Visual Understanding Research Articles

William K. Ovalle PhD, Patrick C. Nahirney PhD Netter's Essential Histology: With Correlated Histopathology (Netter Basic Science) 3rd Edition

With strong correlations between gross anatomy and the microanatomy of structures, Netter’s Essential Histology, 3rd Edition, is the perfect text for today’s evolving medical education. Concise and easy to use, it integrates gross anatomy and embryology with classic histology slides and state-of-the-art scanning electron microscopy, offering a clear, visual understanding of this complex subject. Additional histopathology images, more clinical boxes, and new histopathology content ensure that this textbook-atlas clearly presents the most indispensable histologic concepts and their clinical relevance.Helps you recognize both normal and diseased structures at the microscopic level with the aid of succinct explanatory text as well as numerous clinical boxes. Features more histopathology content and additional clinical boxes to increase your knowledge of pathophysiology and clinical relevance. Includes high-quality light and electron micrographs, including enhanced and colorized electron micrographs that show ultra-structures in 3D, side by side with classic Netter illustrations that link your knowledge of anatomy and cell biology to what is seen in the micrographs. Provides online access to author-narrated video overviews of each chapter, plus Zoomify images and Virtual Slides that include histopathology and can be viewed at different magnifications.

ჟესტების ენა და მისი გამოყენების ტენდენციები პოლიტიკაში

It is clear that there have always been different communication forms between the people all around the world, in this case the word different is appropriate as with communication variety, also with difference between the public, culture and existed ideas in them. Thus, for politician, anywhere in the world, it is important to use verbal and non-verbal communication forms, as with the population, also with other politicians. The fact, that verbal communication is a general factor for the politician when impacting on the public, nobody denies this, and however, as a result of developing of technologies, visual understanding has more increased, that means that verbal communication can be less successful if it is not accompanied with non-verbal. We can say that at present precondition of success in politics is a well refined gesticulation for the politician, well coded around the topic. According to the above mentioned I think that the research about sign language, its theoretical analysis and research is quite important

An efficient deep learning‐based video captioning framework using multi‐modal features

AbstractVisual understanding has become more significant in gathering information in many real‐life applications. For a human, it is a trivial task to understand the content in a visual, however the same is a challenging task for a machine. Generating captions for images and videos for better understanding the situation is gaining more importance as they have wide application in assistive technologies, automatic video captioning, video summarizing, subtitling, blind navigation, and so on. The visual understanding framework will analyse the content present in the video to generate semantically accurate caption for the visual. Apart from the visual understanding of the situation, the gained semantics must be represented in a natural language like English, for which we require a language model. Hence, the semantics and grammar of the sentences being generated in English is yet another challenge. The captured description of the video is supposed to collect information of not just the objects contained in the scene, but it should also express how these objects are related to each other through the activity described in the scene, thus making the entire process a complex task for a machine. This work is an attempt to peep into the various methods for video captioning using deep learning methodologies, datasets that are widely used for these tasks and various evaluation metrics that are used for the performance comparison. The insights that we gained from our premiere work and the extensive literature review made us capable of proposing a practical, efficient video captioning architecture using deep learning which that will utilize the audio clues, external knowledge and attention context to improve the captioning process. Quantum deep learning architectures can bring about extraordinary results in object recognition tasks and feature extraction using convolutions.

Video Captioning Based on Both Egocentric and Exocentric Views of Robot Vision for Human-Robot Interaction

Robot vision provides the most important information to robots so that they can read the context and interact with human partners successfully. Moreover, to allow humans recognize the robot’s visual understanding during human-robot interaction (HRI), the best way is for the robot to provide an explanation of its understanding in natural language. In this paper, we propose a new approach by which to interpret robot vision from an egocentric standpoint and generate descriptions to explain egocentric videos particularly for HRI. Because robot vision equals to egocentric video on the robot’s side, it contains as much egocentric view information as exocentric view information. Thus, we propose a new dataset, referred to as the global, action, and interaction (GAI) dataset, which consists of egocentric video clips and GAI descriptions in natural language to represent both egocentric and exocentric information. The encoder-decoder based deep learning model is trained based on the GAI dataset and its performance on description generation assessments is evaluated. We also conduct experiments in actual environments to verify whether the GAI dataset and the trained deep learning model can improve a robot vision system

A Garbage Detection and Classification Method Based on Visual Scene Understanding in the Home Environment

Garbage classification is a social issue related to people’s livelihood and sustainable development, so letting service robots autonomously perform intelligent garbage classification has important research significance. Aiming at the problems of complex systems with data source and cloud service center data transmission delay and untimely response, at the same time, in order to realize the perception, storage, and analysis of massive multisource heterogeneous data, a garbage detection and classification method based on visual scene understanding is proposed. This method uses knowledge graphs to store and model items in the scene in the form of images, videos, texts, and other multimodal forms. The ESA attention mechanism is added to the backbone network part of the YOLOv5 network, aiming to improve the feature extraction ability of the network, combining with the built multimodal knowledge graph to form the YOLOv5-Attention-KG model, and deploying it to the service robot to perform real-time perception on the items in the scene. Finally, collaborative training is carried out on the cloud server side and deployed to the edge device side to reason and analyze the data in real time. The test results show that, compared with the original YOLOv5 model, the detection and classification accuracy of the proposed model is higher, and the real-time performance can also meet the actual use requirements. The model proposed in this paper can realize the intelligent decision-making of garbage classification for big data in the scene in a complex system and has certain conditions for promotion and landing.

Computerized glow curve deconvolution (CGCD): A comparison using asymptotic vs rational approximation in thermoluminescence kinetic models

In this study an open-source tool GCD Analyzer, based on Microsoft® Excel, for Computerized Glow Curve Deconvolution analysis (CGCD) of thermoluminescence (TL) glow peak has been developed using a more accurate rational approximation. It is capable of deconvolution of glow curves having discrete or continuous trap distribution and can be used for routine as well as emergency radiation dosimetric analysis. This tool has a unique feature of TL glow curve analysis by combining discrete and continuous energy distributions for crystalline, amorphous, and mixed materials. To obtain best values of trap parameters like activation energy (E), frequency factor (s), order of kinetics (b), GCD Analyzer has the capability of analyzing glow curve using selectable individual peak of various physical kinetic models i.e. FOK, SOK, GOK, MOK, and Continuous Traps Distribution (CTD) with subtraction of optional background signal. The residual graph gives a clear visual understanding of the Figure of Merit (F.O.M). A comparison of asymptotic and rational approximation to the built-in second order exponential integral function E2(E/KT) for E/KT < 600 is also presented. The results are verified by deconvolution of test synthetic glow curves with F.O.M up to 0.0005%, experimental glow curve for CTD with F.O.M of 0.9781%, and in the case of GLOWCANIN project glow curves, the F.O.M is comparable to the least values achieved by inter-comparison participants.

Pixel Intensity Vector Field: An Inside Out Approach of Looking at Ultrasound Reflections from the Lung at High Frame Rates.

Ultrasound (US) imaging is becoming the routine modality for the diagnosis and prognosis of lung pathologies. Lung US imaging relies on artifacts from acoustic impedance (Z) mismatches to distinguish and interpret the normal and pathological lung conditions. The air-pleura interface of the normal lung displays specularity due to the huge Z mismatches. However, in the presence of pathologies, the interface alters exhibiting a diffuse behavior due to increased density and reduced spatial distribution of air in the sub-pleural space. The specular or the diffuse behavior influences the reflected acoustic intensity distribution. This study aims to understand the reflection pattern in a normal and pathological lung through a novel approach of determining pixel-level acoustic intensity vector field (IVF) at high frame rates. Detailed lung modeling procedures using k-Wave US toolbox under normal, edematous, and consolidated conditions are illustrated. The analysis of the IVF maps on the three lung models clearly shows the drifting of the air-pleura interface from specular to diffuse with the severity of the pathology.Clinical Relevance- The presented acoustic simulation lung models are an aid to teaching and research by providing a quick visual and intuitive understanding of lung ultrasound physics. The proposed intensity vector field maps are supplementary information to aid diagnostics and characterization of any tissue composed of specular and diffuse components.

Machine Learning Method for Functional Assessment of Retinal Models.

Challenges in the field of retinal prostheses motivate the development of retinal models to accurately simulate Retinal Ganglion Cells (RGCs) responses. The goal of retinal prostheses is to enable blind individuals to solve complex, reallife visual tasks. In this paper, we introduce the functional assessment (FA) of retinal models, which describes the concept of evaluating the performance of retinal models on visual understanding tasks. We present a machine learning method for FA: we feed traditional machine learning classifiers with RGC responses generated by retinal models, to solve object and digit recognition tasks (CIFAR-10, MNIST, Fashion MNIST, Imagenette). We examined critical FA aspects, including how the performance of FA depends on the task, how to optimally feed RGC responses to the classifiers and how the number of output neurons correlates with the model's accuracy. To increase the number of output neurons, we manipulated input images - by splitting and then feeding them to the retinal model and we found that image splitting does not significantly improve the model's accuracy. We also show that differences in the structure of datasets result in largely divergent performance of the retinal model (MNIST and Fashion MNIST exceeded 80% accuracy, while CIFAR-10 and Imagenette achieved ∼40%). Furthermore, retinal models which perform better in standard evaluation, i.e. more accurately predict RGC response, perform better in FA as well. However, unlike standard evaluation, FA results can be straightforwardly interpreted in the context of comparing the quality of visual perception.

Identifying Students’ Needs Towards the Provision of Social Support in Online Learning

Social support has been found to play an important role in retaining learning and contribute to better understanding and performance among students. This study aims to determine the needs and requirements of learners or students towards the provision of social support in online learning. Random sampling technique was used to select 10 students enrolled in an ICT-based course at one of Malaysian university as respondents. The instrument for this study was a semi-structured interview questions adapted from the works of Sarason et al. (1987). Thematic analysis was performed on the transcribed interview to allow visual interpretation and understanding of the context from each response. This study found that the students had often received and prefer to get social support while learning online. The reasons for their preference were for motivation, understanding, information searching and affirmation. The students were also identified to have preference for social support from the instructor more than from peers and the learning content. Overall, Informational Support is the most expected type of social support by the students. This study provides findings that would assist in the provision of social support through the design and development of an online learning environment.

Is It a Cube? Common Visual Perception of Cuboid Drawings

A cube is one of the most fundamental shapes we can draw and can observe from a drawing. The two visualization methods most commonly applied in mathematics textbooks and education are the axonometric and the perspective representations. However, what we see in the drawing is really a cube or only a general cuboid (i.e., a polyhedron with different edge lengths). In this experimental study, 153 first-year ( 19–20-year-old) students, two-thirds of them being female, were asked to interactively adjust a cuboid figure until they believe what they see is really a cube. We were interested in how coherently people, who are actually students of arts studies and engineering with advanced spatial perception skills in most cases, evaluate these drawings. What we have experienced is that for most people there is a common visual understanding of seeing a cube (and not a general cuboid). Moreover, this common sense is surprisingly close to the conventions applied in axonometric drawings, and to the theoretical, geometric solution in the case of three-point perspective drawings, which is the most realistic visualization method.

Experimental Research on Grape Cluster Vibration Signals during Transportation and Placing for Harvest and Post-Harvest Handling

Berry dropping or shattering is an important factor during the harvest and post-harvest handling of fresh eating grapes until they reach the supermarkets. There are a lot of methods to measure post-harvest placing damage and the detachment force for single fruits. However, until now, there has been no objective method to observe and analyze the berry dropping mechanism of cluster fruits during robotic post-harvest handling. Therefore, in this paper, the effect of a cluster’s vibration on berry drop during vertical transportation and the impact of different packaging materials on fresh grape clusters during robotic placing were analyzed. For this purpose, a lead screw lathe, along with an attached actuator, three grape cluster samples (0.48, 0.50, 0.53 kg), three packaging materials (rigid plastic box, corrugated fiberboard box, expandable polystyrene box), four transportation speeds (0.4, 0.6, 0.8, 1.0 m/s), and four acceleration excitations (6, 8, 10, 12 m/s2) that were given in a mechanical system (actuator) were studied. In order to analyze the berry drop mechanism of grape clusters before and after the impact with packaging material, a force sensor and high-speed video camera were used. It was concluded from the vertical transportation test that with the increase in speed and acceleration excitations, the change in hanging force increased positively (R2 = 0.92). Additionally, the force after the striking of the grape cluster with packaging materials decreased negatively (R2 = 0.97), and the corresponding index of berry deflection increased. It was also observed from the high-speed camera images that rigid plastic boxes caused the maximum deflection of the grape berries, with the highest change in force of 8.6 N after the impact. Experimental results showed a negative correlation between the hanging force signals and the force after impact of the cluster, with a goodness of fit of R2 = 0.95 at different speeds. Overall, the proposed findings can be used as a reference study for improving robotic post-harvest handling, providing a useful visual and technical understanding of the berry fall susceptibility of cluster fruits, and can be used to develop a post-harvest robotic placing tool for avoiding berry drop damage on both industrial and farm levels.

Human Behavior Analysis: A Survey on Action Recognition

The visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, without forgetting the environmental heterogeneity between different video images. This complexity splits the problem into two major categories: action classification, recognising the action being performed in the scene, and spatiotemporal action localisation, concerning recognising multiple localised human actions present in the scene. Previous surveys mainly focus on the evolution of this field, from handcrafted features to deep learning architectures. However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison between the state-of-the-art methods.

Image Mining Based on Deep Belief Neural Network and Feature Matching Approach Using Manhattan Distance

Over the past few decades multimedia content, particularly digital images, has increased at a rapid pace, with several complex images being uploaded to various social websites such as Instagram, Facebook and Twitter. Therefore, it is difficult to search and retrieve the relevant image in seconds. Search engines retrieve images based on traditional textbased methods that depend on metadata and captions. In the last few years, a wide range of research has focused on content-based image retrieval (CBIR) based on image mining approaches. This is a challenging research area due to the ever-increasing multimedia database and other image libraries. In order to offer an effective search and retrieval, a novel CBIR system is proposed using the image mining-based deep belief neural network (IMDBN) technique. The proposed method is designed to enhance retrieval accuracy while diminishing the semantic gap between human visual understanding and image feature representation. To achieve this objective, the proposed system carries several steps like preprocessing, feature extraction, classification, and feature matching. Initially, the input database images are fed into the proposed image mining-based CBIR system, whereas colour-shape-texture (CST) feature extraction technique is applied to extract relevant feature set. The extracted features are fused and stored in the feature vector and aresubjected to the proposed IMDBN classification step to retrieve similar images in one label. Whenever a new query content is created, the most relevant images are retrieved. This, in turn, achieves 94% accuracy, which is higher than in existing approaches.

Spatial and Temporal Distribution Analysis of Traffic Accidents Using GIS-Based Data in Harbin

Road traffic safety is a social issue of widespread concern. It is important for traffic managers to understand the distribution patterns of road traffic accidents. To this end, this study examines the spatial and temporal patterns of road traffic accidents from both accident frequency and accident severity perspectives. Road traffic accident data from 2016 to 2018 in Harbin, China, were used for the analysis. First, the spatial localization of accidents was completed using geocoding, and the localized accident data were classified by season. Then, density analysis was performed both with and without considering road network density. The results of the density analysis showed that when road network density was considered, accidents were mainly distributed in urban centers, while accidents were more dispersed when road network density was not considered. Third, a cluster analysis considering accident severity found that low-severity accident clusters occurred mostly in urban centers. High-severity accident clusters were mostly present in suburban areas. Finally, the results of these two methods are shown by using the comap technique. Areas of the city with a high frequency and severity of crashes in each season were identified. This study will help traffic management to have a more visual and intuitive understanding of the urban traffic safety situation and to take targeted measures to improve it accordingly.

Short Literature Review for Visual Scene Understanding

Abstract Individuals are highly accurate for visually understanding natural scenes. By extracting and extrapolating data we reach the highest stage of scene understanding. In the past few years it proved to be an essential part in computer vision applications. It goes further than object detection by bringing machine perceiving closer to the human one: integrates meaningful information and extracts semantic relationships and patterns. Researchers in computer vision focused on scene understanding algorithms, the aim being to obtain semantic knowledge from the environment and determine the properties of objects and the relations between them. For applications in robotics, gaming, assisted living, augmented reality, etc a fundamental task is to be aware of spatial position and capture depth information. First part of this paper focuses on deep learning solutions for scene recognition following the main leads: low-level features and object detection. In the second part we present extensively the most relevant datasets for visual scene understanding. We take into consideration both directions having in mind future applications.

An Intelligent Garbage Sorting System Based on Edge Computing and Visual Understanding of Social Internet of Vehicles

In order to enable Social Internet of Vehicles devices to achieve the purpose of intelligent and autonomous garbage classification in a public environment, while avoiding network congestion caused by a large amount of data accessing the cloud at the same time, it is therefore considered to combine mobile edge computing with Social Internet of Vehicles to give full play to mobile edge computing features of high bandwidth and low latency. At the same time, based on cutting-edge technologies such as deep learning, knowledge graph, and 5G transmission, the paper builds an intelligent garbage sorting system based on edge computing and visual understanding of Social Internet of Vehicles. First of all, for the massive multisource heterogeneous Social Internet of Vehicles big data in the public environment, different item modal data adopts different processing methods, aiming to obtain a visual understanding model. Secondly, using the 5G network, the model is deployed on the edge device and the cloud for cloud-side collaborative management, aiming to avoid the waste of edge node resources, while ensuring the data privacy of the edge node. Finally, the Social Internet of Vehicles devices is used to make intelligent decision-making on the big data of the items. First, the items are judged as garbage, and then the category is judged, and finally the task of grabbing and sorting is realized. The experimental results show that the system proposed in this paper can efficiently process the big data of Social Internet of Vehicles and make valuable intelligent decisions. At the same time, it also has a certain role in promoting the promotion of Social Internet of Vehicles devices.

KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for visual commonsense reasoning

Reasoning is a critical ability towards complete visual understanding. To develop machine with cognition-level visual understanding and reasoning abilities, the visual commonsense reasoning (VCR) task has been introduced. In VCR, given a challenging question about an image, a machine must answer correctly and then provide a rationale justifying its answer. The methods adopting the powerful BERT model as the backbone for learning joint representation of image content and natural language have shown promising improvements on VCR. However, none of the existing methods have utilized commonsense knowledge in visual commonsense reasoning, which we believe will be greatly helpful in this task. Therefore, we incorporate commonsense knowledge into the cross-modal BERT, and propose a novel Knowledge Enhanced Visual-and-Linguistic BERT (KVL-BERT for short) model. Besides taking visual and linguistic contents as input, external commonsense knowledge is integrated into the multi-layer Transformer. In order to preserve the structural information and semantic representation of the original sentence, we propose an algorithm called RMGSR (Relative-position-embedding and Mask-self-attention Guided Semantic Representations). Compared to other task-specific models and general task-agnostic pre-training models, our KVL-BERT outperforms them.

Analyzing governance challenges using Process Net-Map: a case study of a government microcredit scheme in Bangladesh

PurposeThis paper aims to examine the governance challenges confronted by a government microcredit program in Bangladesh following a case study approach.Design/methodology/approachA novel qualitative research tool called process net-map (PNM) was applied to develop a framework for visual understanding of the exact credit implementation process and to identify the actors responsible for creating governance challenges. Key informant interviews were also conducted to identify and distinguish the challenges faced by both the supply-side and demand-side stakeholders.FindingsThe findings reveal that the studied case faced problems in allocating adequate resources to human and physical capacity development. It was combined with the shortage of funds that made it impossible to meet the clients’ expectations. The lack of legal and regulatory framework disabled the organization from controlling political influence and corruption in the system. Moreover, the policy of lending only to groups proved counterproductive as it led to the exclusion of potentially viable borrowers.Practical implicationsThe key recommendation of the study is on increasing the microcredit fund and a reform of the group lending policy along with several other recommendations.Originality/valueThe PNM is a newly developed participatory mapping technique that has not been applied in the field of microfinance. Therefore, the use of this method may add new knowledge of conducting an in-depth analysis of why such challenges are associated with mostly public microfinance programs and how they are linked to the implementation process. The challenges encountered are relevant for the implementation of developmental programs that are dependent on the allocation of public funds.

Current status of the environmental monitoring database on the accident at Fukushima Daiichi Nuclear Power Plant

An enormous amount of environmental monitoring data has been acquired by various organisations for the evaluation and implementation of countermeasures to mitigate the effects of the accident at the Fukushima Daiichi Nuclear Power Plant. However, it is difficult to collate, compare, and analyse this data because it was published in different formats at different sites according to the respective objectives of the publishing organisations. Moreover, these organisations have been accumulating data in large volumes for over nine years after the accident. We established procedures to collect this data, convert them into a unified format, classify them according to categories, and make the data accessible on a web-based database system. The database contains environmental monitoring data on air dose rates, ground deposition densities, and concentrations in various environmental samples such as soil, water, and food. This data is being provided not only in numerical format for quantitative analysis but also as distribution maps and time-series graphs for visual understanding. The database system enabled us to spatially and temporally compare large volumes of monitoring data. By using the database functions, characteristics of some representative data in the database was clarified.

Orthodontic Treatment with Clear Aligners

The paradigm shift in orthodontics arrived with the introduction of Aligner System. It allows both dental practitioner and patient to develop a visual understanding of orthodontic tooth movement. The esthetic and practical advantages of the system have extended orthodontic services to a greater population. The transparency of the clear aligners enhances its esthetic appeal for those adult patients who are averse to wearing conventional labial fixed orthodontic appliances. Although guidelines about the types of malocclusions that this technique can treat exist, few clinical studies have assessed the effectiveness of the appliance.