现有 GAN 类指纹生成方法的主要瓶颈

Generating fingerprint images for biometric purposes is both necessary and challenging. In this study, we presented a fingerprint generation approach based on generative adversarial network. To ensure GAN training stability, we have introduced conditional loss doping that allows a continuous flow of gradients. Our study utilizes a careful combination of a residual network and spectral normalization to generate fingerprints. The proposed average residual connection shows more immunity against vanishing gradients than a simple residual connection. Spectral normalization allows our network to enjoy reduced variance in weight generation, which further stabilizes the training. Proposed scheme uses spectral bounding only in the input and the fully connected layers. Our network synthesized fingerprints up to 256 by 256 in size. We used the multi-scale structural similarity (MS-SSIM) metric for measuring the diversity of the generated samples. Our model has achieved 0.23 MS-SSIM scores for the generated fingerprints. The MS-SSIM score indicates that the proposed scheme is more likely to produce more diverse images and less likely to face mode collapse.

… adversarial network (GAN)-based approach to generate a large number of high-quality synthetic fingerprints that can retain the characteristics of authentic fingerprints. The specific …

Training fingerprint recognition models using synthetic data has recently gained increased attention in the biometric community as it alleviates the dependency on sensitive personal data. Existing approaches for fingerprint generation are limited in their ability to generate diverse impressions of the same finger, a key property for providing effective data for training recognition models. To address this gap, we present FPGAN-Control, an identity preserving image generation framework which enables control over the fingerprint’s image appearance (e.g., fingerprint type, acquisition device, pressure level) of generated fingerprints. We introduce a novel appearance loss that encourages disentanglement between the fingerprint’s identity and appearance properties. In our experiments, we used the publicly available NIST SD302 (N2N) dataset for training the FPGAN-Control model. We demonstrate the merits of FPGAN-Control, both quantitatively and qualitatively, in terms of identity preservation level, degree of appearance control, and low synthetic-to-real domain gap. Finally, training recognition models using only synthetic datasets generated by FPGAN-Control lead to recognition accuracies that are on par or even surpass models trained using real data. To the best of our knowledge, this is the first work to demonstrate this.

… have brought a significant change in the generation of synthetic biometric data. Synthetic biometric data finds applications in developing biometric systems and testing them on a large …

… GAN that are used for the synthetic generation of fingerprints. Critical investigation of underlying technological details of various GAN variants for generating synthetic … the generation of …

Real biometric fingerprint samples belong to the category of personal data, and therefore their usage for deep learning model training may have certain limitations. Artificially generated fingerprint images do not relate to a real person and can be used freely (“privacy-friendly”). Synthesized fingerprint samples are of interest for applied research: biological (papillary lines structure and alteration), forensic (computer fingerprint identification, reconstruction, and restoration of damaged samples), technological (various methods of biometric security). Generation of artificial fingerprints that accurately reproduce the textural features of real fingerprints could be a difficult task. In this paper, we present a deep learning framework — Adaptive Deep Convolutional Generative Adversarial Network (ADCGAN) — that we have developed and researched, and which has demonstrated the ability to generate realistic fingerprint samples that are similar to real ones in terms of their feature spectrum. ADCGAN makes it possible to conduct fingerprint research, without restrictions related to the confidential nature of biometric data.

… in various GAN models, we employ the random layer selection in the fingerprint generator. At … After the training of the fingerprint generator, we build the synthetic dataset containing the …

Synthetic biometric samples are created with an ultimate goal of getting around privacy concerns, mitigating biases in biometric datasets, and reducing the sample acquisition effort to enable large-scale evaluations. The recent breakthrough in the development of neural generative models shifted the focus from image synthesis by mathematical modeling of biometric modalities to data-driven image generation. This paradigm shift on the one hand greatly improves the realism of synthetic biometric samples and therefore enables new use cases, but on the other hand new challenges and concerns arise. Despite their realism, synthetic samples have to be checked for appropriateness for the tasks they are intended which includes new quality metrics. Focusing on sample images of fingerprint, face, iris and vascular patterns, we highlight the benefits of using synthetic samples, review the use cases, and summarize and categorize the most prominent studies on synthetic biometrics aiming at showing recent progress and the direction of future research.

… datasets such as biometric datasets including fingerprint, iris, … by training a GAN to generate synthetic fingerprint images. … we present the GAN model used for the fingerprint generation. …

… adversarial network (DC-GAN) based synthetic fingerprint generator is proposed.A modified … DC-GAN.The network is trained with 55,424 fingerprint data of five samples.Minutiae char- …

Large fingerprint datasets, while important for training and evaluation, are time‐consuming and expensive to collect and require strict privacy measures. Researchers are exploring the use of synthetic fingerprint data to address these issues. This article presents a novel approach for generating synthetic fingerprint images (both spoof and live), addressing concerns related to privacy, cost, and accessibility in biometric data collection. Our approach utilizes conditional StyleGAN2‐ADA and StyleGAN3 architectures to produce high‐resolution synthetic live fingerprints, conditioned on specific finger identities (thumb through little finger). Additionally, we employ CycleGANs to translate these into realistic spoof fingerprints, simulating a variety of presentation attack materials (e.g., EcoFlex, Play‐Doh). These synthetic spoof fingerprints are crucial for developing robust spoof detection systems. Through these generative models, we created two synthetic datasets (DB2 and DB3), each containing 1500 fingerprint images of all 10 fingers with multiple impressions per finger, and including corresponding spoofs in eight material types. The results indicate robust performance: our StyleGAN3 model achieves a Fréchet inception distance (FID) as low as 5, and the generated fingerprints achieve a true acceptance rate (TAR) of 99.47% at a 0.01% false acceptance rate (FAR). The StyleGAN2‐ADA model achieved a TAR of 98.67% at the same 0.01% FAR. We assess fingerprint quality using standard metrics (NFIQ2, MINDTCT), and notably, matching experiments confirm strong privacy preservation, with no significant evidence of identity leakage, confirming the strong privacy‐preserving properties of our synthetic datasets.

This paper reviews recent progress in fingerprint image generation using deep generative models, with a focus on Generative Adversarial Network (GAN)-based and diffusion-based approaches. Fingerprint data are essential for biometric recognition, but collecting large and diverse datasets is difficult, especially for latent fingerprints. Early methods based on physical or statistical modeling could not produce realistic textures or sufficient diversity. With the development of deep learning, GAN-based models such as FingerGAN, PrintsGAN, and lightweight GANs have significantly improved the realism of generated fingerprints by learning data distributions directly. These methods introduce techniques such as structural constraints, multi-stage generation, and improved loss functions to enhance image quality and stability. However, GAN-based models still suffer from problems such as training instability, mode collapse, and limited control over identity consistency. To address these issues, diffusion models have recently been introduced into fingerprint generation. By gradually denoising random noise, diffusion models can generate high-quality and diverse fingerprint images with better stability. Advanced diffusion frameworks further enable controllable generation, allowing users to adjust fingerprint attributes such as style, quality, and sensor type while preserving identity information. Overall, diffusion-based methods show strong potential to become the next generation of fingerprint synthesis techniques.

Generation of synthetic biometric samples such as, for instance, fingerprint images gains more and more importance especially in view of recent cross-border regulations on security of private data. The reason is that biometric data is designated in recent regulations such as the EU GDPR as a special category of private data, making sharing datasets of biometric samples hardly possible even for research purposes. The usage of fingerprint images in forensic research faces the same challenge. The replacement of real datasets by synthetic datasets is the most advantageous straightforward solution which bears, however, the risk of generating "unrealistic" samples or "unrealistic distributions" of samples which may visually appear realistic. Despite numerous efforts to generate high-quality fingerprints, there is still no common agreement on how to define "high-quality'' and how to validate that generated samples are realistic enough. Here, we propose general requirements on synthetic biometric samples (that are also applicable for fingerprint images used in forensic application scenarios) together with formal metrics to validate whether the requirements are fulfilled. Validation of our proposed requirements enables establishing the quality of a generative model (informed evaluation) or even the quality of a dataset of generated samples (blind evaluation). Moreover, we demonstrate in an example how our proposed evaluation concept can be applied to a comparison of real and synthetic datasets aiming at revealing if the synthetic samples exhibit significantly different properties as compared to real ones.

… Previous studies primarily employed Generative Adversarial Networks (GAN) for synthesizing latent fingerprints, leading to issues like mode collapse and unstable training. Recently, …

… generative models, starting with popular GAN architectures, and conducting fingerprint-to-fingerprint … To address challenges such as mode collapse and data imbalance, we build upon …

Over the past few years, there has been a proliferation of research in the area of generative adversarial networks (GANs). GANs present a novel approach to producing synthetic data in varying fields including medicine, traffic control, text transferring, image generation, and cybersecurity. To improve the quality of synthetic generation, specifically for images, the GAN technique was paired with convolutional neural networks (CNNs) to build deep convolutional generative adversarial networks (DCGAN). The DCGAN framework is a simple yet stable framework shown to generate quality photorealistic images. There are a number of studies reviewing GANs, providing a comparative analysis of performance, stabilization, and training methods. With respects to the DCGAN architecture, there are literature reviews reporting its usage in forensic sketch to face transformation and fuzzy face recognition. Here, we provide a review detailing the use of the DCGAN framework with biometrics samples for advancements in biometric authentication systems and cybersecurity. As GANs have shown to be a primary tool in generating deepfakes, we explore the use of DCGANs to generating synthetic biometrics that can deceive security systems and serve as quality training data for other machine learning models. The goal of this review is to contribute a concise consolidated review of techniques involving the DCGAN framework and biometric samples for the improvement of biometric recognition systems and to be used as a reference point for future work in cybersecurity.

Latent fingerprint enhancement is an essential preprocessing step for latent fingerprint identification. Most latent fingerprint enhancement methods try to restore corrupted gray ridges/valleys. In this paper, we propose a new method that formulates latent fingerprint enhancement as a constrained fingerprint generation problem within a generative adversarial network (GAN) framework. We name the proposed network FingerGAN. It can enforce its generated fingerprint (i.e, enhanced latent fingerprint) indistinguishable from the corresponding ground truth instance in terms of the fingerprint skeleton map weighted by minutia locations and the orientation field regularized by the FOMFE model. Because minutia is the primary feature for fingerprint recognition and minutia can be retrieved directly from the fingerprint skeleton map, we offer a holistic framework that can perform latent fingerprint enhancement in the context of directly optimizing minutia information. This will help improve latent fingerprint identification performance significantly. Experimental results on two public latent fingerprint databases demonstrate that our method outperforms the state of the arts significantly. The codes will be available for non-commercial purposes from https://github.com/HubYZ/LatentEnhancement.

Latent fingerprint reconstruction is a vital preprocessing step for its identification. This task is very challenging due to not only existing complicated degradation patterns but also its scarcity of paired training data. To address these challenges, we propose a novel generative adversarial network (GAN) based data augmentation scheme to improve such reconstruction. It translates the abundant clean fingerprints to their corresponding latent ones, only exploiting a small-scale latent dataset and an unpaired large-scale clean dataset, from which a large-scale paired clean-latent augmentation set is built for the reconstruction task. Specifically, our method models the distribution of the latent degradation patterns into a Gaussian one and generates latent fingerprints based on the sampled degradation patterns and clean fingerprints. Besides, we develop an auxiliary training procedure to stabilize training and further disentangle ridge structures and degradation patterns by regressing a latent fingerprint from its latent representation and its corresponding binarized fingerprint. Boosted by the proposed data augmentation, our reconstruction shows significant improvements in visual evaluation and fingerprint identification performance.

… reconstructed images do not look real either. This paper proposes an algorithm to reconstruct fingerprints from minutiae … The fingerprint reconstruction can be considered as an image-to-…

… , but the reconstructed fingerprint contains very few spurious minutiae. Specifically, a fingerprint … , this algorithm also generates many spurious minutiae in the reconstructed fingerprints. …

… by using the potential variables of GAN in the generated neural … that although fingerprint minutiae distribution seemed to be … ’s minutiae template was able to be used to reconstruct a …

Fingerprint recognition and indexing were addressed extensively in the literature. However, the number of the datasets that are used for research and validation is limited. Due to privacy laws and acts in several countries, it is challenging to release finger prints to the public. Consequently, this imposes a challenge on validating these search techniques on larger datasets that can be couple of hundreds of millions. To overcome this limitation, synthetic fingerprints datasets have been introduced as an alternative solution. In this paper we propose a generative model for synthesising fingerprint datasets. In this present work, the synthetic fingerprints are generated from the latent space representation using variational auto encoder. The network is trained to generate random samples that have same distribution as real finger print using latent vectors. By examining the generated synthetic fingerprints images, the ridge patterns were recognisable in most of cases. The unrecognisable synthetic images are reflecting the presence of low quality images in the training samples of the original dataset. Moreover, the extraction of minutiae relies on the quality of the input fingerprint images. In conclusion, the proposed method was able to generate synthetic image that can be further processed to accurately extract the finger minutiae and orientation field.

Given a full fingerprint image (rolled or slap), we present CycleGAN models to generate multiple latent impressions of the same identity as the full print. Our models can control the degree of distortion, noise, blurriness and occlusion in the generated latent print images to obtain Good, Bad and Ugly latent image categories as introduced in the NIST SD27 latent database. The contributions of our work are twofold: (i) demonstrate the similarity of synthetically generated latent fingerprint images to crime scene latents in NIST SD27 and MSP databases as evaluated by the NIST NFIQ 2 quality measure and recognition accuracies obtained by a SOTA fingerprint matcher, and (ii) use of synthetic latents to augment small-size latent training databases in the public domain to improve the performance of DeepPrint, a SOTA fingerprint matcher designed for rolled to rolled fingerprint matching on three latent databases (NIST SD27, NIST SD302, and IIITD-SLF). As an example, with synthetic latent data augmentation, the Rank-1 retrieval performance of DeepPrint is improved from 15.50% to 29.07% on challenging NIST SD27 latent database. Our approach for generating synthetic latent fingerprints can be used to improve the recognition performance of any latent matcher and its individual components (e.g., enhancement, segmentation and feature extraction). https://prip-lab.github.io/Synthetic-Latent-Fingerprint-Generator/

… of synthetic Latent fingerprint samples using GAN with pore-… best for generating synthetic latent fingerprint samples with … Latent space and style network are the integral components …

Deep learning is widely used in the field of biometrics, but a large amount of labeled image data is required to obtain a well-performing complicated model. Finger vein recognition has huge advantages over common biometric methods in terms of security and privacy. However, there are very few finger vein-related datasets. In order to solve this problem, this paper proposes a GAN-based finger vein dataset generation method, which is the first attempt in the domain of finger vein dataset generation by GAN. This paper generates a total of 53,630 images of 5,363 different subjects of finger veins and validates the synthetic dataset, which provides the basis for applying complex deep neural networks in the field of finger vein recognition.

… -GAN is used to generate fingerprint patches while training, thus augmenting the training dataset. The discriminator model of AC-GAN … Thus, the use of AC-GAN eradicates the necessity …

With the rapid growth of fingerprint-based biometric systems, it is essential to ensure the security and reliability of the deployed algorithms. Indeed, the security vulnerability of these systems has been widely recognized. Thus, it is critical to enhance the generalization ability of fingerprint presentation attack detection (PAD) cross-sensor and cross-material settings. In this work, we propose a novel solution for addressing the case of a single source domain (sensor) with large labeled real/fake fingerprint images and multiple target domains (sensors) with only few real images obtained from different sensors. Our aim is to build a model that leverages the limited sample issues in all target domains by transferring knowledge from the source domain. To this end, we train a unified generative adversarial network (UGAN) for multidomain conversion to learn several mappings between all domains. This allows us to generate additional synthetic images for the target domains from the source domain to reduce the distribution shift between fingerprint representations. Then, we train a scale compound network (EfficientNetV2) coupled with multiple head classifiers (one classifier for each domain) using the source domain and the translated images. The outputs of these classifiers are then aggregated using an additional fusion layer with learnable weights. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset. The experimental results show that the proposed method improves the average classification accuracy over twelve classification scenarios from 67.80 to 80.44% after adaptation.

Deep Fake Fingerprint Detection (DFFD) technique is ubiquitously deployed in automatic fingerprint identification systems (AFIS). Portable consumer electronics devices (PCED), such as smartphones, smart tablets, and PCs, also utilize fingerprint as a authentication method of AFIS. In recent years, the emergence of adversarial examples reveals the vulnerability of DNNs and weakens the credibility of PCED. Existing adversarial examples generally adopt perturbation addition, which lack robustness in the face of defensive measures such as adversarial training. Moreover, the perturbations used to deceive DFFD are easily perceived by human eyes. To address the above challenges, this paper proposes a novel generative adversarial fingerprint attack method for PCED. Firstly, to address the issue of poor robustness against defense strategies, this paper proposes a ridge texture rendering based generative adversarial network (RTRGAN) to perform robust generative adversarial fingerprint attack. Subsequently, to further enhance the visual quality of adversarial fingerprints, the realistic ridge texture is assigned by comparing the feature similarity between real fingerprints and adversarial fingerprints. Finally, this paper designs a joint optimization loss function, including the discriminator loss and the adversarial loss, to balance the attack robustness and visual fidelity. Extensive experiments demonstrate that compared with traditional perturbation-based methods, the proposed scheme significantly improves the attack success rate, has remarkable robustness, and generates more realistic adversarial fingerprints to human perception.

Performance evaluation of fingerprint recognition systems requires large-scale databases. Unfortunately, collecting fingerprints is expensive and time-consuming, and publishing them is restricted due to the privacy protection legislation. Hence, an algorithm which can generate huge fingerprint datasets would be of great help. With the popularization of fingerprint authentication systems, detecting fake fingerprints, also known as presentation attack detection, is an essential problem. Inspired by the fast development of deep learning, this paper demonstrates novel algorithms to generate artificial fingerprints and detect fake fingerprints using deep neural networks. The experimental results prove that the proposed system can generate fingerprints which have the same characteristics as real fingerprints. Regarding presentation attack detection, the proposed system shows an average detection error rate of 1.57% on three LivDet databases, including LivDet 2011, 2013, and 2015.

Optical Coherence Tomography (OCT) is a high-resolution, non-invasive imaging technology increasingly used for biometric data collection from fingertips. OCT captures volume data up to 3mm below the skin surface in the form of a series of B-scan images, enabling the reconstruction of internal fingerprints (IF) and internal sweat pores (ISP), thereby enhancing the security of biometric recognition. Despite the advantages, OCT images suffer from speckle noise and tissue discontinuity, making the extraction of subcutaneous biometric features challenging. Traditional hardware and software-based enhancement methods often result in over-smoothing and structural loss. Recent advancements in deep learning (DL) offer promising alternatives, with supervised DL methods showing efficacy when trained with high-quality paired datasets. However, the absence of ground-truth (GT) data makes it impossible to apply these models. This study proposes a novel supervised enhancement method for fingertip OCT images, with a paired dataset generation strategy. An OCT few-shot GAN and a Quality Estimation Module are proposed and incorporated into the strategy to realize translation from minimal GT manual augmentation to high-quality paired dataset, effectively addressing the challenge of data scarcity. A Fast Supervised Enhancement GAN (FSE-GAN) is proposed thereafter to perform simultaneous speckle noise reduction and tissue structure restoration, facilitating accurate extraction of internal fingerprints and sweat pores. Experiments demonstrate that the enhanced images significantly simplify IF and ISP extraction while achieving outstanding result quality.

… fundamentals of latent fingerprinting and a review of AI-based latent fingerprint systems with … latent fingerprint datasets along with the methods for synthetic fingerprint generation using …