Pre-trained VGG-16 Model Research Articles

An Enhanced Transfer Learning Based Classification for Diagnosis of Skin Cancer.

Skin cancer is the most commonly diagnosed and reported malignancy worldwide. To reduce the death rate from cancer, it is essential to diagnose skin cancer at a benign stage as soon as possible. To save lives, an automated system that can detect skin cancer in its earliest stages is necessary. For the diagnosis of skin cancer, various researchers have performed tasks using deep learning and transfer learning models. However, the existing literature is limited in terms of its accuracy and its troublesome and time-consuming process. As a result, it is critical to design an automatic system that can deliver a fast judgment and considerably reduce mistakes in diagnosis. In this work, a deep learning-based model has been designed for the identification of skin cancer at benign and malignant stages using the concept of transfer learning approach. For this, a pre-trained VGG16 model is improved by adding one flatten layer, two dense layers with activation function (LeakyReLU) and another dense layer with activation function (sigmoid) to enhance the accuracy of this model. This proposed model is evaluated on a dataset obtained from Kaggle. The techniques of data augmentation are applied in order to enhance the random-ness among the input dataset for model stability. The proposed model has been validated by considering several useful hyper parameters such as different batch sizes of 8, 16, 32, 64, and 128; different epochs and optimizers. The proposed model is working best with an overall accuracy of 89.09% on 128 batch size with the Adam optimizer and 10 epochs and outperforms state-of-the-art techniques. This model will help dermatologists in the early diagnosis of skin cancers.

Ftl-CoV19: A Transfer Learning Approach to Detect COVID-19.

COVID-19 is an infectious and contagious disease caused by the new coronavirus. The total number of cases is over 19 million and continues to grow. A common symptom noticed among COVID-19 patients is lung infection that results in breathlessness, and the lack of essential resources such as testing, oxygen, and ventilators enhances its severity. Chest X-ray can be used to design and develop a COVID-19 detection mechanism for a quicker diagnosis using AI and machine learning techniques. Due to this silver lining, various new COVID-19 detection techniques and prediction models have been introduced in recent times based on chest radiography images. However, due to a high level of unpredictability and the absence of essential data, standard models have showcased low efficiency and also suffer from overheads and complexities. This paper proposes a model fine tuning transfer learning-coronavirus 19 (Ftl-CoV19) for COVID-19 detection through chest X-rays, which embraces the ideas of transfer learning in pretrained VGG16 model with including combination of convolution, max pooling, and dense layer at different stages of model. Ftl-CoV19 reported promising experimental results; it observed training and validation accuracy of 98.82% and 99.27% with precision of 100%, recall of 98%, and F1 score of 99%. These results outperformed other conventional state of arts such as CNN, ResNet50, InceptionV3, and Xception.

Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis.

Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN). After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 ± 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan-Meier analysis revealed that mortality in patients from Cluster 2 (n = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1-8.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4-5.1, P-value: 0.004). Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after TAVR.

Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.

Edge-Conditioned Feature Transform Network for Hyperspectral and Multispectral Image Fusion

Despite recent advances achieved by deep learning techniques in the fusion of low-spatial-resolution hyperspectral image (LR-HSI) and high-spatial-resolution multispectral image (HR-MSI), it remains a challenge to reconstruct the high-spatial-resolution HSI (HR-HSI) with more accurate spatial details and less spectral distortions, since the low-level structure information such as sharp edges tends to be weakened or lost as the network depth grows. To tackle this issue, we creatively propose an edge-conditioned feature transform network (EC-FTN) in this article, which is mainly composed of three parts, namely, feature extraction network (FEN), feature fusion and transformation network (FFTN), and image reconstruction network (IRN). First, two computationally efficient FENs with 3-D convolutions and reshaping layers are employed to extract the joint spectral-spatial features of input images. Then, the FFTN conditioned on the edge map prior can fuse and transform the features adaptively, in which a fusion node and several cascaded feature modulation modules (FMMs) equipped with feature-wise modulation layers are constructed. Specifically, the edge map is generated via transfer learning, i.e., by applying the Sobel operator to feature maps of the red-green-blue (RGB) version of HR-MSI resulting from the pretrained VGG16 model without extra training. Finally, the desired HR-HSI is recovered from the transformed features through IRN. Furthermore, we elaborately design a weighted combinatorial loss function consisting of mean absolute error, image gradient difference, and spectral angle terms to guide the training. Experiments on both ground-based and remotely sensed datasets demonstrate that our EC-FTN outperforms state-of-the-art methods in visual and quantitive evaluations, as well as in fine details reconstruction.

The Impact of a Number of Samples on Unsupervised Feature Extraction, Based on Deep Learning for Detection Defects in Printed Circuit Boards

Deep learning provides new ways for defect detection in automatic optical inspections (AOI). However, the existing deep learning methods require thousands of images of defects to be used for training the algorithms. It limits the usability of these approaches in manufacturing, due to lack of images of defects before the actual manufacturing starts. In contrast, we propose to train a defect detection unsupervised deep learning model, using a much smaller number of images without defects. We propose an unsupervised deep learning model, based on transfer learning, that extracts typical semantic patterns from defect-free samples (one-class training). The model is built upon a pre-trained VGG16 model. It is further trained on custom datasets with different sizes of possible defects (printed circuit boards and soldered joints) using only small number of normal samples. We have found that the defect detection can be performed very well on a smooth background; however, in cases where the defect manifests as a change of texture, the detection can be less accurate. The proposed study uses deep learning self-supervised approach to identify if the sample under analysis contains any deviations (with types not defined in advance) from normal design. The method would improve the robustness of the AOI process to detect defects.

Deep learning methods in the diagnosis of sacroiliitis from plain pelvic radiographs.

The aim of this study is to develop a computer-aided diagnosis method to assist physicians in evaluating sacroiliac radiographs. Convolutional neural networks, a deep learning method, were used in this retrospective study. Transfer learning was implemented with pre-trained VGG-16, ResNet-101 and Inception-v3 networks. Normal pelvic radiographs (n = 290) and pelvic radiographs with sacroiliitis (n = 295) were used for the training of networks. The training results were evaluated with the criteria of accuracy, sensitivity, specificity and precision calculated from the confusion matrix and AUC (area under the ROC curve) calculated from ROC (receiver operating characteristic) curve. Pre-trained VGG-16 model revealed accuracy, sensitivity, specificity, precision and AUC figures of 89.9%, 90.9%, 88.9%, 88.9% and 0.96 with test images, respectively. These results were 84.3%, 91.9%, 78.8%, 75.6 and 0.92 with pre-trained ResNet-101, and 82.0%, 79.6%, 85.0%, 86.7% and 0.90 with pre-trained inception-v3, respectively. Successful results were obtained with all three models in this study where transfer learning was applied with pre-trained VGG-16, ResNet-101 and Inception-v3 networks. This method can assist clinicians in the diagnosis of sacroiliitis, provide them with a second objective interpretation and also reduce the need for advanced imaging methods such as magnetic resonance imaging.

A Novel Machine Learning Based Framework for Detection of Autism Spectrum Disorder (ASD)

ABSTRACT Autism Spectrum Disorder (ASD) is linked with abridged ability in social behavior. Scientists working in the broader domain of cognitive sciences have done a lot of research to discover the root cause of ASD, but its biomarkers are still unknown. Some studies from the domain of neuroscience have highlighted the fact that corpus callosum and intracranial brain volume hold significant information for the detection of ASD. Taking inspiration from such findings, in this article, we have proposed a machine learning based framework for automatic detection of ASD using features extracted from corpus callosum and intracranial brain volume. Our proposed framework has not only achieved good recognition accuracy but has also reduced the complexity of training machine learning model by selecting features that are most significant in terms of discriminative capabilities for classification of ASD. Second, for benchmarking and to verify potential of deep learning on analyzing neuroimaging data, in this article, we have presented results achieved by using the transfer learning approach. For this purpose, we have used the pre-trained VGG16 model for the classification of ASD.

Abstract 9220: Employing a Convolutional Neural Network Facilitates Unsupervised Clustering of Aortic Outflow Velocity Profiles from Patients With Severe Aortic Stenosis

Introduction: The aortic outflow velocity profile is key to diagnose severe aortic stenosis (AS), and its shape reflects both aortic valve obstruction and left ventricular contractility. Hypothesis: Hypothesizing that aortic outflow velocity profiles contain more valuable information than can be captured by the human eye, features of the complex geometry of Doppler tracings were extracted by a convolutional neural network (CNN) pre-trained on big data (transfer learning). Methods: After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1,000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Principal component analysis (PCA) and k-means clustering of those 1D arrays were performed, and association between cluster and 2-year all-cause mortality was hereinafter assessed. Among 366 eligible patients with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR) for severe AS, good quality Doppler tracings from 101 patients were analyzed. Results: Among 101 patients (mean age: 79.3 ± 6.78 years; 49 [48.5%] women), estimated 2-year survival was 83.0% (95% CI: 75.1-91.7%). The convolutional part of the pre-trained VGG-16 model in conjunction with PCA and k-means clustering distinguished 2 shapes of aortic outflow velocity profiles. Kaplan-Meier analysis revealed that mortality in patients from cluster 2 (n = 40 [39.6%]) was significantly increased (HR for 2-year mortality: 3 [95% CI: 1-8.9]). Apart from reduced cardiac output and mean aortic valve gradient (AVG mean ), patients from cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function and right atrial enlargement. Conventional dichotomization according to AVG mean confirmed that patients with AVG mean < 40 mmHg (n = 54 [53.5%]) decease earlier, but no statistical significance was reached (HR for 2-year mortality: 1.8 [95% CI: 0.59-5.2]). Conclusions: This is a proof-of-principle that transfer learning aids in agnostic interpretation of aortic outflow velocity profiles, thereby holding the promise to refine prognostic resolution for survival after TAVR.

Bottle-Feeding Intervention Detection in the NICU.

Video-based monitoring of patients in the neonatal intensive care unit (NICU) has great potential for improving patient care. Video-based detection of clinical events, such as bottle feeding, would represent a step towards semi-automated charting of clinical events. Recording such events contemporaneously would address the limitations associated with retrospective charting. Such a system could also support oral feeding assessment tools, as the patient's feeding skills and nutrition are pivotal in monitoring their growth. We therefore leverage transfer learning using a pretrained VGG-16 model to classify images obtained during an intervention, to determine if a bottle-feeding event is occurring. Additionally, we explore a data expansion technique by extracting similar-feature images from publicly available sources to supplement our dataset of real NICU patients to address data scarcity. This work also visualizes and quantifies the gap between the source domain (ImageNet data subset) and target domain (NICU dataset), thereby illustrating the impact of expanding our training set for knowledge transfer proficiency. Results show an increase of over 18% in sensitivity after data expansion. Analysis of network activation maps indicates that data expansion is able to reduce the distance between the source and target domains.

Deep Learning for Effective Refugee Tent Extraction Near Syria–Jordan Border

Rukban is a desert area crossing the border between Syria and Jordan, and thousands of Syrian refugees fled into this area since the Syrian civil war in 2014. In the past few years, the number of refugee shelters for the forcibly displaced Syrian refugees in this area has increased rapidly. Estimating the location and number of refugee tents has become a key factor to maintain the sustainability of the refugee shelter camps. Manually counting the shelters is labor-intensive and sometimes prohibitive given the large quantities. In addition, these shelters/tents are usually small in size, irregular in shape, and sparsely distributed in a very large area and could be easily missed by the traditional image-analysis techniques, making the image-based approaches also challenging. In this letter, we proposed a deep fully convolutional neural network (FCN) model to extract automatically the refugee shelters/tents in the worldview-2 (WV-2) satellite images. In addition, we transferred knowledge in the pretrained VGG-16 model to improve the detection accuracy and network training convergence. We compared the proposed approach with the traditional spectral angle mapper (SAM) method, deep convolutional neural network (CNN) models, and the mask Region-based CNN (R-CNN) model. The experimental results show that the FCN model improved the overall accuracy by 4.49%, 3.54%, and 0.88% compared with the CNNs, SAM, and mask R-CNN models, and improved the precision by 34.61%, 41.99%, and 11.87%, respectively.

Spotting Deepfakes and Face Manipulations by Fusing Features from Multi-Stream CNNs Models

Deepfake is one of the applications that is deemed harmful. Deepfakes are a sort of image or video manipulation in which a person’s image is changed or swapped with that of another person’s face using artificial neural networks. Deepfake manipulations may be done with a variety of techniques and applications. A quintessential countermeasure against deepfake or face manipulation is deepfake detection method. Most of the existing detection methods perform well under symmetric data distributions, but are still not robust to asymmetric datasets variations and novel deepfake/manipulation types. In this paper, for the identification of fake faces in videos, a new multistream deep learning algorithm is developed, where three streams are merged at the feature level using the fusion layer. After the fusion layer, the fully connected, Softmax, and classification layers are used to classify the data. The pre-trained VGG16 model is adopted for transferred CNN1stream. In transfer learning, the weights of the pre-trained CNN model are further used for training the new classification problem. In the second stream (transferred CNN2), the pre-trained VGG19 model is used. Whereas, in the third stream, the pre-trained ResNet18 model is considered. In this paper, a new large-scale dataset (i.e., World Politicians Deepfake Dataset (WPDD)) is introduced to improve deepfake detection systems. The dataset was created by downloading videos of 20 different politicians from YouTube. Over 320,000 frames were retrieved after dividing the downloaded movie into little sections and extracting the frames. Finally, various manipulations were performed to these frames, resulting in seven separate manipulation classes for men and women. In the experiments, three fake face detection scenarios are investigated. First, fake and real face discrimination is studied. Second, seven face manipulations are performed, including age, beard, face swap, glasses, hair color, hairstyle, smiling, and genuine face discrimination. Third, performance of deepfake detection system under novel type of face manipulation is analyzed. The proposed strategy outperforms the prior existing methods. The calculated performance metrics are over 99%.

Comparative Study of Image Processing and Transfer Learning Techniques for an Automated PCB Fault Detection System

Printed circuit board (PCB) is one of the most crucial components in most electronic devices. PCBs are manufactured in large quantities, and therefore, maintaining the quality of such large numbers of PCBs is important. An automated inspection system can help in the aspect of quality maintenance. Such a system is able to overcome the limitations of manual inspection for a large number of PCBs. It provides fast detection of defects and hence can prove to be an asset in the manufacturing process. This project aims to achieve fault detection of bare PCBs through two different methods; the traditional algorithmic approach using image processing, which makes use of image subtraction method, and a transfer learning approach, which involves the pre-trained CNN VGG16 model. A comparative study of both the methods is done.

Towards open-source LOD2 modelling using convolutional neural networks

The aim of this paper is to classify and segment roofs using vertical aerial imagery to generate three-dimensional (3D) models. Such models can be used, for example, to evaluate the rainfall runoff from properties for rainwater harvesting and in assessing solar energy and roof insulation options. Aerial orthophotos and building footprints are used to extract individual roofs and bounding boxes, which are then fed into one neural network for classification and then another for segmentation. The approach initially implements transfer learning on a pre-trained VGG16 model. The first step achieves an accuracy of 95.39% as well as a F1 score of 95%. The classified images are segmented using a fully convolutional network semantic segmentation model. The mask of the segmented roof planes is used to extract the coordinates of the roof edges and the nexus points using the Harris corner detector algorithm. The coordinates of the corners are then used to plot a 3D Level of Detail 2 (LOD2) representation of the building and the roof height is determined by calculating the maximum and minimum height of a Digital Surface Model LiDAR point cloud and known building height data. Subsequently the wireframe plot can be used to compute the roof area. This model achieved an accuracy of 80.2%, 96.1%, 96.0%, 85.1% and 91.1% for flat, hip, gable, cross-hip and mansard roofs, respectively.

Multi-modal cyber-aggression detection with feature optimization by firefly algorithm

Aggressive comments containing offensive images and inappropriate gesture signs together with textual comments have grown exponentially in the recent past on social media. These aggressive contents on social media are affecting the victims negatively causing fear, stress, sleeping problems and even suicide in some cases. Since social media contents are unmoderated, a technical solution with the characteristic of having automatic flagging of these contents considering the text and images together is highly needed. This article presents a deep learning and binary firefly-based optimization-based model to classify the social media posts into high-aggressive, medium-aggressive, and non-aggressive classes. The proposed model considers both text and images together to evaluate the aggression level of a post. In this model, the image features of the posts are extracted using pre-trained VGG-16 model, whereas the textual features are extracted using a three-layered convolutional neural network in parallel. The image and text features are then combined to get a hybrid feature set which is further optimized using a binary firefly optimization algorithm. Our proposed model improves the results by 11% in terms of the weighted F1-score with optimized features by binary firefly algorithm over non-optimized features.

VGG16 Transfer Learning Architecture for Salak Fruit Quality Classification

Purpose: This study aims to differentiate the quality of salak fruit with machine learning. Salak is classified into two classes, good and bad class.Design/methodology/approach: The algorithm used in this research is transfer learning with the VGG16 architecture. Data set used in this research consist of 370 images of salak, 190 from good class and 180 from bad class. The image is preprocessed by resizing and normalizing pixel value in the image. Preprocessed images is split into 80% training data and 20% testing data. Training data is trained by using pretrained VGG16 model. The parameters that are changed during the training are epoch, momentum, and learning rate. The resulting model is then used for testing. The accuracy, precision and recall is monitored to determine the best model to classify the images.Findings/result: The highest accuracy obtained from this study is 95.83%. This accuracy is obtained by using a learning rate = 0.0001 and momentum 0.9. The precision and recall for this model is 97.2 and 94.6.Originality/value/state of the art: The use of transfer learning to classify salak which never been used before.

Online Convolutional Neural Network-based anomaly detection and quality control for Fused Filament Fabrication process

ABSTRACT Additive Manufacturing (AM) technologies are experiencing rapid growth in the past decades. Critical objectives for the AM processes are how to ensure product quality and process consistency. The detection and correction of part and process anomalies show great promises and challenges. This paper presents an online laser-based process monitoring and control system to improve the geometric accuracy and in-plane surface quality for the AM process. The point cloud dataset obtained from the 3D laser scanner provides the current part height in the Z direction and in-plane surface depth information for each layer. A Convolutional Neural Network (CNN) model is designed with the pre-trained VGG16 model and validated using the monitoring data to effectively classify the in-plane anomalies. Two developed PID-based online closed-loop control systems are implemented which can significantly reduce the height deviation errors between the fabricated part measurements and design values, and correct the in-plane surface anomalies.

Flame Image Processing and Classification Using a Pre-Trained VGG16 Model in Combustion Diagnosis.

Nowadays, despite a negative impact on the natural environment, coal combustion is still a significant energy source. One way to minimize the adverse side effects is sophisticated combustion technologies, such as, e.g., staged combustion, co-combustion with biomass, and oxy-combustion. Maintaining the combustion process at its optimal state, considering the emission of harmful substances, safe operation, and costs requires immediate information about the process. Flame image is a primary source of data which proper processing make keeping the combustion at desired conditions, possible. The paper presents a method combining flame image processing with a deep convolutional neural network (DCNN) that ensures high accuracy of identifying undesired combustion states. The method is based on the adaptive selection of the gamma correction coefficient (G) in the flame segmentation process. It uses the empirically determined relationship between the G coefficient and the average intensity of the R image component. The pre-trained VGG16 model for classification was used. It provided accuracy in detecting particular combustion states on the ranging from 82 to 98%. High accuracy and fast processing time make the proposed method possible to apply in the real systems.

Effect of dual-convolutional neural network model fusion for Aluminum profile surface defects classification and recognition.

Classifying and identifying surface defects is essential during the production and use of aluminum profiles. Recently, the dual-convolutional neural network(CNN) model fusion framework has shown promising performance for defects classification and recognition. Spurred by this trend, this paper proposes an improved dual-CNN model fusion framework to classify and identify defects in aluminum profiles. Compared with traditional dual-CNN model fusion frameworks, the proposed architecture involves an improved fusion layer, fusion strategy, and classifier block. Specifically, the suggested method extracts the feature map of the aluminum profile RGB image from the pre-trained VGG16 model's pool5 layer and the feature map of the maximum pooling layer of the suggested A4 network, which is added after the Alexnet model. then, weighted bilinear interpolation unsamples the feature maps extracted from the maximum pooling layer of the A4 part. The network layer and upsampling schemes ensure equal feature map dimensions ensuring feature map merging utilizing an improved wavelet transform. Finally, global average pooling is employed in the classifier block instead of dense layers to reduce the model's parameters and avoid overfitting. The fused feature map is then input into the classifier block for classification. The experimental setup involves data augmentation and transfer learning to prevent overfitting due to the small-sized data sets exploited, while the K cross-validation method is employed to evaluate the model's performance during the training process. The experimental results demonstrate that the proposed dual-CNN model fusion framework attains a classification accuracy higher than current techniques, and specifically 4.3% higher than Alexnet, 2.5% for VGG16, 2.9% for Inception v3, 2.2% for VGG19, 3.6% for Resnet50, 3% for Resnet101, and 0.7% and 1.2% than the conventional dual-CNN fusion framework 1 and 2, respectively, proving the effectiveness of the proposed strategy.

Automatic detection of COVID-19 from chest radiographs using deep learning

IntroductionThe breakdown of a deadly infectious disease caused by a newly discovered coronavirus (named SARS n-CoV2) back in December 2019 has shown no respite to slow or stop in general. This contagious disease has spread across different lengths and breadths of the globe, taking a death toll to nearly 700 k by the start of August 2020. The number is well expected to rise even more significantly. In the absence of a thoroughly tested and approved vaccine, the onus primarily lies on obliging to standard operating procedures and timely detection and isolation of the infected persons. The detection of SARS n-CoV2 has been one of the core concerns during the fight against this pandemic. To keep up with the scale of the outbreak, testing needs to be scaled at par with it. With the conventional PCR testing, most of the countries have struggled to minimize the gap between the scale of outbreak and scale of testing. MethodOne way of expediting the scale of testing is to shift to a rigorous computational model driven by deep neural networks, as proposed here in this paper. The proposed model is a non-contact process of determining whether a subject is infected or not and is achieved by using chest radiographs; one of the most widely used imaging technique for clinical diagnosis due to fast imaging and low cost. The dataset used in this work contains 1428 chest radiographs with confirmed COVID-19 positive, common bacterial pneumonia, and healthy cases (no infection). We explored the pre-trained VGG-16 model for classification tasks in this. Transfer learning with fine-tuning was used in this study to train the network on relatively small chest radiographs effectively. ResultsInitial experiments showed that the model achieved promising results and can be significantly used to expedite COVID-19 detection. The experimentation showed an accuracy of 96% and 92.5% in two and three output class cases, respectively. ConclusionWe believe that this study could be used as an initial screening, which can help healthcare professionals to treat the COVID patients by timely detecting better and screening the presence of disease. Implication for practiceIts simplicity drives the proposed deep neural network model, the capability to work on small image dataset, the non-contact method with acceptable accuracy is a potential alternative for rapid COVID-19 testing that can be adapted by the medical fraternity considering the criticality of the time along with the magnitudes of the outbreak.