In a real-world environment a face detector can be applied to extract multiple face images from multiple video streams without constraints on pose and illumination. The extracted face images will have varying image quality and resolution. Moreover, also the detected faces will not be precisely aligned. This paper presents a new approach to on-line face identification from multiple still images obtained under such unconstrained conditions. Our method learns a sparse representation of the most discriminative descriptors of the detected face images according to their classification accuracies. On-line face recognition is supported using a single descriptor of a face image as a query. We apply our method to our newly introduced BHG descriptor, the SIFT descriptor, and the LBP descriptor, which obtain limited robustness against illumination, pose and alignment errors. Our experimental results using a video face database of pairs of unconstrained low resolution video clips of ten subjects, show that our method achieves a recognition rate of 94% with a sparse representation containing 10% of all available data, at a false acceptance rate of 4%.
DOCUMENT
Over the past few years a growing number of artists have critiqued the ubiquity of identity recognition technologies. Specifically, the use of these technologies by state security programs, tech-giants and multinational corporations has met with opposition and controversy. A popular form of resistance to recognition technology is sought in strategies of masking and camouflage. Zach Blas, Leo Selvaggio, Sterling Crispin and Adam Harvey are among a group of internationally acclaimed artists who have developed subversive anti-facial recognition masks that disrupt identification technologies. This paper examines the ontological underpinnings of these popular and widely exhibited mask projects. Over and against a binary understanding and criticism of identity recognition technology, I propose to take a relational turn to reimagine these technologies not as an object for our eyes, but as a relationship between living organisms and things. A relational perspective cuts through dualist and anthropocentric conceptions of recognition technology opening pathways to intersectional forms of resistance and critique. Moreover, if human-machine relationships are to be understood as coming into being in mutual dependency, if the boundaries between online and offline are always already blurred, if the human and the machine live intertwined lives and it is no longer clear where the one stops and the other starts, we need to revise our understanding of the self. A relational understanding of recognition technology moves away from a notion of the self as an isolated and demarcated entity in favour of an understanding of the self as relationally connected, embedded and interdependent. This could alter the way we relate to machines and multiplies the lines of flight we can take out of a culture of calculated settings.
DOCUMENT
Digital surveillance technologies using artificial intelligence (AI) tools such as computer vision and facial recognition are becoming cheaper and easier to integrate into governance practices worldwide. Morocco serves as an example of how such technologies are becoming key tools of governance in authoritarian contexts. Based on qualitative fieldwork including semi-structured interviews, observation, and extensive desk reviews, this chapter focusses on the role played by AI-enhanced technology in urban surveillance and the control of migration between the Moroccan–Spanish borders. Two cross-cutting issues emerge: first, while international donors provide funding for urban and border surveillance projects, their role in enforcing transparency mechanisms in their implementation remains limited; second, Morocco’s existing legal framework hinders any kind of public oversight. Video surveillance is treated as the sole prerogative of the security apparatus, and so far public actors have avoided to engage directly with the topic. The lack of institutional oversight and public debate on the matter raise serious concerns on the extent to which the deployment of such technologies affects citizens’ rights. AI-enhanced surveillance is thus an intrinsically transnational challenge in which private interests of economic gain and public interests of national security collide with citizens’ human rights across the Global North/Global South divide.
MULTIFILE
In a real-world environment a face detector can be applied to extract multiple face images from multiple video streams without constraints on pose and illumination. The extracted face images will have varying image quality and resolution. Moreover, also the detected faces will not be precisely aligned. This paper presents a new approach to on-line face identification from multiple still images obtained under such unconstrained conditions. Our method learns a sparse representation of the most discriminative descriptors of the detected face images according to their classification accuracies.
DOCUMENT
Local Gabor features (jets) have been widely used in face recognition systems. Once the sets of jets have been extracted from the two faces to be compared, a proper measure of similarity (or distance) between corresponding features should be chosen. For instance, in the well known Elastic Bunch Graph Matching (EBGM) approach and other Gabor-based face recognition systems, the cosine distance was used as a measure. In this paper, we provide an empirical evaluation of seven distance measures for comparison, using a recently introduced face recognition system, based on Shape Driven Gabor Jets (SDGJ). Moreover we evaluate different normalization factors that are used to pre-process the jets. Experimental results on the BANCA database suggest that the concrete type of normalization applied to jets is a critical factor, and that some combinations of normalization + distance achieve better performance than the classical cosine measure for jet comparison.
DOCUMENT
Gebruik gezichtsherkenning vormt inbreuk op art. 8 en art.10 EVRM.
MULTIFILE
Growing research in sign language recognition, generation, and translation AI has been accompanied by calls for ethical development of such technologies. While these works are crucial to helping individual researchers do better, there is a notable lack of discussion of systemic biases or analysis of rhetoric that shape the research questions and methods in the field, especially as it remains dominated by hearing non-signing researchers. Therefore, we conduct a systematic review of 101 recent papers in sign language AI. Our analysis identifies significant biases in the current state of sign language AI research, including an overfocus on addressing perceived communication barriers, a lack of use of representative datasets, use of annotations lacking linguistic foundations, and development of methods that build on flawed models. We take the position that the field lacks meaningful input from Deaf stakeholders, and is instead driven by what decisions are the most convenient or perceived as important to hearing researchers. We end with a call to action: the field must make space for Deaf researchers to lead the conversation in sign language AI.
LINK
Dit artikel gaat in op de zogenaamde digitale kloof en beschrijft hoe met de verandering van die digitale kloof ook de bijhorende sociale interventies moeten wijzigen.
DOCUMENT
Abstract Aim: This study protocol aims to examine the effectiveness and preconditions of a self-management program—named REducing Delay through edUcation on eXacerbations (REDUX)—in China. Background: The high disease burden in people with chronic lung disease is mainly due to exacerbations. There is a need for effective exacerbation-management interventions. A nurse-led program, REDUX, helped patients self-manage exacerbations. Design: A single-arm pre-post study. Methods: Fifty-four patients and 24 healthcare professionals (HCPs) in Chinese primary care will be included. The core element of the program is a personalized action plan. HCPs will receive training in using the action plan to help patients manage exacerbations. The intervention will start when a patient is referred to the nurse for a post-exacerbation consultation and ends when the patient presents for the second post-exacerbation consultation. During the first post-exacerbation consultation, the patient and nurse will create the action plan. The primary outcomes in patients will include the delays between the onset of exacerbation and recognition, between exacerbation recognition and action, between exacerbation recognition and consultation with a doctor, and when the patients feel better after receiving medical help from HCPs. The secondary outcomes will include preconditions of the program. The ethics approval was obtained in September 2021. Discussion: This study will discuss a culturally adapted nurse-led self-management intervention for people with chronic lung disease in China. The intervention could help Chinese HCPs provide efficient care and reduce their workload. Furthermore, it will inform future research on tailoring nurse-led self-management interventions in different contexts. Impact: The study will contribute to the evidence on the effectiveness and preconditions of REDUX in China. If effective, the result will assist the nursing of people with chronic lung disease. Trial registration: Registered in the Chinese clinical trial registry (ID: 2100051782).
DOCUMENT
The security of online assessments is a major concern due to widespread cheating. One common form of cheating is impersonation, where students invite unauthorized persons to take assessments on their behalf. Several techniques exist to handle impersonation. Some researchers recommend use of integrity policy, but communicating the policy effectively to the students is a challenge. Others propose authentication methods like, password and fingerprint; they offer initial authentication but are vulnerable thereafter. Face recognition offers post-login authentication but necessitates additional hardware. Keystroke Dynamics (KD) has been used to provide post-login authentication without any additional hardware, but its use is limited to subjective assessment. In this work, we address impersonation in assessments with Multiple Choice Questions (MCQ). Our approach combines two key strategies: reinforcement of integrity policy for prevention, and keystroke-based random authentication for detection of impersonation. To the best of our knowledge, it is the first attempt to use keystroke dynamics for post-login authentication in the context of MCQ. We improve an online quiz tool for the data collection suited to our needs and use feature engineering to address the challenge of high-dimensional keystroke datasets. Using machine learning classifiers, we identify the best-performing model for authenticating the students. The results indicate that the highest accuracy (83%) is achieved by the Isolation Forest classifier. Furthermore, to validate the results, the approach is applied to Carnegie Mellon University (CMU) benchmark dataset, thereby achieving an improved accuracy of 94%. Though we also used mouse dynamics for authentication, but its subpar performance leads us to not consider it for our approach.
DOCUMENT
