VGG16 Architecture Research Articles

Accurate diagnosis of dementia and Alzheimer's with deep network approach based on multi‐channel feature extraction and selection

AbstractIn this article, we have proposed a multi‐stage in‐depth approach based on the improved VGGNet architecture for automatically and accurately diagnosing dementia and Alzheimer's disease. In this approach, first of all, the learned weights of the VGG16 architecture are frozen, and multichannel attributes are extracted from each pooling layer. Then, these attributes were given to the inputs of the attribute average pooling layers, and one‐dimensional attributes were produced using the flattened layer. Distinctive and effective attributes were selected from these deep attributes by the mRMR algorithm. Finally, the selected attributes are given to the input of the eight‐layer classification model, which includes the Fully connected, Relu, and softmax layers. A publicly available data set consisting of four classes and 6400 images was used to test the correctness of the proposed architecture. In addition, since the number of images belonging to the classes in this data set is unstable, data augmentation methods were used. As a result, a 98.6% accuracy score was produced with the developed architecture. These results show that the proposed architecture outperforms the original VGG16 and previous works.

Design of Transfer Learning based Deep CNN Paradigm for Brain Tumor Classification

Brain tumor is a fatal illness causing worldwide fatalities. The existing neuroimaging modalities to detect brain tumors are invasive and are observer-biased. Automatic CAD frameworks using sophisticated AI techniques lessen human intervention and can effectively handle large amounts of data. Automatic CAD frameworks using Machine learning techniques require the use of time-consuming and error-prone manual feature extraction procedures. Deep learning techniques involve automatic feature extraction; hence, appreciable classification results are attained quickly. However, training DL models from scratch takes a significant investment of time, money, and large datasets, which are difficult to attain in the medical domain. Therefore, the trade-off is utilizing the well exhaustively learned models like VGG16, VGG19, AlexNet, etc. to design a novel framework for the classification of brain tumors. The paper aims to develop a CNN-based deep learning framework by fine-tuning the pre-trained VGG16 architecture via transfer learning for brain tumor detection. The designed framework employing the transfer-learning technique gives better results with less data in less time. The brain tumor binary classification using brain MR images using transfer learning achieved an appreciable accuracy of 97%. The training and validation accuracy obtained was 100% and 97%, respectively, with 30 epochs. The loss for classification was as low as 0.0059% and the run time of 32ms/step time, much less than the existing models.

How to detect occluded crosswalks in overview images? Comparing three methods in a heavily occluded area

Crosswalk presence data is crucial for pedestrian safety and urban planning. However, obtaining such data at a large scale is often challenging due to the high cost associated with traditional collection methods. While automated methods based on computer vision have been explored to detect crosswalks from aerial images, a major obstacle to their application is the handling of candidate crosswalks occluded by objects or shadows in the aerial imagery. To address this challenge, this study explores different deep learning-based solutions, including the aerial-view and street-view methods, which are commonly used, and a combination of the two − dual-perspective method. Deep learning models based on Convolutional Neural Networks with VGG16 architecture were trained using 16,815 images to automatically detect crosswalks from both aerial and street view images. To compare the performance of these methods in handling occlusions, 1,378 images from a heavily occluded area were processed separately by the three methods. The results showed that the aerial-view method suffered the most when dealing with images from a heavily occluded area, resulting in the lowest accuracy, precision, recall, and F1 score among the three methods. On the other hand, the street-view method outperformed the aerial-view method significantly. The dual-perspective method demonstrated the highest accuracy and precision values, indicating its superiority in accurately predicting the location of a crosswalk. However, the street-view method exhibited the highest recall value, highlighting its superior ability to recover an occluded crosswalk among all methods.

Comparison of Activation Functions in Convolutional Neural Network for Poisson Noisy Image Classification

Deep learning, specifically the Convolutional Neural Network (CNN), has been a significant technology tool for image processing and human health. CNNs, which mimic the working principles of the human brain, can learn robust representations of images. However, CNNs are susceptible to noise interference, which can impact classification performance. Choosing the right activation function can improve CNNs performance and accuracy. This research aims to test the accuracy of CNN with ResNet50, VGG16, and GoogleNet architectures combined with several activation functions such as ReLU, Leaky ReLU, Sigmoid, and Tanh in the classification of images that experience Poisson noise. Poisson noise is applied to each test data to evaluate CNN accuracy. The data used in this study consists of three scenarios of different numbers of classes, namely 3 classes, 5 classes, and 10 classes. The results showed that combining ResNet50 with the ReLU activation function produced the best performance in class recognition in each scenario of the number of classes experiencing Poisson noise interference. The model achieved 97% accuracy for 3-class data, 95% for 5-class data, and 90% for 10-class data. These results show that using ResNet50 with the ReLU activation function can provide excellent resistance to Poisson noise in image processing. It was found that as the number of classes increases, the accuracy of image recognition tends to decrease. This shows that the more complex the image classification task is with a larger number of classes, the more difficult it is for CNNs to distinguish between different classes. Doi: 10.28991/ESJ-2024-08-02-014 Full Text: PDF

Optimization of the Convolutional Neural Network Method Using Fine-Tuning for Image Classification of Eye Disease

The eye is the most important organ of the human body which functions as the sense of sight. Most people wish they had healthy eyes so they could see clearly about life around them. However, some people experience eye health problems. There are many types of eye diseases ranging from mild to severe. With advances in technology, artificial intelligence can be used to classify eye diseases accurately, one of which is deep learning. Therefore, this study uses the Convolutional Neural Network (CNN) algorithm to classify eye diseases using the VGG16 architecture as a base model and will be combined using a fine-tuning model as an optimization to improve accuracy.

Detection and Classification of Tumors in Brain based on the Location by using MRI

Abstract: Brain tumor is a serious disease occurring in human being. Medical treatment process mainly depends on tumor types and its location. The final decision of neuro specialist and radiologist for the tumor diagnosis mainly depend on evaluation of MRI (Magnetic Resonance Imaging) images. To overcome this, Faster R-CNN deep learning algorithm was proposed for detecting the tumor and marking the area of their occurrence with Region Proposal Network (RPN). The selected MR image dataset consists of three primary brain tumors namely glioma, meningioma and pituitary. The proposed algorithm uses VGG-19 architecture as a base layer for both the region proposal network and the classifier network.

Comparison Analysis of CXR Images in Detecting Pneumonia Using VGG16 and ResNet50 Convolution Neural Network Model

Pneumonia is a lung disease that causes serious fatalities worldwide. Pneumonia can be complicated for medical professionals to identify since it shares similarities with other lung diseases like lung cancer and cardiomegaly. Hospitals face difficulty finding professional radiologists who help to detect pneumonia through radioactive processes. This research proposes VGG16 and ResNet50-based system architecture using the Convolutional Neural Network (CNN) module, which allows the detection of pneumonia. This research identifies pneumonia using chest X-ray (CXR) images through VGG16 and ResNet50 of CNN model architectures. The performance of the proposed models is compared by performance parameters such as processing time, accuracy, and loss. The Pneumonia dataset was obtained from Kaggle and divided into 70% for training, 15 % for validation, and 15% for testing. The results show that the proposed ResNet50 model architecture has a better result than the VGG16 model architecture. It can be clearly observed based on both models' loss and accuracy results. Moreover, the processing time for ResNet50 in training and predicting the CXR images is much faster than the VGG16 model's processing time. Hence, ResNet50 performs better than VGG16 based on the result of loss and accuracy and the processing time for the model to train and predict the data. In conclusion, the findings show the capability of CNN models for detecting pneumonia in CXR images, thus reducing the burden of professional radiologists.

Architecture optimization techniques for Convolutional Neural Networks: further experiments and insights

In this paper, we have researched implementing convolutional neural network (CNN) models for devices with limited resources, such as smartphones and embedded computers. To optimize the number of parameters of these models, we studied various popular methods that would allow them to operate more efficiently. Specifically, our research focused on the ResNet-101 and VGG-19 architectures, which we modified using techniques specific to model optimization. We aimed to determine which approach would work best for particular requirements for a maximum accepted accuracy drop. Our contribution lies in the comprehensive ablation study, which presents the impact of different approaches on the final results, specifically in terms of reducing model parameters, FLOPS, and the potential decline in accuracy. We explored the feasibility of implementing architecture compression methods that can influence the model’s structure. Additionally, we delved into post-training methods, such as pruning and quantization, at various model sparsity levels. This study builds upon our prior research [1] to provide a more comprehensive understanding of the subject matter at hand.

Crop Disease Identification Using Deep Learning Techniques By IJISRT

Detection and control of plant diseases is critical to maintaining global food security. Recent advances in deep learning and computer vision have revolutionized precision agriculture, especially in automatic detection of crop diseases. This research aims to further advance this new trend using deep learning techniques. It focuses specifically on the use of convolutional neural networks (CNN), specifically the VGG19 architecture, for the accurate and efficient detection of agricultural diseases. The study utilized a large database containing numerous photographs of healthy and diseased plants. Adding this information increases the power and capabilities of the model. The VGG19 architecture is based on algorithms that use transfer learning techniques to extract complex information from images.

DVFNet: A deep feature fusion-based model for the multiclassification of skin cancer utilizing dermoscopy images.

Skin cancer is a common cancer affecting millions of people annually. Skin cells inside the body that grow in unusual patterns are a sign of this invasive disease. The cells then spread to other organs and tissues through the lymph nodes and destroy them. Lifestyle changes and increased solar exposure contribute to the rise in the incidence of skin cancer. Early identification and staging are essential due to the high mortality rate associated with skin cancer. In this study, we presented a deep learning-based method named DVFNet for the detection of skin cancer from dermoscopy images. To detect skin cancer images are pre-processed using anisotropic diffusion methods to remove artifacts and noise which enhances the quality of images. A combination of the VGG19 architecture and the Histogram of Oriented Gradients (HOG) is used in this research for discriminative feature extraction. SMOTE Tomek is used to resolve the problem of imbalanced images in the multiple classes of the publicly available ISIC 2019 dataset. This study utilizes segmentation to pinpoint areas of significantly damaged skin cells. A feature vector map is created by combining the features of HOG and VGG19. Multiclassification is accomplished by CNN using feature vector maps. DVFNet achieves an accuracy of 98.32% on the ISIC 2019 dataset. Analysis of variance (ANOVA) statistical test is used to validate the model's accuracy. Healthcare experts utilize the DVFNet model to detect skin cancer at an early clinical stage.

DEEPFAKE FACE RECOGNITION THROUGH MODIFIED AND IMPORVED DEEP TRANSFER LEARNING

The manipulation of photo, audio, and video content has been a topic of interest for many years, as people uses fake faces to indulge in various immoral act like pornography, fraud, and defamation. In the early days, classification of real and fake faces was done using traditional methods such as editing frames by frame or using chroma keying, this traditional approach is time consuming and lacks enough editors that have the technical skills to do the frame-by-frame edition or use the chroma keying. With technological advancement, new techniques have been developed that allow for much more sophisticated and realistic manipulations, one such technique is deepfakes. Deepfakes are created using deep learning algorithms to swap or replace faces in videos or images. This can be done with a high degree of realism, making it difficult to distinguish between real and fake content. This research aims to develop a deep fake detection system using deep transfer learning (modified VGG19 and ResNet50 models), these two models were chosen over other CNN architectures due to their proven better performance, faster recognition time and lesser memory usage. The research modified the original VGG19 and ResNet architectures by replacing the last five layer with a customized dense layers that will help with faster and accurate recognition of faces. A balanced dataset comprising 70,000 real faces from the Flickr dataset and 70,000 fake faces generated by StyleGAN was utilized. This research employed hold-out evaluation method. VGG19 gave an accuracy, f1score of 91.59% and 91.47% respectively while RestNet50 gave an average accuracy and F1score of 96.61% and 96.59% respectively on the testing dataset. This shows that ResNet 50 gave the best performance both on the training, validation and testing dataset. The developed system was also compared with other state-of-art methods and they were all outperformed.

Optimizing Intracranial Hemorrhage Detection: A Comparative Study of VGG Deep Learning Architectures with Transfer Learning on CT Brain scans

Intracranial Hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis. This study applied Visual Geometry Group (VGG) deep learning model to binary classification of cerebral hemorrhage in Computerized Tomography (CT) brain scans, thereby improving the diagnostic process. Using a Kaggle dataset containing 6703 images, this study investigated the validity of VGG11, VGG13, VGG16, and VGG19 architectures, using transfer learning of ImageNet pre-trained weights to improve model performance. This study showed that VGG13 with transfer learning outperformed other models with 99.70% accuracy, indicating the profound impact of pre-trained weights on diagnostic accuracy. VGG models with untrained weights performed differently, with VGG11 achieving 98.61% accuracy, suggesting that less complex models were better suited to specific tasks. Comparative analysis shows that the depth of neural networks and the initialization of pre-training weights are the key factors to optimize performance. The discoveries present encouraging possibilities for integrating Artificial Intelligence (AI) into emergency medical services, with the potential to enhance the detection of cerebral hemorrhage and subsequently improve patient outcomes. While acknowledging limitations associated with dataset diversity and model generalization, the outcomes underscore the importance of tailoring models to specific task requirements. These findings also advocate for additional empirical research to fine-tune and advance the application of AI in healthcare.

Brain Tumor Detection: Transfer Learning Approach with VGG-16

Brain tumors have a profound impact on individuals worldwide, necessitating early detection to improve patient outcomes. This study explores the potential of deep learning in facilitating early tumor detection to aid medical professionals in timely intervention and personalized treatment strategies. While current tumor detection methodologies rely on traditional imaging techniques and manual analysis, they may suffer from limitations in accuracy and efficiency. To address these challenges, we propose a novel method using the VGG-16 architecture, a powerful Convolutional Neural Network (CNN) model, with pre-trained weights for feature extraction. By harnessing the capability of VGG-16, our model effectively discerns tumor patterns from brain MRI scans. The dataset utilized for training and evaluation consists of Brain MRI Images for Brain Tumor Detection from Kaggle, featuring a diverse range of annotated scans. During the evaluation, we focus on the primary performance metric of accuracy, which measures the model's ability to precisely classify tumor and non-tumor cases. Through extensive experimentation and analysis, we critically assess the model's performance and its potential clinical applicability

Comparative Study on Different CNN Architectures Developed on Microstructural Classification in Al-Si Alloys

Recent advances in artificial intelligence have opened up new avenues for microstructure characterization, notably in metallic materials. Physical and mechanical properties generally depend on the microstructure of the metallic material. On the other hand, microstructural characterization takes time and calls for specific techniques that don’t always lead to conclusive results quickly. To address this issue, this research focuses on the application of artificial intelligence approaches to microstructural categorization. We demonstrate the advantages of the AI approach using an example of Al-Si alloy, a material that is widely employed in a variety of industries. To specify a suitable convolutional neural network (CNN) approach for the microstructural classification of the Al-Si alloy, CNN models were trained and compared using DenseNet201, Inception v3, InceptionResNetV2, ResNet152V2, VGG16, and Xception architectures. Resulting from the comparison, it was determined that the developed supervised transfer learning model can execute the microstructural classification of Al-Si alloy microstructural images. This paper is an attempt to advance methods of microstructure recognition/classification/characterization by using Deep Learning approaches. The significance of the established model is demonstrated and its accordance with the literature data. Also, necessity is shown of developing material models and optimization through systematic microstructural investigation, production conditions, and material attributes.

Detection and Classification of Fabric Defects Using Deep Learning Algorithms

The textile industry primarily relies on fabric as a crucial raw material, the production of which involves multiple complex stages. Due to the multitude and complexity of these stages, fabric defects can frequently occur. With the modern fabric production process being nearly fully automated, and given the variety of potential defects, detecting errors on fabrics has become increasingly challenging. The rapid pace of production and the substantial market share of the sector mean that relying on human inspection for error detection can lead to significant time losses and can reduce the accuracy of defect detection to around 60%. Consequently, recent years have seen a shift towards the development of intelligent systems for fabric defect detection in parallel with technological advancements. With the rapid progression of artificial intelligence, the application of image processing techniques has commenced in this field. This study has developed a real-time defect detection system for fabrics using deep learning techniques. Initially, a network model was created using an open-source neural network library, CNN, achieving 89% accuracy. Subsequent implementations using the VGG16 and InceptionV3 architectures reached accuracies of 89% and 86%, respectively. To further improve the study, fabrics were classified into two categories: defective and non-defective, and the pre-trained Convolutional Neural Networks model ResNet50-v2 was employed as a feature extractor. This approach yielded an approximate accuracy of 95%.

Coffee disease detection and classification using image processing: A Literature review

Coffee, as one of the world's most consumed beverages, sustains livelihoods for millions across more than 50 nations. The vulnerability of coffee plants to diseases, particularly Coffee Leaf Rust and Coffee Berry Disease, poses a significant threat to global production and quality. Leveraging advancements in image processing and computer vision, researchers have explored diverse classification algorithms, ranging from traditional Support Vector Machines to state-of-the-art Deep Convolutional Neural Networks (DCNNs). This review literature addresses the challenges of coffee disease detection, emphasizing the need for precise and early identification. Notable studies have achieved commendable accuracies, such as SVMs reaching 96% and DCNNs demonstrating precision but with extended training times. Innovations like feature concatenation, transfer learning, and ensemble methods have emerged as strategies to overcome classification limitations. Recent breakthroughs showcase impressive results, including DenseNet models achieving a classification accuracy of 99.57% and MobileNetV2 reaching 99.93%. Additionally, Convolutional Neural Networks and VGG-19 architecture demonstrated a promising F1-Score of 90% in classifying various coffee leaf diseases. This concludes with a vision for ongoing advancements, emphasizing the fusion of image processing and machine learning technologies to safeguard the global coffee industry by enabling early and accurate disease detection.

Differentiating the Presence of Brain Stroke Types in MR Images using CNN Architecture.

Stroke is reportedly the biggest cause of death and disability in the world, according to the World Health Organisation (WHO). The severity of a stroke can be lowered by recognising the many stroke warning indicators early on. Using CNN, the primary goal of this study is to predict the likelihood that a brain stroke would develop at an early stage. The novelty of the proposed work is to acquire models that can accurately differentiate between stroke and no-stroke (normal) cases using MR Imaging sequences like DWI, SWI, GRE and T2 FLAIR aiding in timely diagnosis and treatment decisions. A dataset comprising real time MRI scans of patients with stroke and no-stroke conditions was collected and preprocessed for model training. The preprocessing involves standardizing the resolution of the images, normalizing pixel values, and augmenting the dataset to enhance model generalization. The ResNet, DenseNet, EfficientNet, and VGG16 architectures were implemented and trained on the preprocessed dataset. The training process involved optimizing model parameters using stochastic gradient descent and minimizing the loss function. The results demonstrate promising performance across all models by obtaining an accuracy of 98% for ResNet, DenseNet and EfficientNet, while 97% for VGG16 in differentiating the stroke using real time MRI data. The proposed work explored the effectiveness of CNN models, including ResNet, DenseNet, EfficientNet, and VGG16, for the differentiation of stroke and no-stroke cases. The models were trained and evaluated using a real-time dataset of brain MR Images. The obtained accuracies highlight the potential of CNN models in accurately differentiating between stroke and non-stroke cases.

Ischemic Stroke Classification Using VGG-16 Convolutional Neural Networks: A Study on Moroccan MRI Scans

This study presents a comprehensive exploration of deep learning models for precise brain ischemic stroke classification using medical data from Morocco. Following the OSEMN approach, our methodology leverages transfer learning with the VGG-16 architecture and employs data augmentation techniques to enhance model performance. Our developed model achieved a remarkable validation accuracy of 90%, surpassing alternative state-of-theart models (ResNet50: 87.0%, InceptionV3: 82.0%, VGG-19: 81.0%). Notably, all models were rigorously evaluated on the same meticulously curated dataset, ensuring fair and consistent comparisons. The investigation underscores VGG-16’s superior performance in distinguishing stroke cases, highlighting its potential as a robust tool for accurate diagnosis. Comparative analyses among popular deep learning architectures not only demonstrate our model’s efficacy but also emphasize the importance of selecting the right architecture for medical image classification tasks. These findings contribute to the growing evidence supporting advanced deep learning techniques in medical imaging. Achieving a validation accuracy of 90%, our model holds significant promise for real-world healthcare applications, showcasing the critical role of cutting-edge technologies in advancing diagnostic accuracy and the transformative potential of deep learning in the medical field.

An Ensemble of Transfer Learning based InceptionV3 and VGG16 Models for Paddy Leaf Disease Classification

Paddy is a crucial food crop providing essential nutrients and energy and serving more than half the global population. Diagnosing and preventing plant diseases at an early stage is crucial for the health and productivity of crops. Automated disease diagnosis eliminates the need for experts and delivers accurate outcomes. This research will diagnose paddy leaf diseases with Deep Learning technology. The diseases such as bacterial blight, blast, tungro, brown spot, and healthy leaf classes are diagnosed and classified in this study. The dataset contains 160 images from each class with 800 images. Our proposed model is an ensemble of transfer-learned InceptionV3 and VGG16 architectures, which utilizes the strength of individual models to improve overall performance. The use of transfer-learned ensemble deep learning architectures achieved impressive accuracy rates of 97.03%, 94.97%, and 98.87% for training, validation and testing respectively. The results indicating that model is not overfit and generalizes well to unseen data. The model's performance is evaluated with confusion matrix with the parameters like precision, recall, F1-score, and support. We also tested the model's performance against other proposed deep learning techniques with and without transfer learning techniques. Moreover, this research advances reliable automated disease detection systems, fostering sustainable agriculture and enhancing global food security.

Classification of clove types using convolution neural network algorithm with optimizing hyperparamters

This study uses clove imagery by classifying it according to ISO 2254-2004 standards: whole, headless, and mother clove. This type of clove will affect the quality and economic value when it has been dried. For this reason, it is necessary to take a first step to control cloves' quality. One way is to classify it from the start. This research will utilize the convolution neural network algorithm and compare it with model transfer learning and modified VGG16 architecture on clove images. In addition, research is also looking for the most optimal hyperparameter. The results of this study indicate that the application of convolution neural network (CNN) to clove images obtains an accuracy value of 84% using a hyperparameter of 50 epochs, a learning rate of 0.001, and a batch size of 16. Meanwhile, for the application of transfer learning VGG16, Resnet50, MobileNetV2, InceptionV3, DensetNet151, and modified VGG16 have respectively each of the highest accuracy including 95.70%, 76.15%, 96.89%, 98.07%, 98.96%, and 99.11%.