VGG16 Network Research Articles

A Decision Support System for Face Sketch Synthesis Using Deep Learning and Artificial Intelligence.

The recent development in the area of IoT technologies is likely to be implemented extensively in the next decade. There is a great increase in the crime rate, and the handling officers are responsible for dealing with a broad range of cyber and Internet issues during investigation. IoT technologies are helpful in the identification of suspects, and few technologies are available that use IoT and deep learning together for face sketch synthesis. Convolutional neural networks (CNNs) and other constructs of deep learning have become major tools in recent approaches. A new-found architecture of the neural network is anticipated in this work. It is called Spiral-Net, which is a modified version of U-Net fto perform face sketch synthesis (the phase is known as the compiler network C here). Spiral-Net performs in combination with a pre-trained Vgg-19 network called the feature extractor F. It first identifies the top n matches from viewed sketches to a given photo. F is again used to formulate a feature map based on the cosine distance of a candidate sketch formed by C from the top n matches. A customized CNN configuration (called the discriminator D) then computes loss functions based on differences between the candidate sketch and the feature. Values of these loss functions alternately update C and F. The ensemble of these nets is trained and tested on selected datasets, including CUFS, CUFSF, and a part of the IIT photo–sketch dataset. Results of this modified U-Net are acquired by the legacy NLDA (1998) scheme of face recognition and its newer version, OpenBR (2013), which demonstrate an improvement of 5% compared with the current state of the art in its relevant domain.

Diagnosis of Melanoma Using Deep Learning

When compared to other types of skin cancer, melanoma is the deadliest. However, those who are diagnosed early on have a better prognosis for the purpose of providing a supplementary opinion to experts; various methods of spontaneous melanoma recognition and diagnosis have been investigated by different researchers. Because of the imbalance between classes, building models from existing information has proven difficult. Machine learning algorithms paired with imbalanced basis training approaches are being evaluated for their performance on the melanoma diagnosis challenge in this study. There were 200 dermoscopic photos in which patterns of skin lesions could be extracted using the VGG16, VGG19, Inception, and ResNet convolutional neural network architectures with the ABCD rule. After employing attribute selection with GS and training data balance using Synthetic Minority Oversampling Technique and Edited Nearest Neighbor rule, the random forest classifier had a sensitivity of nearly 93% and a kappa index ( k − index ) of 78%.

AUTOMATIC DETECTION OF COVID-19 CORONAVIRUS INFECTION BASED ON THE CHEST X-RAYS ANALYSIS WITH DEEP LEARNING MODELS

Early detection of the patients with COVID-19 coronavirus infection is essential to ensure adequate treatment and reduce the burden on the healthcare system. An effective method of detecting COVID-19 is computer analysis of chest X-rays. Changes caused by COVID-19 can be detected by them even in asymptomatic patients, so deep learning models have great potential as the screening tools. The paper proposes a methodology consisting of a stage of preliminary processing of X-ray images, images augmentation and multiclass classification using deep convolutional neural networks Xception, MobileNetV2, DenseNet121, ResNet50 and VGG16, previously trained on the ImageNet dataset. The results of computer experiments showed that VGG16 model demonstrated the best performance of the patients with COVID-19 classification with accuracy of 94,12 %, sensitivity (recall) 95,76 % and AUC = 98 %.

Classification Method of Rape Root Swelling Disease Based on Convolution Neural Network

Both the seedling stage and the adult plant stage of rape can be infected with root edema, and the damaged roots swell to form tumors of different sizes and shapes. The incidence of rape root swelling at the seedling stage reached 17%, and the average incidence at the adult plant stage was 15%, resulting in a 10.2% reduction in rape production. The average plant height, number of siliques, number of kernels per horn, 1000-seed weight and yield per plant of healthy plants were significantly higher than those of diseased plants. Grading root lesions can help trace the root causes of root lesions. However, the method of grading is often performed manually by professionals at present, which has the problems of low speed and low efficiency. In order to solve this problem, a method for grading rape root swelling based on deep convolutional neural network is proposed in this paper. Firstly, a rape root swelling model based on convolutional neural network and regional candidate network was established, and then implement it on the deep learning Tensorflow framework Model, and finally compare and analyze the results. The rape root swelling model uses the VGG16 network to extract the characteristics of the rape root swelling image. The regional candidate network generates the preliminary position candidate frame of the rape root swelling, and Fast-RCNN realizes the classification and positioning of the candidate frame. The results show that this method can achieve rapid and accurate detection of healthy, first-level tumors, second-level tumors, and third-level tumors of four-level rape root swelling, with an average accuracy rate of 84.12%. The experimental results show that the accuracy rate can reach more than 90%.

Fully automatic image colorization based on semantic segmentation technology.

Aiming at these problems of image colorization algorithms based on deep learning, such as color bleeding and insufficient color, this paper converts the study of image colorization to the optimization of image semantic segmentation, and proposes a fully automatic image colorization model based on semantic segmentation technology. Firstly, we use the encoder as the local feature extraction network and use VGG-16 as the global feature extraction network. These two parts do not interfere with each other, but they share the low-level feature. Then, the first fusion module is constructed to merge local features and global features, and the fusion results are input into semantic segmentation network and color prediction network respectively. Finally, the color prediction network obtains the semantic segmentation information of the image through the second fusion module, and predicts the chrominance of the image based on it. Through several sets of experiments, it is proved that the performance of our model becomes stronger and stronger under the nourishment of the data. Even in some complex scenes, our model can predict reasonable colors and color correctly, and the output effect is very real and natural.

VGG19 Network Assisted Joint Segmentation and Classification of Lung Nodules in CT Images.

Pulmonary nodule is one of the lung diseases and its early diagnosis and treatment are essential to cure the patient. This paper introduces a deep learning framework to support the automated detection of lung nodules in computed tomography (CT) images. The proposed framework employs VGG-SegNet supported nodule mining and pre-trained DL-based classification to support automated lung nodule detection. The classification of lung CT images is implemented using the attained deep features, and then these features are serially concatenated with the handcrafted features, such as the Grey Level Co-Occurrence Matrix (GLCM), Local-Binary-Pattern (LBP) and Pyramid Histogram of Oriented Gradients (PHOG) to enhance the disease detection accuracy. The images used for experiments are collected from the LIDC-IDRI and Lung-PET-CT-Dx datasets. The experimental results attained show that the VGG19 architecture with concatenated deep and handcrafted features can achieve an accuracy of 97.83% with the SVM-RBF classifier.

Classification of analyzable metaphase images using transfer learning and fine tuning.

Chromosomes are bodies that contain human genetic information. Chromosomal disorders can cause structural and functional disorders in individuals. Detecting the metaphase stages of the cells accurately is a crucial step to detect possible defects in chromosomes. Thus, it is vital at this stage to identify the identical chromosome of each chromosome, to perform the pairing process, and to identify problems arising from this process. In this study, it was investigated whether the analyzable metaphase images can be analyzed by using the transfer learning and fine tuning approaches of deep learning models. The weights of VGG16 and InceptionV3 models trained with ImageNet data set were transferred to this problem and the classification process was carried out. True positive ratio values are 99%(± 0.9) and 99%(± 0.9) for VGG and Inception networks, respectively. The classification performances obtained depending on the changing training set ratios are presented comparatively in figures. F-measure, precision, and recall values obtained for the VGG and Inception networks were observed as 99%(± 1.0) and 99%(± 1.0), respectively. F-measure, precision, and recall values of VGG and Inceptionv3 networks are also presented with respect to the ratio of training size. The obtained results have compared with the state-of-the-art methods in the literature and supported with the tables and graphics. The training phase was also accelerated by using transfer learning and fine tuning methods. Transfer learning and fine tuning processes have almost similar performance as the models used in the literature and trained from scratch in metaphase Graphical Abstract The Flowchart of the proposed system for classifying metaphase candidates detection.

Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study

The identification of fatigue crack initiation sites (FCISs) is routinely performed in the field of engineering failure analyses; this process is not only time-consuming but also knowledge-intensive. The emergence of convolutional neural networks (CNNs) has inspired numerous innovative solutions for image analysis problems in interdisciplinary fields. As an explorative study, we trained models based on the principle of transfer learning using three state-of-the-art CNNs, namely VGG-16, ResNet-101, and feature pyramid network (FPN), as feature extractors, and a faster R-CNN as the backbone to establish models for FCISs detection. The models showed application-level detection performance, with the highest precision reaching up to 95.9% at a confidence threshold of 0.6. Among the three models, the ResNet model exhibited the highest accuracy and lowest training cost. The performance of the FPN model closely followed that of the ResNet model with an advantage in terms of the recall.

Meme Generation Using Deep Neural Network to Engage Viewers on Social Media

In today’s technological era, most new generations are using memes because the phenomenon of memes is rapidly gaining in popularity. In addition, various modifications and parodies use social and cultural phenomena to transform an original idea into another. Virus memes are sometimes called virus scripts and are the most widespread on the Internet. However, there is little scientific evidence for this assumption. This paper presents an innovative method to generate memes using machine learning algorithms that match the users’ humorous and relevant captions. The VGG16 network is used to return the embedded image. We have collected feedback from citizens of more than five countries and received 37 feedbacks to find humorous memes. The obtained results from feedback are very encouraging from the generated memes.

Deep learning-based diagnosis of temporal lobe epilepsy associated with hippocampal sclerosis: An MRI study

PurposeThe currently available indicators—sensitivity and specificity of expert radiological evaluation of MRIs—to identify mesial temporal lobe epilepsy (MTLE) associated with hippocampal sclerosis (HS) are deficient, as they cannot be easily assessed. We developed and investigated the use of a novel convolutional neural network trained on preoperative MRIs to aid diagnosis of these conditions. Subjects and methodsWe enrolled 141 individuals: 85 with clinically diagnosed mesial temporal lobe epilepsy (MTLE) and hippocampal sclerosis International League Against Epilepsy (HS ILAE) type 1 who had undergone anterior temporal lobe hippocampectomy were assigned to the MTLE-HS group, and 56 epilepsy clinic outpatients diagnosed as nonepileptic were assigned to the normal group. We fine-tuned a modified CNN (mCNN) to classify the fully connected layers of ImageNet-pretrained VGG16 network models into the MTLE-HS and control groups. MTLE-HS was diagnosed using MRI both by the fine-tuned mCNN and epilepsy specialists. Their performances were compared. ResultsThe fine-tuned mCNN achieved excellent diagnostic performance, including 91.1% [85%, 96%] mean sensitivity and 83.5% [75%, 91%] mean specificity. The area under the resulting receiver operating characteristic curve was 0.94 [0.90, 0.98] (DeLong’s method). Expert interpretation of the same image data achieved a mean sensitivity of 73.1% [65%, 82%] and specificity of 66.3% [50%, 82%]. These confidence intervals were located entirely under the receiver operating characteristic curve of the fine-tuned mCNN. ConclusionsDeep learning-based diagnosis of MTLE-HS from preoperative MR images using our fine-tuned mCNN achieved a performance superior to the visual interpretation by epilepsy specialists. Our model could serve as a useful preoperative diagnostic tool for ascertaining hippocampal atrophy in patients with MTLE.

Deep Learning-Based Diagnosis Method of Emergency Colorectal Pathology.

One of the most common malignant tumors of the digestive tract is emergency colorectal cancer. In recent years, both morbidity and mortality rates, particularly in our country, are getting higher and higher. At present, diagnosis of colorectal cancer, specifically in the emergency department of a hospital, is based on the doctor's pathological diagnosis, and it is heavily dependent on the doctor's clinical experience. The doctor's workload is heavy, and misdiagnosis events occur from time to time. Therefore, computer-aided diagnosis technology is desperately needed for colorectal pathological images to assist pathologists in reducing their workload, improve the efficiency of diagnosis, and eliminate misdiagnosis. To address these issues, a gland segmentation of emergency colorectal pathology images and diagnosis of benign and malignant pathology is presented in this paper. Initially, a multifeatured auxiliary diagnosis is designed to enable diagnosis of benign and malignant diagnosis of emergency colorectal pathology. The proposed algorithm constructs an SVM-enabled pathological diagnosis model which is based on contour, color, and texture features. Additionally, their combination is used for pathological benign and malignant pathological diagnosis of two types of data sets D1 (original pathological image dataset) and D2 (dataset that has undergone glandular segmentation) diagnosis. Experimental results show that the proposed pathological diagnosis model has higher diagnostic accuracy on D2. Among these datasets, SVM based on the multifeature fusion of contour and texture achieved the highest diagnostic accuracy rate, i.e., 83.75%, which confirms that traditional image processing methods have limitations. Diagnosing benign and malignant colorectal pathology in an emergency is more difficult and must be treated on a priority basis. Finally, an emergency colorectal pathology diagnosis method, which is based on deep convolutional neural networks such as CIFAR and VGG, is proposed. After configuring and training process of the two networks, trained CIFAR and VGG network models are applied to the diagnosis of both datasets, i.e., D1 and D2, respectively.

Sports Intelligent Assistance System Based on Deep Learning

Traditional sports aid systems analyze sports data via sensors and other types of equipment and can support athletes with retrospective analysis, but they require several sensors and have limited data. This paper examines a sports aid system that uses deep learning to recognize, review, and analyze behaviors through video acquisition and intelligent video sequence processing. This paper’s primary research is as follows: (1) With an eye on the motion assistance system’s application scenarios, the network topology and implementation details of the two-stage Faster R-CNN and the single-stage YOLOv3 target detection algorithms are investigated. Additionally, training procedures are used to enhance the algorithm’s detection performance and training speed. (2) To address the issue of target detection techniques’ low detection performance in complicated backgrounds, an improved scheme from Faster R-CNN is proposed. To begin, a new approach replaces the VGG-16 network in the previous algorithm with a ResNet-101 network. Second, an expansion plan for the dataset is provided. (3) To address the short duration of action video and the high correlation of image sequence data, we present an action recognition method based on LSTM. To begin, we will present a motion decomposition scheme and evaluation index based on the key transaction frame in order to simplify the motion analysis procedure. Second, the spatial features of the frame images are extracted using a convolutional neural network. Besides, the spatial and temporal aspects of the image sequence are fused using a two-layer bidirectional LSTM network. The algorithm suggested in this research has been validated using a golf experiment, and the results are favorable.

Identification of boiling flow pattern in narrow rectangular channel based on TFA-CNN combined method

In this paper, an indirect flow pattern recognition method based on time-frequency analysis and neural networks is proposed to investigate the flow patterns in the narrow rectangular channel under heating and non-inertial conditions. Firstly, the adaptive optimal kernel algorithm is utilized to analyze on the typical pressure signal and convert it into time-frequency spectrograms. Then based on the concept of transfer learning strategy, convolutional neural networks are applied as feature extractors to classify flow patterns by the spectrogram images. The proposed method is verified by the visualized flow boiling experiment data. The results show that the adaptive time-frequency algorithm can effectively reflect the characteristics of different flow pattern signals, and several chosen neural network models show high recognition accuracy after training. Among them, VGG-16 network with small convolution kernels and strong transferability has the highest recognition rate. In addition, the network based on data of static conditions remains identifying more than 75% spectrograms of rolling conditions, exhibiting the generalization ability of the method under different flow conditions.

COVID-19 diagnosis prediction using classical-to-quantum ensemble model with transfer learning for CT scan images

ABSTRACT At present, there are problems of low detection efficiency and accuracy in chest CT images of COVID-19 as well as limited computational power of deep learning model training. Developing a classical-to-quantum (CQ) ensemble model with transfer learning to efficiently detect patients with COVID-19 using chest CT images.: Attributes were extracted from chest CT scans using pre-trained networks ResNet50, VGG16 and AlexNet, while dressed quantum circuits were used as classifiers. The overall accuracy of the CQ method based on three aforementioned networks on the chest CT dataset is 83.2%, 86.2% and 85.0%, respectively. The proposed ensemble model has a precision of 89.0% for pneumonia samples, an overall accuracy of 88.6% and a pneumonia class recall rate of 83.0%. In addition, to further verify the robustness of the ensemble model, breast ultrasound and brain tumour images were used in it. The suggested ensemble approach is effective for classifying and detecting medical pictures with complicated features, particularly for detecting COVID-19 patients using chest CT images.

DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

Novel multi-site graph convolutional network with supervision mechanism for COVID-19 diagnosis from X-ray radiographs

The novel Coronavirus disease 2019 (COVID-2019) has become a global pandemic and affected almost all aspects of our daily life. The total number of positive COVID-2019 cases has exponentially increased in the last few months due to the easy transmissibility of the virus. It can be detected using the nucleic acid test or the antibodies blood test which are not always available and take several hours to get the results. Therefore, researchers proposed computer-aided diagnosis systems using the state-of-the-art artificial intelligence techniques to learn imaging biomarkers from chest computed tomography and X-ray radiographs to effectively diagnose COVID-19. However, previous methods either adopted transfer learning from a pre-trained model on natural images or were trained on limited datasets. Either cases may lead to accuracy deficiency or overfitting. In addition, feature space suffers from noise and outliers when collecting X-ray images from multiple datasets. In this paper, we overcome the previous limitations by firstly collecting a large-scale X-ray dataset from multiple resources. Our dataset includes 11,312 images collected from 10 different data repositories. To alleviate the effect of the noise, we suppress it in the feature space of our new dataset. Secondly, we introduce a supervision mechanism and combine it with the VGG-16 network to consider the differences between the COVID-19 and healthy cases in the feature space. Thirdly, we propose a multi-site (center) COVID-19 graph convolutional network (GCN) that exploits dataset information, the status of training samples, and initial scores to effectively classify the disease status. Extensive experiments using different convolutional neural network-based methods with and without the supervision mechanism and different classifiers are performed. Results demonstrate the effectiveness of the proposed supervision mechanism in all models and superior performance with the proposed GCN.

ANINet: a deep neural network for skull ancestry estimation

BackgroundAncestry estimation of skulls is under a wide range of applications in forensic science, anthropology, and facial reconstruction. This study aims to avoid defects in traditional skull ancestry estimation methods, such as time-consuming and labor-intensive manual calibration of feature points, and subjective results.ResultsThis paper uses the skull depth image as input, based on AlexNet, introduces the Wide module and SE-block to improve the network, designs and proposes ANINet, and realizes the ancestry classification. Such a unified model architecture of ANINet overcomes the subjectivity of manually calibrating feature points, of which the accuracy and efficiency are improved. We use depth projection to obtain the local depth image and the global depth image of the skull, take the skull depth image as the object, use global, local, and local + global methods respectively to experiment on the 95 cases of Han skull and 110 cases of Uyghur skull data sets, and perform cross-validation. The experimental results show that the accuracies of the three methods for skull ancestry estimation reached 98.21%, 98.04% and 99.03%, respectively. Compared with the classic networks AlexNet, Vgg-16, GoogLenet, ResNet-50, DenseNet-121, and SqueezeNet, the network proposed in this paper has the advantages of high accuracy and small parameters; compared with state-of-the-art methods, the method in this paper has a higher learning rate and better ability to estimate.ConclusionsIn summary, skull depth images have an excellent performance in estimation, and ANINet is an effective approach for skull ancestry estimation.

Fingerlings mass estimation: A comparison between deep and shallow learning algorithms

The paper presents some results regarding the automatic mass estimation of Pintado Real fingerlings, using machine learning techniques to support the fish production process. For this purpose, an image dataset called FISHCV1206FSEG, was created which is composed of 1206 images of fingerlings with their respective annotated masses. Through the fish contours, the area and perimeter were extracted, and submitted to the J48, SVM, and KNN classification algorithms and a linear regression algorithm. The images were also submitted to ResNet50, InceptionV3, Exception, VGG16, and VGG19 convolutional neural networks. As a result, the classification algorithm J48 reached an accuracy of 58.2% and a linear regression model capable of predicting the mass of a Pintado Real fingerling with a mean squared error of 1.5 g. The convolutional neural network ResNet50 obtained an accuracy of 67.08%. We can highlight the contributions of this work through the presentation of a methodology to classify the mass of fingerlings in a non-invasive way and by the analyses and comparing results of different machine learning algorithms for classification and regression.

DA-M2Det: An Iris Classification Network for UBM Images

Primary angle closure glaucoma (PACG) is primarily diagnosed by ophthalmologists through morphological analysis of the iris in ultrasonic biomicrocopy(UBM). In recent years, Deep convolutional neural networks (CNNs) show potential for quick category definition in eye disease. According to the characteristics of iris in UBM images, we proposed a network (DenseNet and Attention gate) DA-M2Det to automatic classification iris morphology. Firstly, in the framework of M2Det network, We used the backbone of DenseNet to replace the VGG backbone of M2Det, better extraction of basic feature layers. Secondly, three scales of attention gate (AG) was added to the Thinned U-shape Module (TUM), enable the network to pay more attention to the iris region. Finally, we use the retraining method to further improve the accuracy of iris classification. The classification results of VGG-16, M2Det, ResNet-50 and DA-M2Det networks are compared experimentally. The results show that, in three different iris shapes (including arch, flat and depression), DA-M2Det achieves an average classification accuracy of 85%, which is higher than that of the other three networks. Experimental results show that DA-M2Det can accurately classify irises into three categories, assisting ophthalmologists to quickly diagnose the cause of glaucoma and accurately perform clinical treatment thereby.

Deep Learnt Features and Machine Learning Classifier for Texture classification

Texture classification plays a vital role in the emerging research field of image classification. This paper approaches the texture classification problem using significant features extracted from pre-trained Convolutional Neural Network (CNN) like Alexnet, VGG16, Resnet18, Googlenet, MobilenetV2, and Darknet19. These features are classified by machine learning classifiers such as Support Vector Machine (SVM), Ensemble, K Nearest Neighbour (KNN), Naïve Bayes (NB), Decision Tree (DT), and Discriminant Analysis (DA). The performance of the work is evaluated with the texture databases namely KTH-TIPS, FMD, UMD-HR, and DTD. Among these CNN features derived from VGG16 classify by SVM provides better classification accuracy rather than using VGG16 with a softmax classifier.