scholarly journals CNN-Based Multimodal Human Recognition in Surveillance Environments

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3040 ◽  
Author(s):  
Ja Koo ◽  
Se Cho ◽  
Na Baek ◽  
Min Kim ◽  
Kang Park

In the current field of human recognition, most of the research being performed currently is focused on re-identification of different body images taken by several cameras in an outdoor environment. On the other hand, there is almost no research being performed on indoor human recognition. Previous research on indoor recognition has mainly focused on face recognition because the camera is usually closer to a person in an indoor environment than an outdoor environment. However, due to the nature of indoor surveillance cameras, which are installed near the ceiling and capture images from above in a downward direction, people do not look directly at the cameras in most cases. Thus, it is often difficult to capture front face images, and when this is the case, facial recognition accuracy is greatly reduced. To overcome this problem, we can consider using the face and body for human recognition. However, when images are captured by indoor cameras rather than outdoor cameras, in many cases only part of the target body is included in the camera viewing angle and only part of the body is captured, which reduces the accuracy of human recognition. To address all of these problems, this paper proposes a multimodal human recognition method that uses both the face and body and is based on a deep convolutional neural network (CNN). Specifically, to solve the problem of not capturing part of the body, the results of recognizing the face and body through separate CNNs of VGG Face-16 and ResNet-50 are combined based on the score-level fusion by Weighted Sum rule to improve recognition performance. The results of experiments conducted using the custom-made Dongguk face and body database (DFB-DB1) and the open ChokePoint database demonstrate that the method proposed in this study achieves high recognition accuracy (the equal error rates of 1.52% and 0.58%, respectively) in comparison to face or body single modality-based recognition and other methods used in previous studies.

2020 ◽  
Vol 11 (SPL3) ◽  
pp. 736-739
Author(s):  
Pravinya ◽  
Dhanraj Ganapathy ◽  
Subhashree Rohinikumar

Fractures of the middle third of the face have increased in number over the past two decades. Trauma to the facial area results in injuries not only to dental structures but also maxillomandibular fractures. In addition, these injuries frequently occur in combination with injuries of other parts of the body. The etiology of these fractures have various causes, such as traffic accidents, falls, assaults, sports, and others. The aim of the study was to assess the knowledge and awareness about LeFort I fracture among undergraduate dental students. A custom made questionnaire comprising of 10 questions to assess the knowledge about LeFort I fracture was formulated and circulated among 100 undergraduate dental students. The responses were then subjected to statistical analysis. Among 100 undergraduate dental students, 52% of them were aware of the types of maxillofacial fractures, and LeFort I fracture is a maxillary fracture, 34% of them have reported that Le Fort I fracture causes disruption of the cribriform plate of the ethmoid bone,35% of them reported that LeFort I fracture might be associated with cerebrospinal fluid leak and 25% of them were still unaware that floating palate is the typical clinical presentation of LeFort I fracture. Also, only 30% were aware that intermaxillary fixation is the management of LeFort I fracture. The present study suggests that among undergraduate dental students, the knowledge about the clinical presentation and the management of LeFort I fracture is inadequate.


2021 ◽  
Author(s):  
James Daniel Dunn ◽  
Victor Perrone de Lima Varela ◽  
Victoria Ida Nicholls ◽  
Michaell Papinutto ◽  
David White ◽  
...  

People’s ability to recognize faces varies to a surprisingly large extent and these differences are hereditary. But cognitive and perceptual processing giving rise to these differences remain poorly understood. Here we compared visual sampling of 10 super-recognizers – individuals that achieve the highest levels of accuracy in face recognition tasks – to typical viewers. Participants were asked to learn, and later recognize, a set of unfamiliar faces while their gaze position was recorded. They viewed faces through ‘spotlight’ apertures varying in size, where the face on the screen was modified in real-time to constrict the visual information displayed to the participant around their gaze position. Higher recognition accuracy in super-recognizers was only observed when at least 36% of the face was visible. We also identified qualitative differences in their visual sampling that can explain their superior recognition accuracy: (1) less systematic focus on the eye region; (2) more fixations to the central region of faces; (3) greater visual exploration of faces in general. These differences were observed in both natural and spotlight viewing conditions, but were most apparent when learning faces and not during recognition. Critically, this suggests that superior recognition performance is founded on enhanced encoding of faces into memory rather than memory retention. Together, our results point to a process whereby super-recognizers construct a more robust memory trace by accumulating samples of complex visual information across successive eye movements.


1964 ◽  
Vol 9 (4) ◽  
pp. 336-344 ◽  
Author(s):  
E. Llewellyn Thomas ◽  
Eugene Stasiak

The eye-movement patterns of nine hospitalized psychiatric patients were compared with those of ten non-patients when looking at pictures of themselves and others. There were highly significant differences between both the mean fixation times of the two groups and also between the area of the body to which they paid the most attention. The mean fixation times of all the non-patients grouped closely around 0.61 seconds whereas the patients varied between 0.12 seconds and 0.47 seconds and 0.72 seconds and 1.04 seconds. Non-patients looked at all body levels, but spent much more time looking at the face. Patients on the other hand paid much more visual attention to the body and tended to avoid the face. It is suggested that the variability in the fixation times and the tendency to avoid the face reflects a mechanism in the patient which is tending to avoid receiving information about certain aspects of the external world.


2020 ◽  
Vol 99 (4) ◽  
pp. 379-383
Author(s):  
Vasily N. Afonyushkin ◽  
N. A. Donchenko ◽  
Ju. N. Kozlova ◽  
N. A. Davidova ◽  
V. Yu. Koptev ◽  
...  

Pseudomonas aeruginosa is a widely represented species of bacteria possessing of a pathogenic potential. This infectious agent is causing wound infections, fibrotic cystitis, fibrosing pneumonia, bacterial sepsis, etc. The microorganism is highly resistant to antiseptics, disinfectants, immune system responses of the body. The responses of a quorum sense of this kind of bacteria ensure the inclusion of many pathogenicity factors. The analysis of the scientific literature made it possible to formulate four questions concerning the role of biofilms for the adaptation of P. aeruginosa to adverse environmental factors: Is another person appears to be predominantly of a source an etiological agent or the source of P. aeruginosa infection in the environment? Does the formation of biofilms influence on the antibiotic resistance? How the antagonistic activity of microorganisms is realized in biofilm form? What is the main function of biofilms in the functioning of bacteria? A hypothesis has been put forward the effect of biofilms on the increase of antibiotic resistance of bacteria and, in particular, P. aeruginosa to be secondary in charcter. It is more likely a biofilmboth to fulfill the function of storing nutrients and provide topical competition in the face of food scarcity. In connection with the incompatibility of the molecular radii of most antibiotics and pores in biofilm, biofilm is doubtful to be capable of performing a barrier function for protecting against antibiotics. However, with respect to antibodies and immunocompetent cells, the barrier function is beyond doubt. The biofilm is more likely to fulfill the function of storing nutrients and providing topical competition in conditions of scarcity of food resources.


Screen Bodies ◽  
2018 ◽  
Vol 3 (2) ◽  
pp. 86-98
Author(s):  
Josh Morrison ◽  
Sylvie Bissonnette ◽  
Karen J. Renner ◽  
Walter S. Temple

Kate Mondloch, A Capsule Aesthetic: Feminist Materialisms in New Media Art (Minneapolis: University of Minnesota Press, 2018), 151 pp. ISBN: 9781517900496 (paperback, $27) Alberto Brodesco and Federico Giordano, editors, Body Images in the Post-Cinematic Scenario: The Digitization of Bodies (Milan: Mimesis International, 2017). 195 pp., ISBN: 9788869771095 (paperback, $27.50) Cynthia J. Miller and A. Bowdoin Van Riper, editors, What’s Eating You? Food and Horror on Screen (New York: Bloomsbury Academic, 2017). 370pp., ISBN: 9781501322389 (hardback, $105); ISBN: 9781501343964 (paperback, $27.96); ISBN: 9781501322419 (ebook, $19.77) Kaya Davies Hayon, Sensuous Cinema: The Body in Contemporary Maghrebi Cinema (New York: Bloomsbury, 2018). 181pp., ISBN: 9781501335983 (hardback, $107.99)


2021 ◽  
pp. 003329412110184
Author(s):  
Paola Surcinelli ◽  
Federica Andrei ◽  
Ornella Montebarocci ◽  
Silvana Grandi

Aim of the research The literature on emotion recognition from facial expressions shows significant differences in recognition ability depending on the proposed stimulus. Indeed, affective information is not distributed uniformly in the face and recent studies showed the importance of the mouth and the eye regions for a correct recognition. However, previous studies used mainly facial expressions presented frontally and studies which used facial expressions in profile view used a between-subjects design or children faces as stimuli. The present research aims to investigate differences in emotion recognition between faces presented in frontal and in profile views by using a within subjects experimental design. Method The sample comprised 132 Italian university students (88 female, Mage = 24.27 years, SD = 5.89). Face stimuli displayed both frontally and in profile were selected from the KDEF set. Two emotion-specific recognition accuracy scores, viz., frontal and in profile, were computed from the average of correct responses for each emotional expression. In addition, viewing times and response times (RT) were registered. Results Frontally presented facial expressions of fear, anger, and sadness were significantly better recognized than facial expressions of the same emotions in profile while no differences were found in the recognition of the other emotions. Longer viewing times were also found when faces expressing fear and anger were presented in profile. In the present study, an impairment in recognition accuracy was observed only for those emotions which rely mostly on the eye regions.


2021 ◽  
pp. 1-13
Author(s):  
Shikhar Tyagi ◽  
Bhavya Chawla ◽  
Rupav Jain ◽  
Smriti Srivastava

Single biometric modalities like facial features and vein patterns despite being reliable characteristics show limitations that restrict them from offering high performance and robustness. Multimodal biometric systems have gained interest due to their ability to overcome the inherent limitations of the underlying single biometric modalities and generally have been shown to improve the overall performance for identification and recognition purposes. This paper proposes highly accurate and robust multimodal biometric identification as well as recognition systems based on fusion of face and finger vein modalities. The feature extraction for both face and finger vein is carried out by exploiting deep convolutional neural networks. The fusion process involves combining the extracted relevant features from the two modalities at score level. The experimental results over all considered public databases show a significant improvement in terms of identification and recognition accuracy as well as equal error rates.


2021 ◽  
Vol 11 (4) ◽  
pp. 1667
Author(s):  
Kerstin Klaser ◽  
Pedro Borges ◽  
Richard Shaw ◽  
Marta Ranzini ◽  
Marc Modat ◽  
...  

Synthesising computed tomography (CT) images from magnetic resonance images (MRI) plays an important role in the field of medical image analysis, both for quantification and diagnostic purposes. Convolutional neural networks (CNNs) have achieved state-of-the-art results in image-to-image translation for brain applications. However, synthesising whole-body images remains largely uncharted territory, involving many challenges, including large image size and limited field of view, complex spatial context, and anatomical differences between images acquired at different times. We propose the use of an uncertainty-aware multi-channel multi-resolution 3D cascade network specifically aiming for whole-body MR to CT synthesis. The Mean Absolute Error on the synthetic CT generated with the MultiResunc network (73.90 HU) is compared to multiple baseline CNNs like 3D U-Net (92.89 HU), HighRes3DNet (89.05 HU) and deep boosted regression (77.58 HU) and shows superior synthesis performance. We ultimately exploit the extrapolation properties of the MultiRes networks on sub-regions of the body.


Sign in / Sign up

Export Citation Format

Share Document