扩散模型用于指纹生成

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.

… 7] uses direction field generation and density field generation to … ridge pattern generation model to reconstruct real fingerprint … In the aforementioned diffusion model, a pivotal aspect lies …

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.

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.

… with other biometric systems, contactless fingerprint verification … based on the Denoising Diffusion Probabilistic Model (DDPM). … a model capable of capturing finer details of fingerprints …

High-quality, diversified, and large-scale datasets are crucial for creating reliable deep-learning models for biometric applications. Unfortunately, there is a shortage of well-labeled data. This paper introduces a text-conditional biometric imaging generation framework, addressing the complexities associated with multi-modality considerations. The proposed framework harnesses cutting-edge diffusion probabilistic models to produce multi-modal biometric images at high resolutions, seamlessly aligning with biometric language prompts. The experimental results unequivocally validate the efficacy of the proposed framework in generating a diverse array of highly realistic synthetic biometric images while consistently maintaining a commendable level of fidelity when juxtaposed with their respective reference datasets. The contributions of this study offer substantial potential for propelling advancements in biometric imaging research.

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

… As a result, the present paper opens opportunities suggesting potential fingerprinting tools … and AI in latent fingerprinting in doublefold manner, i)synthetic fingerprints data generation …

Fingerprint-based indoor positioning systems (IPSs) are being explored to aid in location-based services due to their robustness in nonline-of-sight (NLOS) conditions. Current systems use high-dimensional radio frequency (HDRF) fingerprints, such as Wi-Fi channel state information (CSI), to achieve higher positioning precision. Since data acquisition is labor-intensive, researchers proposed to enrich the dataset with generative models. It, however, faced challenges arising from capturing the intricate HDRF distribution using simplistic models and the lack of a framework that simultaneously addresses the generative model training, sample evaluation, and selection. In order to synthesize high-quality HDRF fingerprints, this article proposes an HDRF fingerprint generation framework using a conditional diffusion model (CDM) that learns the packet-level feature distribution by decomposing HDRF fingerprints using grid points, anchors, and frequency channel information while preserving the feature spatial correlation within a fingerprint. A sample selection process using the Mahalanobis distance and the principal component analysis (PCA) Q-statistic is used to ensure the sample fidelity. An adaptive learning strategy is further developed to integrate the generated synthetic HDRF fingerprints into downstream positioning tasks. Experimental results on two HDRF datasets quantitatively and qualitatively showcase the diversity and fidelity of the synthetic samples. Compared to solely using the original dataset, integrating the synthetic HDRF fingerprints from the developed framework to train downstream positioning models can, furthermore, decrease the positioning error by up to 16%.

Specific emitter identification (SEI) separates the radio frequency fingerprint (RFF) from signals, which is of great significance in solving Internet of Things (IoT) security problems. However, the scarcity of high-quality, diverse, and labeled data in real-world scenarios limits the application of SEI. Under such conditions, the SEI is referred to as few-shot SEI (FS-SEI). To surmount this challenge, we propose a diffusion model-based data augmentation method capable of generating a substantial volume of diverse, high-quality data. Specifically, we develop a multi-scale convolutional block attention module denoising diffusion probabilistic model (MSCBAM-DDPM), which enhances feature capture capabilities, laying the foundation for the generation of diverse data. Furthermore, we propose an adaptive two-stage multi-domain loss function that guides the model to learn the characteristics of the original data and further derive other similar features, thereby achieving the goal of generating diverse and high-quality data. Finally, we theoretically derive the feasibility of the proposed loss function and further demonstrate the excellent diversity and quality of the data generated by our method, as well as its considerable gain for FS-SEI, through extensive experiments on real-world signal datasets.