Canny2Palm: Realistic and Controllable Palmprint Generation for Large-scale Pre-training

• URL: http://arxiv.org/abs/2505.04922v1
• Date: Thu, 08 May 2025 03:37:07 GMT
• Title: Canny2Palm: Realistic and Controllable Palmprint Generation for Large-scale Pre-training
• Authors: Xingzeng Lan, Xing Duan, Chen Chen, Weiyu Lin, Bo Wang,
• Abstract summary: We propose a novel synthesis method named Canny2Palm that extracts palm textures with Canny edge detector and uses them to condition a Pix2Pix network for realistic palmprint generation.<n>Canny2Palm not only synthesizes realistic data following the distribution of real palmprints but also enables controllable diversity to generate large-scale new identities.<n>On open-set palmprint recognition benchmarks, models pre-trained with Canny2Palm synthetic data outperform the state-of-the-art with up to 7.2% higher identification accuracy.
• Score: 5.0959026998402965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Palmprint recognition is a secure and privacy-friendly method of biometric identification. One of the major challenges to improve palmprint recognition accuracy is the scarcity of palmprint data. Recently, a popular line of research revolves around the synthesis of virtual palmprints for large-scale pre-training purposes. In this paper, we propose a novel synthesis method named Canny2Palm that extracts palm textures with Canny edge detector and uses them to condition a Pix2Pix network for realistic palmprint generation. By re-assembling palmprint textures from different identities, we are able to create new identities by seeding the generator with new assemblies. Canny2Palm not only synthesizes realistic data following the distribution of real palmprints but also enables controllable diversity to generate large-scale new identities. On open-set palmprint recognition benchmarks, models pre-trained with Canny2Palm synthetic data outperform the state-of-the-art with up to 7.2% higher identification accuracy. Moreover, the performance of models pre-trained with Canny2Palm continues to improve given 10,000 synthetic IDs while those with existing methods already saturate, demonstrating the potential of our method for large-scale pre-training.

Related papers

• Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models [31.760874666742282]
  Palm recognition is significantly limited by the lack of large-scale publicly available datasets.<n>Previous methods have adopted B'ezier curves to simulate the palm creases, which then serve as input for conditional GANs to generate realistic palmprints.<n>We introduce a new identity-based palm crease representation that provides a new palm crease generation mechanism more closely aligned with the real distribution.
  arXiv  Detail & Related papers  (2025-03-24T03:30:58Z)
• PVTree: Realistic and Controllable Palm Vein Generation for Recognition Tasks [32.3316737065653]
  Palm vein recognition is an emerging biometric technology that offers enhanced security and privacy.<n>Existing methods, however, often produce unrealistic palm vein patterns or struggle with controlling identity and style attributes.<n>We propose a novel palm vein generation framework named PVTree to address these issues.<n>Our proposed palm vein generation method surpasses existing methods and achieves a higher TAR@FAR=1e-4 under the 1:1 Open-set protocol.
  arXiv  Detail & Related papers  (2025-03-04T12:15:33Z)
• GenPalm: Contactless Palmprint Generation with Diffusion Models [25.738682467090335]
  This paper introduces a novel palmprint generation method using diffusion probabilistic models. We develop an end-to-end framework for synthesizing multiple palm identities and validate the realism and utility of the generated palmprints.
  arXiv  Detail & Related papers  (2024-06-01T03:33:25Z)
• Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification [47.35171881187345]
  We propose a physics-driven spectrum-consistent federated learning method for palmprint verification, dubbed as PSFed-Palm. Our approach first partitions clients into short- and long-spectrum groups according to the wavelength range of their local spectrum images. We impose constraints on the local models to ensure their consistency with the global model, effectively preventing model drift.
  arXiv  Detail & Related papers  (2023-08-01T11:01:17Z)
• RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition [26.82617300073746]
  We propose a novel realistic pseudo-palmprint generation model to synthesize palmprints with massive identities. Our model improves the state-of-the-art B'ezierPalm by more than $5%$ and $14%$ in terms of TAR@FAR=1e-6 under the $1:1$ and $1:3$ Open-set protocol. Our method still outperforms ArcFace with $100%$ real training data, indicating that we are closer to real-data-free palmprint recognition.
  arXiv  Detail & Related papers  (2023-07-26T07:57:56Z)
• SpoofGAN: Synthetic Fingerprint Spoof Images [47.87570819350573]
  A major limitation to advances in fingerprint spoof detection is the lack of publicly available, large-scale fingerprint spoof datasets. This work aims to demonstrate the utility of synthetic (both live and spoof) fingerprints in supplying these algorithms with sufficient data.
  arXiv  Detail & Related papers  (2022-04-13T16:27:27Z)
• Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining [27.81138870690135]
  We introduce an intuitive geometric model which represents palmar creases with parameterized B'ezier curves. By randomly sampling B'ezier parameters, we can synthesize massive training samples of diverse identities. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability.
  arXiv  Detail & Related papers  (2022-03-11T01:20:22Z)
• ProxyFAUG: Proximity-based Fingerprint Augmentation [81.15016852963676]
  ProxyFAUG is a rule-based, proximity-based method of fingerprint augmentation. The best performing positioning method on this dataset is improved by 40% in terms of median error and 6% in terms of mean error, with the use of the augmented dataset.
  arXiv  Detail & Related papers  (2021-02-04T15:59:30Z)
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting [70.81987741132451]
  Deep generative models have achieved a qualitatively new level of performance. There are concerns on how this technology can be misused to spoof sensors, generate deep fakes, and enable misinformation at scale. Our work enables a responsible disclosure of such state-of-the-art generative models, that allows researchers and companies to fingerprint their models.
  arXiv  Detail & Related papers  (2020-12-16T03:51:54Z)
• Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data [64.65952078807086]
  Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs) Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. We seek a proactive and sustainable solution on deepfake detection by introducing artificial fingerprints into the models.
  arXiv  Detail & Related papers  (2020-07-16T16:49:55Z)
• Towards Palmprint Verification On Smartphones [62.279124220123286]
  Studies in the past two decades have shown that palmprints have outstanding merits in uniqueness and permanence. We built a DCNN-based palmprint verification system named DeepMPV+ for smartphones. The efficiency and efficacy of DeepMPV+ have been corroborated by extensive experiments.
  arXiv  Detail & Related papers  (2020-03-30T08:31:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.