扩散模型用于指纹生成

The utilization of synthetic data for fingerprint recognition has garnered increased attention due to its potential to alleviate privacy concerns surrounding sensitive biometric data. However, current methods for generating fingerprints have limitations in creating impressions of the same finger with useful intra-class variations. To tackle this challenge, we present GenPrint, a framework to produce fingerprint images of various types while maintaining identity and offering humanly understandable control over different appearance factors, such as fingerprint class, acquisition type, sensor device, and quality level. Unlike previous fingerprint generation approaches, GenPrint is not confined to replicating style characteristics from the training dataset alone: it enables the generation of novel styles from unseen devices without requiring additional fine-tuning. To accomplish these objectives, we developed GenPrint using latent diffusion models with multimodal conditions (text and image) for consistent generation of style and identity. Our experiments leverage a variety of publicly available datasets for training and evaluation. Results demonstrate the benefits of GenPrint in terms of identity preservation, explainable control, and universality of generated images. Importantly, the GenPrint-generated images yield comparable or even superior accuracy to models trained solely on real data and further enhances performance when augmenting the diversity of existing real fingerprint datasets.

The majority of contemporary fingerprint synthesis is based on the Generative Adversarial Network (GAN). Recently, the Denoising Diffusion Probabilistic Model (DDPM) has been demonstrated to be more effective than GAN in numerous scenarios, particularly in terms of diversity and fidelity. This research develops a model based on the enhanced DDPM for fingerprint generation. Specifically, the image is decomposed into sub-images of varying frequency sub-bands through the use of a wavelet packet transform (WPT). This method enables DDPM to operate at a more local and detailed level, thereby accurately obtaining the characteristics of the data. Furthermore, a polynomial noise schedule has been designed to replace the linear noise strategy, which can result in a smoother noise addition process. Experiments based on multiple metrics on the datasets SOCOFing and NIST4 demonstrate that the proposed model is superior to existing models.

This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual tokenizers improves reconstruction quality, it requires substantially larger diffusion models and more training iterations to achieve comparable generation performance. Consequently, existing systems often settle for suboptimal solutions, either producing visual artifacts due to information loss within tokenizers or failing to converge fully due to expensive computation costs. We argue that this dilemma stems from the inherent difficulty in learning unconstrained high-dimensional latent spaces. To address this, we propose aligning the latent space with pretrained vision foundation models when training the visual tokenizers. Our proposed VA-VAE (Vision foundation model Aligned Variational AutoEncoder) significantly expands the reconstruction-generation frontier of latent diffusion models, enabling faster convergence of Diffusion Transformers (DiT) in high-dimensional latent spaces. To exploit the full potential of VA-VAE, we build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT. The integrated system achieves state-of-the-art (SOTA) performance on ImageNet 256×256 generation with an FID score of 1.35 while demonstrating remarkable training efficiency by reaching an FID score of 2.11 in just 64 epochs – representing an over 21× convergence speedup compared to the original DiT. Models and codes are available at https://github.com/hustvl/LightningDiT.

Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored by human evaluators to those from DALL-E, even when the latter uses expensive CLIP reranking. Additionally, we find that our models can be fine-tuned to perform image inpainting, enabling powerful text-driven image editing. We train a smaller model on a filtered dataset and release the code and weights at https://github.com/openai/glide-text2im.

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned through recent self-supervised learning methods. We argue that one main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations. Moreover, training can be made easier by incorporating high-quality external visual representations, rather than relying solely on the diffusion models to learn them independently. We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders. The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs. For instance, our method can speed up SiT training by over 17.5$\times$, matching the performance (without classifier-free guidance) of a SiT-XL model trained for 7M steps in less than 400K steps. In terms of final generation quality, our approach achieves state-of-the-art results of FID=1.42 using classifier-free guidance with the guidance interval.

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a given reference set and synthesize novel renditions of them in different contexts. In this work, we present a new approach for “personalization” of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. Once the subject is embedded in the output domain of the model, the unique identifier can be used to synthesize novel photorealistic images of the subject contextualized in different scenes. By leveraging the semantic prior embedded in the model with a new autogenous class-specific prior preservation loss, our technique enables synthesizing the subject in diverse scenes, poses, views and lighting conditions that do not appear in the reference images. We apply our technique to several previously-unassailable tasks, including subject recontextualization, text-guided view synthesis, and artistic rendering, all while preserving the subject's key features. We also provide a new dataset and evaluation protocol for this new task of subject-driven generation. Project page: https://dreambooth.github.io/

We present novel approaches involving generative adversarial networks and diffusion models in order to synthesize high quality, live and spoof fingerprint images while preserving features such as uniqueness and diversity. We generate live fingerprints from noise with a variety of methods, and we use image translation techniques to translate live fingerprint images to spoof. To generate different types of spoof images based on limited training data we incorporate style transfer techniques through a cycle autoencoder equipped with a Wasserstein metric along with Gradient Penalty (CycleWGAN-GP) in order to avoid mode collapse and instability. We find that when the spoof training data includes distinct spoof characteristics, it leads to improved live-to-spoof translation. We assess the diversity and realism of the generated live fingerprint images mainly through the Fr\'echet Inception Distance (FID) and the False Acceptance Rate (FAR). Our best diffusion model achieved a FID of 15.78. The comparable WGAN-GP model achieved slightly higher FID while performing better in the uniqueness assessment due to a slightly lower FAR when matched against the training data, indicating better creativity. Moreover, we give example images showing that a DDPM model clearly can generate realistic fingerprint images.

The progress of fingerprint recognition applications encounters substantial hurdles due to privacy and security concerns, leading to limited fingerprint data availability and stringent data quality requirements. This article endeavors to tackle the challenges of data scarcity and data quality in fingerprint recognition by implementing data augmentation techniques. Specifically, this research employed two state-of-the-art generative models in the domain of deep learning, namely Deep Convolutional Generative Adversarial Network (DCGAN) and the Diffusion model, for fingerprint data augmentation. Generative Adversarial Network (GAN), as a popular generative model, effectively captures the features of sample images and learns the diversity of the sample images, thereby generating realistic and diverse images. DCGAN, as a variant model of traditional GAN, inherits the advantages of GAN while alleviating issues such as blurry images and mode collapse, resulting in improved performance. On the other hand, Diffusion, as one of the most popular generative models in recent years, exhibits outstanding image generation capabilities and surpasses traditional GAN in some image generation tasks. The experimental results demonstrate that both DCGAN and Diffusion can generate clear, high-quality fingerprint images, fulfilling the requirements of fingerprint data augmentation. Furthermore, through the comparison between DCGAN and Diffusion, it is concluded that the quality of fingerprint images generated by DCGAN is superior to the results of Diffusion, and DCGAN exhibits higher efficiency in both training and generating images compared to Diffusion.

Biometric authentication is important for security and human device interaction, however, problems of fingerprint loss attributable to medical conditions, privacy issues and scarcity of data prevent widespread adoption. In this research, we present an AI based solution to the issue of generating synthetic fingerprint using T-SFG framework, where we solve the problem of biometric availability, privacy protection and ethical data handling. It differs from classic methods based on the presence of private biometric data and does not require storage or processing of such data, which is compliant with privacy regulations such as GDPR and HIPAA. Synthetic fingerprint generation also helps in data augmentation, which allows for generating diverse and representative datasets to make models robust and reduce bias in diverse demographics. The results of this technique are significantly cheaper and faster than in the real world, while being able to generate scaled dataset. Additionally, these factors enable the proposed framework to improve the modularity of authentication technologies in different conditions, give stress testing to biometric systems for security holes, and helps sync that AI model training by simulating uncommon and broad constraints. The experimental results show that T-SFG can produce high quality synthetic fingerprints for biometric applications, privacy focused authentication and for the development of artificial skin or prosthetic limbs with fingerprint ridges for improved touchscreen interaction. The results show that synthetic biometric data can also help the research, innovation and regulatory compliant solutions and more secure, accessible and ethical biometric technologies.

No abstract available

This paper presents a comprehensive data reliability testing framework for evaluating synthetic biometric data, addressing privacy concerns in fingerprint and iris recognition systems. This unified and modality-independent methodology establishes six quantitative metrics: randomness, quality similarity, attribute similarity, non-duplication, ID-preservation, and geometric diversity. The framework is implemented through a novel RD-Net architecture consisting of a Random Network for privacy protection and a Deterministic Network for maintaining essential biometric characteristics. Experiments using public datasets (FVC 2002, IITDelhi-Iris, and CASIA-Iris-V4) demonstrate that synthetic samples maintain high dissimilarity from source datasets while preserving their structural properties. The synthetic biometric data generated through the proposed Random Network and Deterministic Network architectures are evaluated using the data reliability testing framework, confirming distribution similarity with real data across all proposed metrics and achieving scores over 80. This approach offers a method for generating and evaluating synthetic biometric data that balances privacy protection with functional validity in biometric system development and testing.

Biometric fingerprint identification hinges on the reliability of its sensors; however, calibrating and standardizing these sensors poses significant challenges, particularly in regards to repeatability and data diversity. To tackle these issues, we propose methodologies for fabricating synthetic 3D fingerprint targets, or phantoms, that closely emulate real human fingerprints. These phantoms enable the precise evaluation and validation of fingerprint sensors under controlled and repeatable conditions. Our research employs laser engraving, 3D printing, and CNC machining techniques, utilizing different materials. We assess the phantoms’ fidelity to synthetic fingerprint patterns, intra-class variability, and interoperability across different manufacturing methods. The findings demonstrate that a combination of laser engraving or CNC machining with silicone casting produces finger-like phantoms with high accuracy and consistency for rolled fingerprint recordings. For slap recordings, direct laser engraving of flat silicone targets excels, and in the contactless fingerprint sensor setting, 3D printing and silicone filling provide the most favorable attributes. Our work enables a comprehensive, method-independent comparison of various fabrication methodologies, offering a unique perspective on the strengths and weaknesses of each approach. This facilitates a broader understanding of fingerprint recognition system validation and performance assessment.

No abstract available

No abstract available

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.

No abstract available

The advancement of fingerprint research within public academic circles has been trailing behind facial recognition, primarily due to the scarcity of extensive publicly available datasets, despite fingerprints being widely used across various domains. Recent progress has seen the application of deep learning techniques to synthesize fingerprints, predominantly focusing on large-area fingerprints within existing datasets. However, with the emergence of AIoT and edge devices, the importance of tiny partial fingerprints has been underscored for their faster and more cost-effective properties. Yet, there remains a lack of publicly accessible datasets for such fingerprints. To address this issue, we introduce publicly available datasets tailored for tiny partial fingerprints. Using advanced generative deep learning, we pioneer diffusion methods for fingerprint synthesis. By combining random sampling with inpainting diffusion guided by feature keypoints masks, we enhance data augmentation while preserving key features, achieving up to 99.1% recognition matching rate. To demonstrate the usefulness of our fingerprint images generated using our approach, we conducted experiments involving model training for various tasks, including denoising, deblurring, and deep forgery detection. The results showed that models trained with our generated datasets outperformed those trained without our datasets or with other synthetic datasets. This indicates that our approach not only produces diverse fingerprints but also improves the model’s generalization capabilities. Furthermore, our approach ensures confidentiality without compromise by partially transforming randomly sampled synthetic fingerprints, which reduces the likelihood of real fingerprints being leaked. The total number of generated fingerprints published in this article amounts to 818,077. Moving forward, we are ongoing updates and releases to contribute to the advancement of the tiny partial fingerprint field. The code and our generated tiny partial fingerprint dataset can be accessed at https://github.com/Hsu0623/Inpainting-Diffusion-Synthetic-and-Data-Augment-with-Feature-Keypoints-for-Tiny-Partial-Fingerprints.git

Smartphone-based contactless fingerphoto authentication has become a reliable alternative to traditional contact-based fingerprint biometric systems owing to rapid advances in smartphone camera technology. Despite its convenience, fingerprint authentication through fingerphotos is more vulnerable to presentation attacks, which has motivated recent research efforts towards developing fingerphoto Presentation Attack Detection (PAD) techniques. However, prior PAD approaches utilized supervised learning methods that require labeled training data for both bona fide and attack samples. This can suffer from two key issues, namely (i) generalization—the detection of novel presentation attack instruments (PAIs) unseen in the training data, and (ii) scalability—the collection of a large dataset of attack samples using different PAIs. To address these challenges, we propose a novel unsupervised approach based on a state-of-the-art deep-learning-based diffusion model, the Denoising Diffusion Probabilistic Model (DDPM), which is trained solely on bona fide samples. The proposed approach detects Presentation Attacks (PA) by calculating the reconstruction similarity between the input and output pairs of the DDPM. We present extensive experiments across three PAI datasets to test the accuracy and generalization capability of our approach. The results show that the proposed DDPM-based PAD method achieves significantly better detection error rates on several PAI classes compared to other baseline unsupervised approaches.

Fingerprints have been crucial evidence for law enforcement agencies for a long time. Though the rapidly developing deep learning has dramatically improved the performance of the latent fingerprint recognition algorithm, a fully automated latent fingerprint identification system is still far from meeting actual needs. One major issue is the lack of publicly available latent fingerprint databases. Recently, diffusion probabilistic models have emerged as state-of-the-art deep generative methods for image synthesis. These models have better distribution coverage and less mode collapse than the popular Generative Adversarial Networks. In this paper, we propose an end-to-end latent fingerprint synthetic approach based on the improved denoising diffusion probabilistic model. The proposed approach could simultaneously generate latent, rolled, and plain fingerprints of high visual realism. Several primary degradation factors, such as various background textures, limited area of ridge patterns, and structural noise, can be directly generated without any postprocessing, unlike existing methods. We conduct NFIQ2 and perceptual analysis in the experiments to evaluate the proposed approach. The results indicate that the quality and visual realism of the proposed synthetic fingerprints is similar to the natural ones, demonstrating the effectiveness of our approach.

Billions of contact-based fingerprint images have been acquired in large databases. Contactless 2D fingerprint identification systems have emerged to provide more hygienic and secured alternatives and are highly sought under the current pandemic. The success of such an alternative requires high match accuracy, not just for the contactless-to-contactless but also for the contactless-to-contact-based matching, which is currently below expectations for large-scale deployments. We introduce a new approach to advance such expectations on match accuracy and also to address privacy-related concerns, e.g., recent GDPR regulations, in the acquisition of very large databases. This paper introduces a novel approach for accurately synthesizing multi-view contactless 3D fingerprints to develop a very large-scale multi-view fingerprint database, and corresponding contact-based fingerprint database. A unique advantage of our approach is the simultaneous availability of much-needed ground truth labels and alleviation of laborious and often prone to erroneous tasks performed by human labeling. We also introduce a new framework that can not only accurately match contactless to contact-based images but also contactless to contactless images, as both of these capabilities are simultaneously required to advance contactless fingerprint technologies. Our rigorous experimental results presented in this paper, both for within-database and cross-database experiments, illustrate outperforming results to simultaneously meet both of these expectations and validate the effectiveness of the proposed approach.

No abstract available

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state of the art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including unconditional image generation, text-to-image synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.5 and Frechet Inception Distance (FID) of 7.4, improving over the previous best IS of 52.52 and FID of 18.6.

Diffusion models are a powerful class of techniques in ML for generating realistic data, but they are highly prone to overfitting, especially with limited training data. While data augmentation such as image rotation can mitigate this issue, it often causes leakage, where augmented content appears in generated samples. In this paper, we propose a novel regularization framework, called shifted data-augmentation (SDA), for training unconditional diffusion models. SDA introduces an auxiliary diffusion path using transformed data and the noise-shift technique alongside the standard path with original data. This dual-path structure enables effective regularization while suppressing leakage through a trajectory shift in the diffusion process. We implement SDA with image rotation as its most basic and interpretable configuration. We also conduct synthetic and empirical analyses demonstrating that SDA effectively leverages the regularization benefit of image rotation. In particular, SDA yielded notable performance in training with limited data.