人脸识别技术研究的两个新突破

国内外对人脸识别技术的研究虽已有100多年的历史，但至今仍有许多技术难题尚未被攻克。本文作者在人脸识别技术方面取得了一些新的研究成果：采用小波及分形理论分析人脸的关键特征，从而实现了海量人像的快速识别和查询；应用神经网络建模，建立颅面与脸面相对应的数学模型，从而解决了以往人像重建时嘴唇、鼻子、耳朵难以重建的技术难题。     

应用优势将促人脸识别实现大跨越

人脸识别是一种基于人的脸部特征信息进行身份识别的生物识别技术。它用摄像机或摄像头采集含有人脸的图像或视频流，并自动在图像中检测和跟踪人脸．进而对检测到的人脸进行脸部的一系列相关技术，包括人脸图像采集、人脸定位、人脸识别预处理、记忆存储和比对辨识，最后达到识别不同人身份的目的。     

人脸识别技术在治安管理中的应用及其规范路径

人脸识别技术是基于人的面部特征信息进行身份识别的一种生物识别技术.智慧警务背景下,在治安管理中广泛应用人脸识别技术,对于提高治安管理效率和打造"平安城市"具有重大意义.但人脸识别技术具有远程识别性和识别独特性等特征,其在应用于治安管理时会存在技术滥用的风险.因此,有必要对人脸识别技术进行有效规范,包括明确人脸识别技术应...     

美国对人脸识别技术的法律规制

人脸识别(Face Recognition)技术是一项基于人的面部特征进行身份识别的生物识别技术,俗称“刷脸”。该技术通过采集人像、关键点提取、对人像进行预处理、待征提取、人脸识别比对等过程,实现人脸识别验证的效果。     

人脸识别技术在安防监控中的应用

市场背景 人脸识别技术是近年来随着计算机技术、图象处理技术、模式识别技术等技术与理论的快速进步而出现的一种崭新的人体生物特征识别技术。人脸识别技术利用人的面部图像特征进行身份识别，该技术通过人像照片比对即可判别人员真实身份，是继指纹识别之后最受关注及满足公安警务应用的一项人体生物特征识别技术。     

图像处理技术的实战应用

正(image processing)又称为影像处理,是用计算机对图像进行处理达到所需结果的技术。起源于20世纪20年代,一般为数字图像处理。图像处理技术的主要内容包括图像压缩、增强复原、匹配描述识别3个部分,常见的处理有图像数字化、图像编码、图像增强、图像复原、图像分割和图像分析等。数字图像处理技术可以帮助人们更客观、准确地认识世界。人的视觉系统帮助我们从外界获     

刷脸问题治理逻辑的一般规则转向——以技术透明度为基本立场

人脸识别技术滥用导致的信息安全风险饱受社会关注,学者们基于生物识别信息保护、算法治理、技术应用场景限制等视角提出了人脸识别信息保护的专门立法方案。尽管人脸识别信息具有唯一指向性、不易更改性等特征,但这些同样存在于其他生物识别信息,并不足以成为专门规定和单行立法保护的必要事由。在审视和反思现有学说有关人脸信息与人脸识别信息的客体范围混同和场景化理论的解释误区的基础上,我国刷脸问题的治理逻辑不应当陷入"新型信息技术引发社会风险有必要专门规制"的僵化理念,而是应当以增强自然人与信息处理者之间有关刷脸技术应用的透明度为基本立场,基于场景一致性理论和人脸特征识别比对数据库的标准化来限定刷脸技术的必要性情形。     

人脸识别技术在公共安全领域中的应用

正在公共安全领域,AI技术驱动的智能视频和图像处理,正逐渐成为不可或缺的技术。人脸识别作为首当其冲的应用,正在公安刑侦中正在产生深远的影响。作为人脸识别领域的领军企业,商汤科技所提供的人脸布控、视图情报研判系统,目前已在北京、深圳、上海、四川和重庆等地落地应用,取得了多项成果,大幅提高了刑侦人员的执行效率。人脸识别的发展和深度学习带来的突破人脸识别,是基于人的脸部特征信息进行身份识别的一种生物识别技术。由于不需要用户主动配合,     

图像处理技术的实战应用

正影像处理(image processing),是用计算机对图像进行处理达到所需结果的技术。起源于20世纪20年代,一般为数字图像处理。图像处理技术的主要内容包括图像压缩、增强复原、匹配描述识别3个部分,常见的处理有图像数字化、图像编码、图像增强、图像复原、图像分割和图像分析等。数字图像处理技术可以帮助人们更客观、准确地认识世界。人的视觉系统帮助我们从外界获取3/4以上的信息,图像、图形是所有视     

人脸识别信息保护的规范建构

人脸识别是人工智能的重要应用。运用人脸识别技术应加强人脸信息保护。我国人脸识别信息保护缺乏专门的法律规范，《个人信息保护法》第62条特别强调对“人脸识别”制定专门的保护规范。我国应在系统总结现有立法、执法和司法经验的基础上，树立尊重数字人权、适当限制公权、注重利益平衡的理念，构建人脸识别信息保护的实体性规范、优化人脸识别信息保护的程序性设计，以《个人信息保护法》等法律法规为依据，由国家网信部门统筹协调有关部门，围绕人脸识别的收集、存储、使用、加工、传输、提供、公开、删除等行为制定《人脸识别信息保护规范》。     

Image conditions for machine-based face recognition of juvenile faces

Machine-based facial recognition could help law enforcement and other organisations to match juvenile faces more efficiently. It is especially important when dealing with indecent images of children to minimise the workload, and deal with moral and stamina challenges related to human recognition. With growth related changes, juvenile face recognition is challenging. The challenge not only relates to the growth of the child’s face, but also to face recognition in the wild with unconstrained images. The aim of the study was to evaluate how different conditions (i.e. black and white, cropped, blur and resolution reduction) can affect machine-based facial recognition of juvenile age progression. The study used three off-the-shelf facial recognition algorithms (Microsoft Face API, Amazon Rekognition, and Face++) and compared the original images and the age progression images under the four image conditions against an older image of the child. The results showed a decrease in facial similarity with an increased age gap, in comparison to Microsoft; Amazon and Face++ showed higher confidence scores and are more resilient to a change in image condition. The image condition ‘black and white’ and ‘cropped’ had a negative effect across all three APIs. The relationship between age progression images and the younger original image was explored. The results suggest manual age progression images are no more useful than the original image for facial identification of missing children, and Amazon and Face++ performed better with the original image.     

Combination of Face Regions in Forensic Scenarios

This article presents an experimental analysis of the combination of different regions of the human face on various forensic scenarios to generate scientific knowledge useful for the forensic experts. Three scenarios of interest at different distances are considered comparing mugshot and CCTV face images using MORPH and SC face databases. One of the main findings is that inner facial regions combine better in mugshot and close CCTV scenarios and outer facial regions combine better in far CCTV scenarios. This means, that depending of the acquisition distance, the discriminative power of the facial regions change, having in some cases better performance than the full face. This effect can be exploited by considering the fusion of facial regions which results in a very significant improvement of the discriminative performance compared to just using the full face.     

Improving automatic face recognition with user interaction

Face recognition systems aim to recognize the identity of a person depicted in a photograph by comparing it against a gallery of prerecorded images. Current systems perform quite well in controlled scenarios, but they allow for none or little interaction in case of mistakes due to the low quality of images or to algorithmic limitations. Following the needs and suggestions of investigators, we present a guided user interface that allows to adjust from a fully automatic to a fully assisted modality of execution, according to the difficulty of the task and to amount of available information (gender, age, etc.): the user can generally rely on automatic execution and intervene only on a limited number of examples when a failure is automatically detected or when the quality of intermediate results is deemed unsatisfactory. The interface runs on top of a preexistent automatic face recognition algorithm in such a way to guarantee full control over the execution flow and to exploit the peculiarities of the underlying image processing techniques. The viability of the proposed solution is tested on a classic face identification task run on a standard publicly available database (the XM2VTS), assessing the improvement to user interaction over the automatic system performance.     

A Preliminary Study of the Reliability of Anatomical Facial Landmarks Used in Facial Comparison

Anatomical landmarks are considered the most objective indicators for use in forensic facial comparisons. Therefore, accurately identifying and locating these landmarks is the beginning of reliable facial comparison. This study evaluated the accuracy with which facial landmarks are located and examined their reliability according to type of landmark, head posture, and image quality. Nine operators located a series of landmarks on prepared facial images used to produce comparison images. Then, the average distances between the reciprocal landmarks (ADRL) on the reference and the comparison images were measured as indicators of landmark reliability. We found that a set of landmarks had higher or lower reliability as a function of the head angle and image quality. More reliable landmarks were associated with certain head postures and degrees of image quality. These should be used for facial comparison analysis depending on various head and image conditions.     

一种AI换脸方法生成的伪造视频分析

深度伪造(Deepfake)是一种将图像篡改与AI相结合的面部替换方法。本文首先介绍了Deepfake的产生背景和发展状况,介绍了相应检测技术的研究状况,并对相关文献进行归纳;然后探究了Deepfake运行的基本构架和核心部件,给出了视频面部替换的基本流程和步骤,并阐释了利用自编码网络进行脸部图像训练和转换的原理;最后,从视频的基本信息、编辑痕迹、违背摄影规律、视频整体和案情五个方面与原始视频作对比,分析这类伪造视频存在的问题。深度伪造技术在推动娱乐和文化发展的同时也产生了大量恶意的换脸视频,对国家安全、社会稳定和个人隐私造成潜在的威胁,本文通过对Deepfake实现原理的研究和伪造视频特征的分析,希望能够为该类视频的真伪检验提供一定的理论支持。     

Likelihood Ratios for Deep Neural Networks in Face Comparison

In this study, we aim to compare the performance of systems and forensic facial comparison experts in terms of likelihood ratio computation to assess the potential of the machine to support the human expert in the courtroom. In forensics, transparency in the methods is essential. Consequently, state-of-the-art free software was preferred over commercial software. Three different open-source automated systems chosen for their availability and clarity were as follows: OpenFace, SeetaFace, and FaceNet; all three based on convolutional neural networks that return a distance (OpenFace, FaceNet) or similarity (SeetaFace). The returned distance or similarity is converted to a likelihood ratio using three different distribution fits: parametric fit Weibull distribution, nonparametric fit kernel density estimation, and isotonic regression with pool adjacent violators algorithm. The results show that with low-quality frontal images, automated systems have better performance to detect nonmatches than investigators: 100% of precision and specificity in confusion matrix against 89% and 86% obtained by investigators, but with good quality images forensic experts have better results. The rank correlation between investigators and software is around 80%. We conclude that the software can assist in reporting officers as it can do faster and more reliable comparisons with full-frontal images, which can help the forensic expert in casework.     

Explosion Scene Forensic Image Interpretation

Image interpretation is an important aspect in the field of forensic science; however, it is seldom reported how to use these techniques in explosion scene forensic investigations. On 12 August 2015, a series of explosions killed 165 people and injured hundreds more at a container storage station at the Port of Tianjin. In this study, we applied image interpretation methods to determine the seat of the explosion by analyzing low‐quality video clips of the event. The interpretation fits well with recently published standard operating procedures, including the hypothesis, evaluation, inference, and confirmation. Image processing was adopted to enhance the images while the explosion scene was reconstructed with the same images. Some important features were extracted and utilized to distinguish whether the flashes were caused by reflection or a real blast. We reveal the real explosion location, which guides the overall investigation. The results indicate that image interpretation is a powerful tool for forensic investigators to analyze low‐quality images in complicated explosions or fire accidents.     

Automatic forensic face recognition from digital images.

Digital image evidence is now widely available from criminal investigations and surveillance operations, often captured by security and surveillance CCTV. This has resulted in a growing demand from law enforcement agencies for automatic person-recognition based on image data. In forensic science, a fundamental requirement for such automatic face recognition is to evaluate the weight that can justifiably be attached to this recognition evidence in a scientific framework. This paper describes a pilot study carried out by the Forensic Science Service (UK) which explores the use of digital facial images in forensic investigation. For the purpose of the experiment a specific software package was chosen (Image Metrics Optasia). The paper does not describe the techniques used by the software to reach its decision of probabilistic matches to facial images, but accepts the output of the software as though it were a 'black box'. In this way, the paper lays a foundation for how face recognition systems can be compared in a forensic framework. The aim of the paper is to explore how reliably and under what conditions digital facial images can be presented in evidence.     

The Effect of Image Quality and Forensic Expertise in Facial Image Comparisons

Images of perpetrators in surveillance video footage are often used as evidence in court. In this study, identification accuracy was compared for forensic experts and untrained persons in facial image comparisons as well as the impact of image quality. Participants viewed thirty image pairs and were asked to rate the level of support garnered from their observations for concluding whether or not the two images showed the same person. Forensic experts reached their conclusions with significantly fewer errors than did untrained participants. They were also better than novices at determining when two high‐quality images depicted the same person. Notably, lower image quality led to more careful conclusions by experts, but not for untrained participants. In summary, the untrained participants had more false negatives and false positives than experts, which in the latter case could lead to a higher risk of an innocent person being convicted for an untrained witness.     

基于BEMD二次分解与维纳滤波相结合的图像去噪算法

目的提出基于二维经验模态分解(BEMD)与维纳滤波相结合的图像去噪算法并验证其去噪效果。方法通过对含噪的图像进行BEMD尺度分解,提取前两阶含噪的尺度分量,使用维纳滤波进行一次去噪,然后再次进行BEMD分解和滤波去噪,从而达到去噪的目的。将本文提出的算法与经典算法进行比较,验证该算法的可行性和鲁棒性。结果实验表明,该算法不仅能够有效降低图像的噪声,而且能很好地保持图像信息。结论本文提出的图像去噪算法思路新颖,效果良好,在法庭科学图像处理领域有很好的参考和应用价值。