Image-Based Somatotype as a Biometric Trait for Non-Collaborative Person Recognition at a Distance and On-The-Move

It has recently been shown in Re-Identification (Re-ID) work that full-body images of people reveal their somatotype, even after change in apparel. A significant advantage of this biometric trait is that it can easily be captured, even at a distance, as a full-body image of a person, taken by a standard 2D camera. In this work, full-body image-based somatotype is investigated as a novel soft biometric feature for person recognition at a distance and on-the-move. The two common scenarios of (i) identification and (ii) verification are both studied and evaluated. To this end, two different deep networks have been recruited, one for the identification and one for the verification scenario. Experiments have been conducted on popular, publicly available datasets and the results indicate that somatotype can indeed be a valuable biometric trait for identity recognition at a distance and on-the-move (and hence also suitable for non-collaborative individuals) due to the ease of obtaining the required images. This soft biometric trait can be especially useful under a wider biometric fusion scheme.

Download Full-text

Systematic Review and Meta-Analysis of Virtual Reality in Mental Healthcare: Effects of Full Body Illusions on Body Image Disturbance

Frontiers in Virtual Reality ◽

10.3389/frvir.2021.657638 ◽

2021 ◽

Vol 2 ◽

Author(s):

Collin Turbyne ◽

Abe Goedhart ◽

Pelle de Koning ◽

Frederike Schirmbeck ◽

Damiaan Denys

Keyword(s):

Body Image ◽

Virtual Reality ◽

Body Size ◽

Clinical Utility ◽

Meta Analysis ◽

Future Research ◽

Head Mounted Display ◽

Full Body ◽

Virtual Body ◽

Clinical Populations

Background: Body image (BI) disturbances have been identified in both clinical and non-clinical populations. Virtual reality (VR) has recently been used as a tool for modulating BI disturbances through the use of eliciting a full body illusion (FBI). This meta-analysis is the first to collate evidence on the effectiveness of an FBI to reduce BI disturbances in both clinical and non-clinical populations.Methods: We performed a literature search in MEDLINE (PubMed), EMBASE, PsychINFO, and Web of Science with the keywords and synonyms for “virtual reality” and “body image” to identify published studies until September 2020. We included studies that (1) created an FBI with a modified body shape or size and (2) reported BI disturbance outcomes both before and directly after the FBI. FBI was defined as a head-mounted display (HMD)-based simulation of embodying a virtual body from an egocentric perspective in an immersive 3D computer-generated environment.Results: Of the 398 identified unique studies, 13 were included after reading full-texts. Four of these studies were eligible for a meta-analysis on BI distortion inducing a small virtual body FBI in healthy females. Significant post-intervention results were found for estimations of shoulder width, hip width, and abdomen width, with the largest reductions in size being the estimation of shoulder circumference (SMD = −1.3; 95% CI: −2.2 to −0.4; p = 0.004) and hip circumference (SMD = −1.0; 95% CI: −1.6 to −0.4; p = 0.004). Mixed results were found in non-aggregated studies from large virtual body FBIs in terms of both estimated body size and BI dissatisfaction and in small virtual body FBI in terms of BI dissatisfaction.Conclusions: The findings presented in this paper suggest that the participants' BIs were able to conform to both an increased as well as a reduced virtual body size. However, because of the paucity of research in this field, the extent of the clinical utility of FBIs still remains unclear. In light of these limitations, we provide implications for future research about the clinical utility of FBIs for modulating BI-related outcomes.

Download Full-text

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Sensors ◽

10.3390/s17030605 ◽

2017 ◽

Vol 17 (3) ◽

pp. 605 ◽

Cited By ~ 48

Author(s):

Dat Nguyen ◽

Hyung Hong ◽

Ki Kim ◽

Kang Park

Keyword(s):

Visible Light ◽

Recognition System ◽

Body Images ◽

Person Recognition ◽

Thermal Cameras

Download Full-text

ROBUST MULTIMODAL PERSON RECOGNITION USING LOW-COMPLEXITY AUDIO-VISUAL FEATURE FUSION APPROACHES

International Journal of Semantic Computing ◽

10.1142/s1793351x10000985 ◽

2010 ◽

Vol 04 (02) ◽

pp. 155-179 ◽

Cited By ~ 1

Author(s):

DHAVAL SHAH ◽

KYU J. HAN ◽

SHRIKANTH S. NARAYANAN

Keyword(s):

Feature Fusion ◽

Low Cost ◽

Low Complexity ◽

Multimodal Fusion ◽

Superior Performance ◽

Visual Features ◽

Fusion Technique ◽

Facial Movements ◽

Person Recognition ◽

Fusion Scheme

In this paper, we first show the importance of face-voice correlation for audio-visual person recognition. We propose a simple multimodal fusion technique which preserves the correlation between audio-visual features during speech and evaluate the performance of such a system against audio-only, video-only, and audio-visual systems which use audio and visual features neglecting the interdependency of a person's spoken utterance and the associated facial movements. Experiments performed on the VidTIMIT dataset show that the proposed multimodal fusion scheme has a lower error rate than all other comparison conditions and is more robust against replay attacks. The simplicity of the fusion technique allows for low-complexity designs for a simple low-cost real-time DSP implementation. We then discuss some problems associated with the previously proposed design and, as a solution to those problems, propose two novel classifier designs which provide more flexibility and a convenient way to represent multimodal data where each modality has different characteristics. We also show that these novel classifier designs offer superior performance in terms of both accuracy and robustness.

Download Full-text

Gender classification of full body images based on the convolutional neural network

2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) ◽

10.1109/spac.2017.8304366 ◽

2017 ◽

Cited By ~ 3

Author(s):

Zhenxia Yu ◽

Chengxuan Shen ◽

Lin Chen

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Gender Classification ◽

Body Images ◽

Full Body

Download Full-text

Obese Individuals' Perception of Body Image

Perceptual and Motor Skills ◽

10.2466/pms.1970.31.2.617 ◽

1970 ◽

Vol 31 (2) ◽

pp. 617-618 ◽

Cited By ~ 4

Author(s):

William L. Bailey ◽

Martin M. Shinedling ◽

I. Reed Payne

Keyword(s):

Body Image ◽

Normal Weight ◽

Body Images ◽

Overweight People ◽

Figure Drawings

To test differences in size of body image of underweight, normal weight, and overweight people, 105 undergraduates were administered a Draw-A-Person test. The torso and head of the figure drawings were each assigned a number from 0 to 3 according to the degree their dimensions represented obese characteristics. Obese Ss drew significantly larger figures, indicating larger body images than normal or underweight Ss.

Download Full-text

Body Image and Disturbed Eating Attitudes Among Adolescents

Pakistan Journal of Psychological Research ◽

10.33824/pjpr.2021.36.3.23 ◽

2021 ◽

Vol 36 (3) ◽

pp. 413-430

Author(s):

Wajeha Zainab ◽

Shafaq Ahmad

Keyword(s):

Body Image ◽

Ideal Body Weight ◽

Eating Attitudes ◽

Body Parts ◽

Body Images ◽

Cross Sectional ◽

Disturbed Eating ◽

Ideal Body ◽

Body Self ◽

The Impact

Among all the psychiatric conditions, eating disorders has the highest mortality rates and most of the sufferers are adolescents. As the standards for beauty and attraction are changing and creating a bigger gap between actual and ideal body images resulting in dissatisfied, striving individuals to attain ideal body weight and shape. The current study is intended to explore the impact of closely related but discrete aspects of body image on disturbed eating attitudes among adolescents in Pakistan. Schools and universities were selected through convenient sampling, based on cross sectional research study involved 300 students of 15-20 years (M = 17.23, SD = 1.42) who completed the Eating Attitudes Test and Multidimensional Body-Self Relations Questionnaires. Analyses revealed that the adolescents with disturbed eating attitudes had scored significantly more on cognitive and affective components of body image that is overweight preoccupation and dissatisfaction with their body parts when compared to adolescents with normal eating patterns. Findings of this study are consistent with the existing literature in western culture that suggests that Preoccupation with weight and shape and body dissatisfaction is a risk factor for disturbed eating attitudes among adolescents.

Download Full-text

Effects of Breast Cancer on Women's Psychological Health: A Review of Self-Compassion-Based Interventions in Body Image

Nesne Psikoloji Dergisi ◽

10.7816/nesne-09-22-12 ◽

2021 ◽

Vol 9 (22) ◽

Keyword(s):

Breast Cancer ◽

Body Image ◽

Psychological Health ◽

Breast Cancer Survivors ◽

Body Images ◽

Important Place ◽

Rehabilitation Intervention ◽

Self Compassion ◽

Day By Day

Research on how breast cancer and its treatment affect women's psychological health is increasing day by day. There is information that the psychological health of women is affected not only in the treatment, but also during the period from cancer diagnosis to the beginning of cancer treatment. In recent years, pre-rehabilitation intervention, which is an up-to-date approach that recommends intervention in this process, comes to the fore. The problems women experience with their body images have an important place in the effects of breast cancer and its treatment on women's psychological health. Body image is defined as a conceptualized state of the emotions, thoughts and behaviors that a person feels about their physical characteristics. In recent years, interventions aimed at reducing body image problems in women with breast cancer have been increasing. Self-compassion is defined as an individual's approach to their flaws with a sincere, caring and warm attitude. The emphasis on the role of self-compassion in reducing the problems that women with breast cancer experience with body images is increasing day by day. Based on this information, in this study, the literature on the problems faced by women with breast cancer with their body image and the role of self-compassion in reducing these problems is reviewed and discussed within the scope of pre-rehabilitation intervention. Keywords: Self-compassion, breast cancer survivors, interventions for self-compassion, body image

Download Full-text

Level of Physical Activity on the Body Image of Young Women

Journal of Morphological Sciences ◽

10.1055/s-0039-1693721 ◽

2019 ◽

Vol 36 (03) ◽

pp. 156-161

Author(s):

Katielly Santana ◽

Almir de França Ferraz ◽

André Rodrigues Lourenço Dias ◽

Rosilene Andrade Silva Rodrigues ◽

Camila Pasa ◽

...

Keyword(s):

Physical Activity ◽

Body Image ◽

Body Image Dissatisfaction ◽

The Body ◽

Lower Amount ◽

Body Images ◽

Education Professionals ◽

Vigorous Intensity ◽

Different Levels ◽

Activity Questionnaire

AbstractPhysical exercise has the ability to alter the measurements of the body related to esthetic. The objective of the present study was to compare the body image and body esthetic between two groups of women with different levels of physical activity. We evaluated 79 women who were divided into 2 groups: 39 women with low or moderate levels of physical activity, and 40 women with high levels of physical activity according to the International Physical Activity Questionnaire (IPAQ). Anthropometric and body composition measurements were taken using the InBody S10 multifrequency device (InBody Co., Eonju-ro, Gangnam-gu, Seoul, South Korea). The scale of silhouettes, which is composed of 9 engravings of body images, was used to verify the body image, as well as the Portuguese version of the Body Shape Questionnaire (BSQ) validated for university students. The group of evaluators was composed of twenty physical education professionals of both sexes, ten male and ten female. The group with low/moderate levels of physical activity, as expected, showed a lower amount (minutes per week) of physical activity of mild, moderate and vigorous intensity when compared with the group with high levels of physical activity (p < 0.05), and they also had a higher ratio of fat mass (FM) per height squared (p = 0.047). The BSQ questionnaire scores, the current and ideal silhouettes, as well as body image dissatisfaction, were not different between the groups (p > 0.05). The overall body esthetic score, attributed only by the male and only by the female evaluators, did not differ significantly (p > 0.05). We concluded that the level of physical activity did not influence the body image and body esthetic of the women.

Download Full-text

Lip Motion Features for Biometric Person Recognition

Visual Speech Recognition ◽

10.4018/978-1-60566-186-5.ch017 ◽

2009 ◽

pp. 495-532 ◽

Cited By ~ 1

Author(s):

Maycel Isaac Faraj ◽

Josef Bigun

Keyword(s):

Replay Attack ◽

Motion Vectors ◽

Identity Recognition ◽

Digit Recognition ◽

Person Recognition ◽

Audio Features ◽

Motion Features ◽

Audio Data ◽

Video And Audio ◽

Audio System

The present chapter reports on the use of lip motion as a stand alone biometric modality as well as a modality integrated with audio speech for identity recognition using digit recognition as a support. First, the auhtors estimate motion vectors from images of lip movements. The motion is modeled as the distribution of apparent line velocities in the movement of brightness patterns in an image. Then, they construct compact lip-motion features from the regional statistics of the local velocities. These can be used as alone or merged with audio features to recognize identity or the uttered digit. The author’s present person recognition results using the XM2VTS database representing the video and audio data of 295 people. Furthermore, we present results on digit recognition when it is used in a text prompted mode to verify the liveness of the user. Such user challenges have the intention to reduce replay attack risks of the audio system.

Download Full-text