Differential 3D Facial Recognition: Adding 3D to Your State-of-the-Art 2D Method.
Ontology highlight
ABSTRACT:
SUBMITTER: Martino JMD
PROVIDER: S-EPMC7892197 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The proportion of individuals with depression has rapidly increased along with the growth of the global population. Depression has been the currently most prevalent mental health disorder. An effective depression recognition system is especially crucial for the early detection of potential depression risk. A depression-related dataset is also critical while evaluating the system for depression or potential depression risk detection. Due to the sensitive nature of clinical data, availability and scale of such datasets are scarce. To our knowledge, there are few extensively practical depression datasets for the Chinese population. In this study, we first create a large-scale dataset by asking subjects to perform five mood-elicitation tasks. After each task, subjects' audio and video are collected, including 3D information (depth information) of facial expressions via a Kinect. The constructed dataset is from a real environment, i.e., several psychiatric hospitals, and has a specific scale. Then we propose a novel approach for potential depression risk recognition based on two kinds of different deep belief network (DBN) models. One model extracts 2D appearance features from facial images collected by an optical camera, while the other model extracts 3D dynamic features from 3D facial points collected by a Kinect. The final decision result comes from the combination of the two models. Finally, we evaluate all proposed deep models on our built dataset. The experimental results demonstrate that (1) our proposed method is able to identify patients with potential depression risk; (2) the recognition performance of combined 2D and 3D features model outperforms using either 2D or 3D features model only; (3) the performance of depression recognition is higher in the positive and negative emotional stimulus, and females' recognition rate is generally higher than that for males. Meanwhile, we compare the performance with other methods on the same dataset. The experimental results show that our integrated 2D and 3D features DBN is more reasonable and universal than other methods, and the experimental paradigm designed for depression is reasonable and practical.
| S-EPMC8102822 | biostudies-literature
Project description:The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides an advanced discriminative representation of actions. Moreover, we generalize Localized Trajectories to 3D by using the depth modality. One of the main advantages of 3D Localized Trajectories is that they describe radial displacements that are perpendicular to the image plane. Extensive experiments and analysis were carried out on five different datasets.
| S-EPMC6720755 | biostudies-literature
Project description:Many human activities and states are related to the facial muscles' actions: from the expression of emotions, stress, and non-verbal communication through health-related actions, such as coughing and sneezing to nutrition and drinking. In this work, we describe, in detail, the design and evaluation of a wearable system for facial muscle activity monitoring based on a re-configurable differential array of stethoscope-microphones. In our system, six stethoscopes are placed at locations that could easily be integrated into the frame of smart glasses. The paper describes the detailed hardware design and selection and adaptation of appropriate signal processing and machine learning methods. For the evaluation, we asked eight participants to imitate a set of facial actions, such as expressions of happiness, anger, surprise, sadness, upset, and disgust, and gestures, like kissing, winkling, sticking the tongue out, and taking a pill. An evaluation of a complete data set of 2640 events with 66% training and a 33% testing rate has been performed. Although we encountered high variability of the volunteers' expressions, our approach shows a recall = 55%, precision = 56%, and f1-score of 54% for the user-independent scenario(9% chance-level). On a user-dependent basis, our worst result has an f1-score = 60% and best result with f1-score = 89%. Having a recall ?60% for expressions like happiness, anger, kissing, sticking the tongue out, and neutral(Null-class).
| S-EPMC7506891 | biostudies-literature
Project description:* To compare surgical and oncological outcomes in patients underwent to colorectal resection with 3D vs 2D laparoscopic technique.
* To evaluate the visual overload in surgeons using 3D laparoscopic technique.
| 2220465 | ecrin-mdr-crc
Project description:A circle/sphere populating method is proposed to generate 2D/3D stochastic microstructures. The proposed method uses circles/spheres as the basic elements and generates microstructure features through the populating process of the circles/spheres. In the populating process, the cores are first generated randomly and circles/spheres start to populate around the cores or the previous generation's circles/spheres. The populating process is controlled by the input parameters including the volume fraction, core number, circle/sphere size distribution, circle/sphere populating distance distribution, circle/sphere populating number, and populating direction constraint angle. The proposed method was compared with the QSGS method and random circle/sphere method in 2-dimensional (2D) and 3-dimensional (3D) cases. The proposed method shows advantages in generating microstructures with clear feature geometries and boundaries. Furthermore, parametric studies are conducted in 2D and 3D to investigate the effect of input parameters on the generated microstructures. With the consideration of circle/sphere spatial distributions, the proposed method can achieve different degrees of feature clustering and agglomerating. A wide range of microstructure morphologies can be achieved by adjusting the input parameters. A more accurate description of the features in the microstructures can be achieved without the involvement of the annealing-based optimization process. As a case study, the proposed method was used to generate sandstone microstructures with different grain size distributions and spatial distributions, and the permeability of generated sandstone was analyzed. Furthermore, the proposed method was applied to generate the microstructure model with a target radial distribution function to demonstrate its computational efficiency by comparing it with the random sphere method and simulated annealing based method.
| S-EPMC10070670 | biostudies-literature
Project description:Artificial intelligence (AI) technology is widely applied in different medical fields, including the diagnosis of various diseases on the basis of facial phenotypes, but there is no evaluation or quantitative synthesis regarding the performance of artificial intelligence. Here, for the first time, we summarized and quantitatively analyzed studies on the diagnosis of heterogeneous diseases on the basis on facial features. In pooled data from 20 systematically identified studies involving 7 single diseases and 12,557 subjects, quantitative random-effects models revealed a pooled sensitivity of 89% (95% CI 82% to 93%) and a pooled specificity of 92% (95% CI 87% to 95%). A new index, the facial recognition intensity (FRI), was established to describe the complexity of the association of diseases with facial phenotypes. Meta-regression revealed the important contribution of FRI to heterogeneous diagnostic accuracy (p = 0.021), and a similar result was found in subgroup analyses (p = 0.003). An appropriate increase in the training size and the use of deep learning models helped to improve the diagnostic accuracy for diseases with low FRI, although no statistically significant association was found between accuracy and photographic resolution, training size, AI architecture, and number of diseases. In addition, a novel hypothesis is proposed for universal rules in AI performance, providing a new idea that could be explored in other AI applications.
| S-EPMC8621146 | biostudies-literature
Project description:MotivationHi-C contact maps reflect the relative contact frequencies between pairs of genomic loci, quantified through deep sequencing. Differential analyses of these maps enable downstream biological interpretations. However, the multi-fractal nature of the chromatin polymer inside the cellular envelope results in contact frequency values spanning several orders of magnitude: contacts between loci pairs separated by large genomic distances are much sparser than closer pairs. The same is true for poorly covered regions, such as repeated sequences. Both distant and poorly covered regions translate into low signal-to-noise ratios. There is no clear consensus to address this limitation.ResultsWe present Serpentine, a fast, flexible procedure operating on raw data, which considers the contacts in each region of a contact map. Binning is performed only when necessary on noisy regions, preserving informative ones. This results in high-quality, low-noise contact maps that can be conveniently visualized for rigorous comparative analyses.Availability and implementationSerpentine is available on the PyPI repository and https://github.com/koszullab/serpentine; documentation and tutorials are provided at https://serpentine.readthedocs.io/en/latest/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC7320618 | biostudies-literature
Project description:Concrete is the most used human-made material in the world, and it is responsible for around 8% of the total greenhouse gas emissions worldwide. Hence, efficient concrete construction methods are one of the main foci of research in architecture, civil engineering, and material science. One recent development that promises to achieve this goal is the use of digital fabrication for building components. Most investigations focus on direct extrusion 3D printing with concrete, which has already been covered in several review articles. Conversely, this article reviews a different approach, which focuses on the indirect digital fabrication of concrete through 3D printed formworks. This approach is under investigation for structural and nonstructural, as well as for on- and off-site applications, with a number of projects having already been built, but a comprehensive review of 3D printed formworks has not yet been compiled to synthesize the findings. This article provides a comprehensive map of the state-of-the-art of five different 3D printing technologies used for the fabrication of formworks so far. The aim is to serve as a fundamental reference for future research, provide a basis for consistent language in this field, and support the development of construction standards. The article further discusses the new geometric possibilities with 3D printed formworks and their potential for making concrete construction more sustainable. In addition, the opportunities and challenges of 3D printed formworks are evaluated in the context of other traditional and digital fabrication tools. A synthetic classification in five functional typologies is proposed and illustrated with 30 representative case studies. Finally, the article concludes with a brief reflection on the role of 3D printing in the broader context of formwork innovation and a possible outlook for this technology.
| S-EPMC9059241 | biostudies-literature
Project description:Over the years, neuroscientists and psychophysicists have been asking whether data acquisition for facial analysis should be performed holistically or with local feature analysis. This has led to various advanced methods of face recognition being proposed, and especially techniques using facial landmarks. The current facial landmark methods in 3D involve a mathematically complex and time-consuming workflow involving semi-landmark sliding tasks. This paper proposes a homologous multi-point warping for 3D facial landmarking, which is verified experimentally on each of the target objects in a given dataset using 500 landmarks (16 anatomical fixed points and 484 sliding semi-landmarks). This is achieved by building a template mesh as a reference object and applying this template to each of the targets in three datasets using an artificial deformation approach. The semi-landmarks are subjected to sliding along tangents to the curves or surfaces until the bending energy between a template and a target form is minimal. The results indicate that our method can be used to investigate shape variation for multiple datasets when implemented on three databases (Stirling, FRGC and Bosphorus).
| S-EPMC7924716 | biostudies-literature
Project description:Three-dimensional (3D) printing refers to a number of manufacturing technologies that generate a physical model from digital information. Medical 3D printing was once an ambitious pipe dream. However, time and investment made it real. Nowadays, the 3D printing technology represents a big opportunity to help pharmaceutical and medical companies to create more specific drugs, enabling a rapid production of medical implants, and changing the way that doctors and surgeons plan procedures. Patient-specific 3D-printed anatomical models are becoming increasingly useful tools in today's practice of precision medicine and for personalized treatments. In the future, 3D-printed implantable organs will probably be available, reducing the waiting lists and increasing the number of lives saved. Additive manufacturing for healthcare is still very much a work in progress, but it is already applied in many different ways in medical field that, already reeling under immense pressure with regards to optimal performance and reduced costs, will stand to gain unprecedented benefits from this good-as-gold technology. The goal of this analysis is to demonstrate by a deep research of the 3D-printing applications in medical field the usefulness and drawbacks and how powerful technology it is.
| S-EPMC6451800 | biostudies-other