arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.00803cs.CVcs.AI
收藏

在StyleGAN潜在空间操作中控制人脸框架生成:修改人脸以欺骗我们的记忆

Controlling Face's Frame generation in StyleGAN's latent space operations: Modifying faces to deceive our memory

Instituto Tecnológico de Buenos Aires (ITBA)(布宜诺斯艾利斯技术学院)

Agustín Roca, Nicolás Ignacio Britos

AI总结:

本文研究StyleGAN2潜在空间操作对人脸框架的影响,通过识别和比较人脸框架,发现修改睁眼、张嘴可保持框架稳定,而水平朝向影响最大,为利用生成人脸干扰人类记忆识别提供依据。

摘要:

Innocence Project是一个致力于减少错误定罪的非营利组织。该组织与布宜诺斯艾利斯理工学院(ITBA)的睡眠与记忆实验室(Laboratorio de Sueño y Memoria)合作,正在研究人脸识别背景下的人类记忆。他们有一个强有力的假设,认为人类记忆在识别人脸时高度依赖人脸框架。如果这一假设得到证实,可能意味着警方列队辨认中的人脸识别不可信,因为它们可能导致错误定罪。本研究通过实验尝试证明这一点,实验使用具有不同属性(如眼睛大小)但尽可能保持其框架不变的人脸。在本项目中,我们延续了先前项目的工作,该项目提供了使用StyleGAN2生成逼真人脸的基本工具。我们深入研究该工具的内部机制,以充分利用StyleGAN2的功能,同时添加更多特性,例如修改其某些属性,包括张嘴或睁眼。由于该工具的使用高度依赖于保持人脸框架,我们开发了一种方法来识别每张图像的人脸框架,并开发了一个函数,用于在应用某些操作后将其与神经网络的输出进行比较。我们得出结论:在修改睁眼或张嘴程度时,人脸框架得以保持;在修改垂直面部朝向、性别、年龄和微笑时,对人脸框架变化有相当大的影响;最后,水平面部朝向对人脸框架显示出重大影响。这样,实验室可以应用某些操作,并确信人脸框架不会显著改变,从而使这些操作可用于欺骗受试者的记忆。

英文摘要:

Innocence Project is a non-profitable organization that works in reducing wrongful convictions. In collaboration with Laboratorio de Sueño y Memoria from Instituto Tecnológico de Buenos Aires (ITBA), they are studying human memory in the context of face identification. They have a strong hypothesis stating that human memory heavily relies in face's frame to recognize faces. If this is proved, it could mean that face recognition in police lineups couldn't be trusted, as they may lead to wrongful convictions. This study uses experiments in order to try to prove this using faces with different properties, such as eyes size, but maintaining its frame as much as possible. In this project, we continue the work from a previous project that provided the basic tool to generate realistic faces using StyleGAN2. We take a deep dive into the internals of this tool to make full use of StyleGAN2 functionalities, while also adding more features, such as modifying certain of its attributes, including mouth-opening or eye-opening. As the usage of this tool heavily relies on maintaining the face-frame, we develop a way to identify the face-frame of each image and a function to compare it to the output of the neural network after applying some operations. We conclude that the face-frame is maintained when modifying eye-opening or mouth opening. When modifying vertical face orientation, gender, age and smile, have a considerable impact on its frame variation. And finally, the horizontal face orientation shows a major impact on the face-frame. This way, the Lab may apply some operations being confident that the face-frame won't significantly change, making them viable to be used to deceive subjects' memories.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑