Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Parkinson's disease focused multimodal wearable vision based gait monitoring system with real time feedback to support mobility and caregiver well-being.

Discover mental health·2026
Same author

A novel framework for human object classification in flooded environments using YOLOv12n and FastGRNN-MBT.

Scientific reports·2026
Same author

AI-driven audio-to-video generation for dynamic content creation via stable diffusion and CNN-augmented transformers.

Scientific reports·2026
Same author

Adaptive network based fuzzy inference system efficientnet for autism spectrum disorder detection with optimization based pivotal region extraction.

Psychiatry research. Neuroimaging·2025
Same author

Grapes leaf disease dataset for precision agriculture.

Data in brief·2025
Same author

Enhancing semantic segmentation for autonomous vehicle scene understanding in indian context using modified CANet model.

MethodsX·2025

相关实验视频

Updated: May 10, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

一种使用深度卷积神经网络的增强轻量级面部活力检测方法.

Swapnil R Shinde1,2, Anupkumar M Bongale3, Deepak Dharrao1

  • 1Department of Computer Science and Engineering, Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Lavale, Pune, Maharashtra 412115, India.

MethodsX
|March 19, 2025
PubMed
概括

这项研究介绍了LwFLNeT,一种轻量级的深度CNN,用于打击面部伪造攻击. 它可以有效地检测二维和三维攻击,使用具有并行脱落层的新型双流架构.

关键词:
生物识别身份验证验证深度卷积神经网络是一个深度卷积神经网络.面部伪造检测 面部伪造检测轻量级的架构轻量级的架构路夫兰尼特 (LwFLNeT) 是一个

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

448
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K

相关实验视频

Last Updated: May 10, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

448
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 网络安全 网络安全

背景情况:

  • 生物识别认证,包括人脸识别,对于安全至关重要,但很容易受到使用二维和三维方法的复杂人脸伪造攻击.
  • 目前的反伪造措施通常依赖于特定攻击的设计和复杂的架构,导致高计算成本.
  • 现有的深度转移学习模型虽然有效,但对于现实世界的应用来说,它们在计算上昂贵.

研究的目的:

  • 提出LwFLNeT,一种新的,轻量级的深度卷积神经网络 (CNN) 架构,用于强大的面部伪造攻击检测.
  • 设计一种通用和高效的方法,能够检测2D和3D脸部伪造企图.
  • 通过交叉数据集评估,与最先进的技术对比,验证拟议方法的性能.

主要方法:

  • 开发一种轻量级双流CNN架构,结合并行脱落层以减轻过度装配.
  • 实施一个通用的深度CNN设计,以解决2D和3D面部伪造模式.
  • 使用跨数据集列车测试评估和标准性能指标进行广泛的验证.

主要成果:

  • 拟议的LwFLNeT在检测二维和三维面部伪造攻击方面取得了出色的性能.
  • 轻量级的双流CNN架构有效地减少了通过并行脱落层的过.
  • 与现有的方法相比,广义化的CNN架构在检测各种伪造攻击方面表现出更高的效率.

结论:

  • LwFLNeT为面部伪造检测提供了一种高效,强大的解决方案,其性能优于目前的方法.
  • 新型架构有效地处理2D和3D伪造攻击,并降低了计算开销.
  • 这项研究为增强生物识别安全提供了一个计算成本低廉但高度有效的深度学习模型.