross-validated on the SOCOFing dataset with regularization and data augmentation to enhance generalization and spoof resistance. Experimental results show that the proposed CNN achieved a training accuracy of 99.10% with a loss of 0.0223 and a validation accuracy of 98.89% with a loss of 0.0114. Moreover, the model maintained a low false acceptance rate of 0.33% and false rejection rate of 0.25%, demonstrating its efficacy and credibility for secure and real-time biometric authentication. A rigorous comparison with conventional CNN models and DCCN architectures confirmed that the proposed model provides higher accuracy, lower computational cost, and stronger resistance to spoofing attacks. These findings indicate that the proposed system successfully addresses existing limitations and offers a practical, scalable, and reliable solution for fingerprint verification using deep CNN architectures.

Contactless fingerprint recognition is highly promising and an essential component in the automatic fingerprint identification system. However, due to the inherent characteristic of perspective distortions of contactless fingerprints, achieving a highly accurate contactless fingerprint recognition system is very challenging. In this paper, we propose a robust contactless fingerprint recognition method based on global minutia topology and loose genetic algorithm. In order to avoid the inaccurate minutiae alignment problem suffered in conventional transformation-based methods, the minutiae correspondence is established by optimizing an energy function of the similarity matrix. We define an innovative similarity matrix based on both minutiae and minutia-pairs, which takes the global minutia topology into account. By adopting a distortion-free feature of ridge count to define the similarity, the problem of perspective distortions is effectively overcome. To solve the optimization, we propose a new genetic algorithm (GA) named loose GA with new mutation and crossover operators. We also propose a strict minutia-pair expanding algorithm to enhance the reliability of the minutiae correspondence. For recognition, a metric for measuring comparison scores which takes advantage of both the global topological similarity and the number of corresponding minutiae is proposed. We evaluate our method using two contactless fingerprint benchmark databases and achieve competitive performances in comparison with the state-of-the-art methods.

An evaluation of fake fingerprint databases utilizing SVM classification

3D fingerprint imaging system based on full-field fringe projection profilometry

Biometrics is used to identify individual in groups by their characteristics, such as fingerprint, face, iris, voice and behavioral characteristics like hand written signature and keystroke. Normally, a majority of biometrics recognition systems adopt methods by using unique feature to discriminate different individual from groups. But there is some forgery, subjective modifications like making up exiting as usual. A multimodal biometric recognition systemusing multiple biometrics to identify is proposed. In addition, it can support better Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR) by combining two or more physical or behavioral features. With lots of approached have been proposed, experts also pay much attention to the methods mentioned in recent years. The objective of this paper is to support a survey of multimodal biometric recognition system and approach using face, fingerprint recognition and enhanced iris characters that commonly used recently.