LCA-GAN: Low-Complexity Attention-Generative Adversarial Network for Age Estimation with Mask-Occluded Facial Images

Facial-image-based age estimation is being increasingly used in various fields. Examples include statistical marketing analysis based on age-specific product preferences, medical applications such as beauty products and telemedicine, and age-based suspect tracking in intelligent surveillance camera systems. Masks are increasingly worn for hygiene, personal privacy concerns, and fashion. In particular, the acquisition of mask-occluded facial images has become more frequent due to the COVID-19 pandemic. These images cause a loss of important features and information for age estimation, which reduces the accuracy of age estimation. Existing de-occlusion studies have investigated masquerade masks that do not completely occlude the eyes, nose, and mouth;however, no studies have investigated the de-occlusion of masks that completely occlude the nose and mouth and its use for age estimation, which is the goal of this study. Accordingly, this study proposes a novel low-complexity attention-generative adversarial network (LCA-GAN) for facial age estimation that combines an attention architecture and conditional generative adversarial network (conditional GAN) to de-occlude mask-occluded human facial images. The open databases MORPH and PAL were used to conduct experiments. According to the results, the mean absolution error (MAE) of age estimation with the de-occluded facial images reconstructed using the proposed LCA-GAN is 6.64 and 6.12 years, respectively. Thus, the proposed method yielded higher age estimation accuracy than when using occluded images or images reconstructed using the state-of-the-art method.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.Copyright © 2022 Inderscience Enterprises Ltd.

A Novel Approach of Smart Contract based Distributed Ledger Technology using Deep Learning Techniques to Secure Medical Images

Internet of Medical Things (IoMT) is on-demand research area, generally utilized in most of medical applications. Security is a challenging problem in decentralized platform while handling with medical data or images. An effective deep learning-based blockchain framework with reduced transaction cost is proposed to enhance the security of medical images in IoMT. The proposed study involves four different stages like image acquisition, encryption, optimal key generation, secured storing. The input images initially are collected in the image acquisition stage. Then, the collected medical images are encrypted using coupled map lattice (CML). This encryption process assists to preserve the input medical images from the attackers. In order to provide more confidentiality to the encrypted images, optimal keys are generated using opposition-based sparrow search optimization (O-SSO) algorithm. These encrypted images are stored using distributed ledger technology (DLT) and smart contract based blockchain technology. This blockchain technology enhances the data integrity and authenticity and allows secured transmission of medical images. After decrypting the image, the disease is diagnosed in the classification stage using proposed Recurrent Generative Neural Network (RGNN) model. The proposed study used python tool for simulation analysis and the medical images are gathered from CT images in COVID-19 dataset. © 2022 IEEE.

Smart Artificial Intelligence techniques using embedded band for diagnosis and combating COVID-19.

Recently, COVID-19 virus spread to create a major impact in human body worldwide. The Corona virus, initiated by the SARS-CoV-2 virus, was known in China, December 2019 and affirmed a worldwide epidemic by the World Health Organization on 11 March 2020. The core aim of this research is to detect the spreading of COVID-19 virus and solve the problems in human lungs infection quickly. An Artificial Intelligence (AI) technique is a possibly controlling device in the battle against the corona virus epidemic. Recently, AI with computational techniques are utilized for COVID-19 virus with the building blocks of Deep Learning method using Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) is used to classify and identify the lung images affected region. These two algorithms used to diagnose COVID-19 infections rapidly. The AI applications against COVID-19 are Medical Imaging for Diagnosis, Lung delineation, Lesion measurement, Non-Invasive Measurements for Disease Tracking, Patient Outcome Prediction, Molecular Scale: from Proteins to Drug Development and Societal Scale: Epidemiology and Infodemiology.

Multi-modal lung ultrasound image classification by fusing image-based features and probe information

Lung ultrasound is a widely used portable, cheap, and non-invasive medical imaging technology that can be used to identify various lung pathologies. In this work, we propose a multi-modal approach for lung ultrasound image classification that combines image-based features with information about the type of ultrasound probe used to acquire the input image. Experiments on a large lung ultrasound image dataset that contains images acquired with a linear or a convex ultrasound probe demonstrated the superiority of the proposed approach for the task of classifying lung ultrasound images as "COVID-19”, "Normal”, "Pneumonia”, or "Other”, when compared to simply using image-based features. Classification accuracy reached 99.98% using the proposed combination of the Xception pre-trained CNN model with the ultrasound probe information, as opposed to 96.81% when only the pre-trained EfficientNetB4 CNN model was used. Furthermore, the experimental results demonstrated a consistent improvement in classification performance when combining the examined base CNN models with probe information, indicating the efficiency of the proposed approach. © 2022 IEEE.

An Effective Approach for Forgery Detection of Fake COVID-19 Report

With advancements in technology and image processing software, digital image forgery has become increasingly simple. However, because digital images, such as COVID-19 reports, are a common source of information, the authenticity of these digital reports has become a big concern. In recent days, it has been discovered that an increasing number of academics have begun to focus on the issue of digital report manipulation. A new deep learning-based digital picture forgery detection solution has been acquired. The mechanism is intended to ensure that the COVID-19 report on health care has not been amended or tampered with. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4

Over the past few decades, research on object detection has developed rapidly, one of which can be seen in the fashion industry. Fast and accurate detection of an E-commerce fashion product is crucial to choosing the appropriate category. Nowadays, both new and second-hand clothing is provided by E-commerce sites for purchase. Therefore, when categorizing fashion clothing, it is essential to categorize it precisely, regardless of the cluttered background. We present recently acquired tiny product images with various resolutions, sizes, and positions datasets from the Shopee E-commerce (Thailand) website. This paper also proposes the Fashion Category—You Only Look Once version 4 model called FC-YOLOv4 for detecting multiclass fashion products. We used the semi-supervised learning approach to reduce image labeling time, and the number of resulting images is then increased through image augmentation. This approach results in reasonable Average Precision (AP), Mean Average Precision (mAP), True or False Positive (TP/FP), Recall, Intersection over Union (IoU), and reliable object detection. According to experimental findings, our model increases the mAP by 0.07 percent and 40.2 percent increment compared to the original YOLOv4 and YOLOv3. Experimental findings from our FC-YOLOv4 model demonstrate that it can effectively provide accurate fashion category detection for properly captured and clutter images compared to the YOLOv4 and YOLOv3 models.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.

Contactless COVID-19 vaccine verification system

The novel Corona virus has created maximum impact to the society with growing challenges as a result of its new evaluation. The development of new strategic plans or initiated to safeguard the people from global pandemic were wearing Mask in public places sanitization or employed to have maximum protection. Various modifications or derived in public places to avoid contact with each other physically. The proposed studies focus on the driving a Roberts to model for contact us communication is established. The proposed approach utilised Embedded Technology enabled vaccinated people verification is done. Proposed design is identified as an advance people identification system using advance to computing techniques with Raspberry Pi 4. The benefit of reconfigurable embedded technology offers low cost and reliable hardware used to make customized consumer products. The proposed system can be placed in public places to validate the people entry. Automated systems are highly reliable in long term accessibility. The system can be installed anywhere easily using a small camera object and display insertion. © 2022 International Journal of Health Sciences.

Using the VENµS Super-Spectral Camera for detecting moving vehicles

Monitoring transportation for planning, management, and security purposes has become a growing interest for various stakeholders. A methodology for detecting moving vehicles is based on the acquisition time gap between the pushbroom detector sub-arrays. However, this technique requires overcoming differences in ground sampling distance and/or spectral features of the sensor’s bands used for change detection. The current work demonstrates a proof of concept for the VENµS satellite’s capability to detect moving vehicles in a single pass with a relatively low spatial resolution. The VENµS Super-Spectral Camera has a unique stereoscopic capability because the two spectral bands, with the same central wavelength and width, are positioned at the extreme ends of the camera’s focal plane. This design enables a 2.7-sec difference in observation time. The normalized difference moving object index (NDMOI) has been designed to detect moving vehicles using these bands without image preprocessing for dimensionality reduction or geometric corrections, as other sensors require. Results show the successful detection of small- to medium-sized moving vehicles. Especially interesting is the detection of private cars that are, on average, 2–3 m smaller than the VENµS ground sampling distance. Vehicle movement was effectively detected in different backgrounds/environments, e.g., on asphalt and unpaved roads, as well as over bare soil and plowed fields. Furthermore, a multitemporal analysis of moving vehicles during the Covid-19 pandemic in 2020 shows the effectiveness of the proposed methodology.

Covid 19-Lung Segmentation and Detection-A Literature Review

The 2019 corona virus pandemic (COVID-19) has expanded worldwide. Medical imaging, such as X-rays and CT, plays a crucial part in the worldwide fight of COVID-19, whilst new technologies of artificial intelligence (AI) further increase the imagery tools and assist medical professionals. We examine the quick reactions to COVID-19 in the medical imaging community, propelled by AI. For example, AI-enhanced picture collection may greatly assist to automate the process of scanning and also restructure the workflow with little patient interaction, giving the imagery professionals the greatest protection. In this review, the methods of extracting the features for lung CT images and for segmentation and classification we searched many data source like IEEE, Elsevier, Springer, the correct delineation of infectious X-ray and CT images by AI may further increase the job efficiency, making quantification afterwards more efficient. In addition, radiographers make clinical judgments, for example for diagnosis, tracking and prognosis of the disease, with their computer assist platforms. This review study thus covers the complete medical imagers' pipeline, including the capture of images, segmentation, diagnosis, and follow-up approaches including COVID-19. The implementation of Smart into X-ray and CT, both frequently employed in frontline hospitals, is particularly important to show the newest advances in the fight against COVID-19 in diagnostic imaging and radiology. X-rays and CT in chests are commonly employed in the COVID-19 testing and diagnosis. In order to minimise the high danger of infection during the COVID-19 pandemic, contactless and automated image capture workflows are needed. The usual process of imagery however, entails inescapable interaction between technicians and patients. In particular, the technicians assist in the positioning of the patient first in posing the patient according to a certain protocol, such as first-head versus first-foot, and supine versus prone at CT, then visually identify the target part of the patient's body location, and manually adjust the relative position and position between the patient and the x- ray tube. This procedure enables personnel to touch patients closely, which leads to significant risk of virus exposure. A contactless and automated picture process is therefore necessary to reduce interaction.

Customization and testing of a mobile reader app for an open-access SARS-CoV-2 antigen lateral flow assay

Lateral flow assays (LFA’s) are a common diagnostic test form, particularly in low-to-middle income countries (LMIC’s). Visual interpretation of LFA’s can be subjective and inconsistent, especially with faint positive results, and commercial readers are expensive and challenging to implement in LMIC’s. We report a phone-agnostic Android app to acquire images and interpret results of a variety of LFA’s with no additional hardware. Starting from the open-source “rdt-scan” codebase, we integrated new features and revamped the peak detection method. This included improved perspective corrections, phone level check to eliminate shadows, high resolution still-image capture besides existing video frame capture, and new peak detection method. This peak detection incorporated smoothing and baseline removal from the one-dimensional profiles of a given color channel’s intensity averaged across the read window’s width, with location and relative size constraints to correctly report locations and peak heights of control and test lines. The app was tested in a real-world setting in conjunction with an open-access LFA for SARS-CoV-2 antigen developed by GH Labs. The app acquired 155 images of LFA cassettes, and results were compared against both visual interpretation by trained clinical staff and PCR results from the same patients. With an appropriate setting for test line intensity threshold, the app matched visual read for all cases but one missed visual positive. From ROC analyses against PCR, the app outperformed visual read by 1-3% across sensitivity, specificity, and AUC. The app thus demonstrated promise for accurate, consistent interpretation of LFA’s while generating digital records that could also be useful for health surveillance. © 2022 SPIE

A Review on AI-Based Techniques for Tackling COVID-19

Corona virus has affected the lives of people significantly due to its very high transmission rate. It is a serious threat to human beings. Therefore, it has become quite a challenge for governments, companies, researchers, and other health organizations for developing policies to reduce the effects of corona virus and developing its cure as soon as possible. Technologies, particularly artificial intelligence (AI), are playing a vital role in managing COVID-19 as it is capable of rapidly processing a large amount of data and analyzing it in no time. AI-based techniques such as machine learning, deep learning, etc. are being actively used by several nations for fighting against COVID-19. These techniques are already being used for diagnosing patients, drug discovery, awareness, training of doctors and support staff, etc. The aim of this study is to survey the available literature and present the role of AI in tackling COVID-19 all around the world. Further, it discusses various applications of AI such as diagnosing patients, tracking, monitoring patient’s health, discovering drugs, spreading awareness, etc. for fighting against the pandemic, and this study also identifies the approaches that are currently being proposed by the researcher for diagnosing COVID-19 patients using CT and X-ray images. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Contactless Palm Vein Biometric Authentication and Health Monitoring Device

Today, the novel COVID-19 pandemic has taken a significant toll on countries worldwide and impacted the lives and well-being of people across nations. Measures need to be taken to slow down the spread of such viruses, which can be reduced by taking proper precautions to avoid unnecessary contact and incurring hygienic habits. People can become infected by touching infected objects or surfaces, then touching their eyes, nose or mouth. We need proper and hygienic authentication systems for granting access to authorized users at various places such as companies, universities, banks, etc. Today there are multiple biometric systems that can serve this purpose, but to maintain hygiene we need systems that are contactless in nature thus to reduce spread of infections through touch. The palm vein pattern is distinctive biometric identity of individuals that is also a safe and reliable biometric authentication technique. The major advantage of palm vein biometric that we consider in our proposed system is that this kind of authentication can be done in a contactless way. Here, we propose an authentication system that uses palm vein pattern biometric to authenticate users in a contactless way. We have also added the functionalities of temperature detection and blood oxygen level detection to this system. These health symptoms are the major symptoms of various fatal virus infections such as the coronavirus. By checking the users for these symptoms before granting access, we can further limit the spread of infections and also help detect the infected patients. The proposed system does this in a contactless way. © 2021 IEEE.

Machine Intelligent Techniques for COVID-19 Detection: A Critical Review and Analysis

Every human being is discussing a highly addressed topic in the current days which is about the COrona VIrus Disease (COVID) in 2019-2020. The outbreak of corona has affected the human race all over the world, the patient count is increasing day by day, and doctors are in a critically need of computer-aided diagnosis with machine learning (ML) algorithms that will discover and diagnose the coronavirus for a large number of patients. Also, it is more complicated to estimate the discharge time and the criticalness of the patient during treatment. Chest computed tomography (CT) scan was the best tool for the corona diagnosis. Also survival analysis methods in ML outperform better in predicting discharge time. In this, we survey on the COVID 19 diagnosis with a chain of CT scan pictures mined from the COVID-19 data set by using ML algorithms like marine predator, simplified suspected infected recovered (SIR), image acquisition, and some more techniques and also survival analysis techniques of ML. The survey clearly explains the models used up to now which are highly defined for the diagnosis of COVID-19 Virus. © 2021 IEEE.

A New Methodology for Bridge Inspections in Linear Infrastructures from Optical Images and HD Videos Obtained by UAV

Many bridges and other structures worldwide present a lack of maintenance or a need for rehabilitation. The first step in the rehabilitation process is to perform a bridge inspection to know the bridge′s current state. Routine bridge inspections are usually based only on visual recognition. In this paper, a methodology for bridge inspections in communication routes using images acquired by unmanned aerial vehicle (UAV) flights is proposed. This provides access to the upper parts of the structure safely and without traffic disruptions. Then, a standardized and systematized novel image acquisition protocol is applied for data acquisition. Afterwards, the images are studied by civil engineers for damage identification and description. Then, specific structural inspection forms are completed using the acquired information. Recommendations about the need of new and more detailed inspections should be included at this stage when needed. The suggested methodology was tested on two railway bridges in France. Image acquisition of these structures was performed using an UAV for its ability to provide an expert assessment of the damage level. The main advantage of this method is that it makes it possible to safely accurately identify diverse damages in structures without the need for a specialised engineer to go to the site. Moreover, the videos can be watched by as many engineers as needed with no personal movement. The main objective of this work is to describe the systematized methodology for the development of bridge inspection tasks using a UAV system. According to this proposal, the in situ inspection by a specialised engineer is replaced by images and videos obtained from an UAV flight by a trained flight operator. To this aim, a systematized image/videos acquisition method is defined for the study of the morphology and typology of the structural elements of the inspected bridges. Additionally, specific inspection forms are proposed for every type of structural element. The recorded information will allow structural engineers to perform a postanalysis of the damage affecting the bridges and to evaluate the subsequent recommendations.

Super-resolution using Deep Networks for Chest X-Ray Images

Super-resolution imaging is extensively deliberated in medical imaging modalities nowadays, there being a wide panic on the effect of COVID-19 virus impression. Generally, spatial resolutions of CXR are insufficient due to the constraints such as image acquisition time, hardware limits and physical limits. It is a clinically challenging task to recover the high resolution CXR images. A significant concern in CXR imaging is X-Ray contrast disparity and the demand to attain high quality images with adequate structural and imaging details. To address these problems, we propose an effective deep network for the super-resolution reconstruction method to recover high-resolution CXR images while retaining diagnostic capabilities. Specifically, the reinforcement subnetwork is hosted to generate sharp and informative qualitative features. The quantitative and qualitative assessments found that the proposed model based on the evaluation index improves the CXR super-resolution. In addition, the PSNR index of the proposed model has 0.30 higher than that of the SRCNN network. © 2021 IEEE.

A Deep Learning Neural Network Techniques in Visualization, Imaging Data Acquisition And Diagnosis for Covid-19

The corona virus disease pandemic of 2019 (COVID-19) is sweeping the globe. Medical imaging, such as X-ray and computed tomography (CT), is critical in the global fight against COVID-19, and recently evolving artificial intelligence (AI) technologies are enhancing the capacity of imaging tools and assisting medical specialists. For example, image acquisition driven by Deep Learning Architecture may help optimise the scanning process and reshape the workflow with minimal patient intervention, ensuring the best security for imaging technicians. Furthermore, computer-aided platforms assist radiologists in making clinical decisions, such as disease identification, surveillance, and prognosis. In this workflow, we cover the full range of COVID-19-related medical imaging and analysis techniques, including image processing, segmentation, diagnosis, and follow-up. Traditional methods are used to interpret the evaluation, and various output metrics are collected._

Diagnosis and combating COVID-19 using wearable Oura smart ring with deep learning methods.

Since the coronavirus (COVID-19) outbreak keeps on spreading all through the world, scientists have been crafting varied technologies mainly focusing on AI for an approach to acknowledge the difficulties of the epidemic. In this current worldwide emergency, the clinical business is searching for new advancements to screen and combat COVID-19 contamination. Strategies used by artificial intelligence can stretch screen the spread of the infection, distinguish highly infected patients, and be compelling in supervising the illness continuously. The artificial intelligence anticipation can further be used for passing dangers by sufficiently dissecting information from past sufferers. International patient support with recommendations for population testing, medical care, notification, and infection control can help fight this deadly virus. We proposed the hybrid deep learning method to diagnose COVID-19. The layered approach is used here to measure the symptom level of the patients and to analyze the patient image data whether he/she is positive with COVID-19. This work utilizes smart AI techniques to predict and diagnose the coronavirus rapidly by the Oura smart ring within 24 h. In the laboratory, a coronavirus rapid test is prepared with the help of a deep learning model using the RNN and CNN algorithms to diagnose the coronavirus rapidly and accurately. The result shows the value 0 or 1. The result 1 indicates the person is affected with coronavirus and the result 0 indicates the person is not affected with coronavirus. X-Ray and CT image classifications are considered here so that the threshold value is utilized for identifying an individual's health condition from the initial stage to a severe stage. Threshold value 0.5 is used to identify coronavirus initial stage condition and 1 is used to identify the coronavirus severe condition of the patient. The proposed methods are utilized for four weighting parameters to reduce both false positive and false negative image classification results for rapid and accurate diagnosis of COVID-19.