Deep Learning Based Image Classification Research Articles

Deep Learning-Based Dust Detection on Solar Panels: A Low-Cost Sustainable Solution for Increased Solar Power Generation

The world is shifting towards renewable energy sources due to the harmful effects of fossils fuel-based power generation in the form of global warming and climate change. When it comes to renewable energy sources, solar-based power generation remains on top of the list as a clean and carbon cutting alternative to the fossil fuels. Naturally, the sites chosen for installing solar parks to generate electricity are the ones that get maximum solar radiance throughout the year. Consequently, such sites offer challenges for the solar panels such as increased temperature, humidity and high dust levels that negatively affect their power generation capability. In this work, we are more concerned with the detection of dust from the images of the solar panels so that the cleaning process can be done in time to avoid power loses due to dust accumulation on the surface of solar panels. To this end, we utilize state-of-art deep learning-based image classification models and evaluate them on a publicly available dataset to identify the one that gives maximum classification accuracy for dusty solar panel detection. We utilize pre-trained models of 20 deep learning models to encode the images that are then used to train and validate four variants of a support vector machine. Among the 20 models, we get the maximum classification of 86.79% when the images are encoded with the pre-trained model of DenseNet169 and then use these encodings with a linear SVM for image classification.

Robust brain MRI image classification with SIBOW-SVM

Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertianty quantification, classification accuracy, computational efficiency, and data robustness.

Deep Learning-Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.

Artificial intelligence (AI)-based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error. This systematic review and meta-analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI-based medical image analysis studies. Diagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS-2 tool was utilized to assess quality. The meta-analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets. Of 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS-2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta-analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity. Application of AI-based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI-based models cannot replace a well-trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.

A review of black-box adversarial attacks on image classification

In recent years, deep learning-based image classification models have been extensively studied in academia and widely applied in industry. However, deep learning is inherently vulnerable to adversarial attacks, posing security threats to image classification models in security sensitive field, such as face recognition, medical image diagnosis and traffic sign recognition. Especially for black-box adversarial attacks, which can be carried out even without remote model information, the security issues facing deep learning are even more serious. Despite more and more attentions on this issue, existing reviews always analyze black-box adversarial attack only from one perspective, focus on only a certain application field. This paper systematically reviews and discusses existing progress, demonstrating black-box adversarial attacks from multiple perspectives and systematically classifying existing methods. Besides, we also sort out and categorize the application of current black-box adversarial attacks and identify several promising directions for future research.

H-QNN: A Hybrid Quantum–Classical Neural Network for Improved Binary Image Classification

Image classification is an important application for deep learning. With the advent of quantum technology, quantum neural networks (QNNs) have become the focus of research. Traditional deep learning-based image classification involves using a convolutional neural network (CNN) to extract features from the image and a multi-layer perceptron (MLP) network to create the decision boundaries. However, quantum circuits with parameters can extract rich features from images and also create complex decision boundaries. This paper proposes a hybrid QNN (H-QNN) model designed for binary image classification that capitalizes on the strengths of quantum computing and classical neural networks. Our H-QNN model uses a compact, two-qubit quantum circuit integrated with a classical convolutional architecture, making it highly efficient for computation on noisy intermediate-scale quantum (NISQ) devices that are currently leading the way in practical quantum computing applications. Our H-QNN model significantly enhances classification accuracy, achieving a 90.1% accuracy rate on binary image datasets. In addition, we have extensively evaluated baseline CNN and our proposed H-QNN models for image retrieval tasks. The obtained quantitative results exhibit the generalization of our H-QNN for downstream image retrieval tasks. Furthermore, our model addresses the issue of overfitting for small datasets, making it a valuable tool for practical applications.

Image Classification Based on Low-Level Feature Enhancement and Attention Mechanism

Deep learning-based image classification networks heavily rely on the extracted features. However, as the model becomes deeper, important features may be lost, resulting in decreased accuracy. To tackle this issue, this paper proposes an image classification method that enhances low-level features and incorporates an attention mechanism. The proposed method employs EfficientNet as the backbone network for feature extraction. Firstly, the Feature Enhancement Module quantifies and statistically processes low-level features from shallow layers, thereby enhancing the feature information. Secondly, the Convolutional Block Attention Module enhances the high-level features to improve the extraction of global features. Finally, the enhanced low-level features and global features are fused to supplement low-resolution global features with high-resolution details, further improving the model’s image classification ability. Experimental results illustrate that the proposed method achieves a Top-1 classification accuracy of 86.49% and a Top-5 classification accuracy of 96.90% on the ETH-Food101 dataset, 86.99% and 97.24% on the VireoFood-172 dataset, and 70.99% and 92.73% on the UEC-256 dataset. These results demonstrate that the proposed method outperforms existing methods in terms of classification performance.

PATH-13. LEARNED RESIZING WITH EFFICIENT TRAINING (LRET) FACILITATES IMPROVED PERFORMANCE OF LARGE-SCALE BRAIN TUMOR HISTOLOGY IMAGE CLASSIFICATION MODELS

Abstract BACKGROUND Histologic examination is vital in oncology research and diagnostics. The adoption of digital scanning of whole slide images (WSI) has created an opportunity to leverage deep learning-based image classification methods to enhance diagnosis and risk stratification. However, technical limitations prevent training and deployment of accurate comprehensive multiclass deep convolutional neural networks (DCNN) models for histopathology image classification. The input dimensions of DCNN architectures are small compared to the typical pathologist field of view, degrading performance by excluding important architectural features. Furthermore, data requirements for comprehensive models are sufficiently large to overwhelm the system memory during training. METHODS A method termed Learned Resizing with Efficient Training (LRET) was developed to address the main limitations of traditional histopathology classification model training. The LRET method couples efficient training techniques with image resizing to facilitate seamless integration of larger histology image patches into state-of-the-art classification models while preserving important structural information. The LRET method was coupled with two distinct resizing techniques to train three diverse histology image datasets using five different DCNN architectures. Performance metrics were compared on cross validation and hold out test sets. RESULTS LRET-trained models were flexible to multiple input patch dimensions and DCNN models. We demonstrated performance improvement across all datasets while significantly reducing the training time and resources over traditional methods. Using a large-scale, multiclass brain tumor classification dataset consisting of 74 distinct histopathologic classes, LRET-trained models outperformed existing methods by 15-28% in accuracy, yielding 94% accuracy for the best model. CONCLUSION The LRET method for DCNN training significantly enhances the performance of large-scale multiclass histopathology image classification. The implications of this work extend to broader applications within medical imaging and beyond, where efficient integration of high-resolution images into deep learning pipelines is paramount for driving advancements research and clinical practice.

Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology.

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

Performance comparison of deep learning-based image classification algorithms on ImageNet

Performance comparison of deep learning-based image classification algorithms on ImageNet

Artificial intelligence-driven microalgae autotrophic batch cultivation: A comparative study of machine and deep learning-based image classification models

The goal of this study is to classify microalgae of different species, using machine learning (ML) and deep learning (DL) methods. At present, we applied gray-scaling, bilateral filtering, adaptive thresholding, Sobel edge detection, and Canny edge detection, for the segmentation of microalgae. Morphological and texture descriptors, which are part of the important geometrical features, were used for feature extraction. Results indicates that the final combined features, with optimised image pre-processing techniques, produced high accuracy of 96.93 % and 97.63 % for k-nearest neighbours (k−NN) and support vector machine (SVM) classifiers, respectively. Overall, the Azure custom vision model performed the best with the highest accuracy of 97.67 % and 97.86 % at probability threshold of 50 % and 80 %, respectively. Our study aimed to bridge artificial intelligence technologies to microalgae based on understanding of shape, texture, and convolution features, which could accelerate the development of real-time monitoring, as well as rapid and precise microalgae classification.

<span>Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 using a Deep CNN and ResNet 50</span>

<span>Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 using a Deep CNN and ResNet 50</span>

Finding the input features that reduce the entropy of a neural network’s prediction

In deep learning-based image classification, the entropy of a neural network’s output is often taken as a measure of its uncertainty. We introduce an explainability method that identifies those features in the input that impact most this uncertainty. Learning the corresponding features by straightforward backpropagation typically leads to results that are hard to interpret. We propose an extension of the recently proposed oriented, modified integrated gradients (OMIG) technique as an alternative to produce perturbations of the input that have a visual quality comparable to explainability methods from the literature but marks features that have a substantially higher impact on the entropy. The potential benefits of the modified OMIG method are demonstrated by comparison with current state-of-the-art explainability methods on several popular databases. In addition to a qualitative analysis of explainability results, we propose a metric for their quantitative comparison, which evaluates the impact of identified features on the entropy of a prediction.

Optimal Deep Learning-Based Image Classification for IoT-Enabled UAVs in Remote Sensing Applications

Optimal Deep Learning-Based Image Classification for IoT-Enabled UAVs in Remote Sensing Applications

Intelligent analysis of corrosion characteristics of steel pipe piles of offshore construction wharfs based on computer vision

The lower part of offshore construction wharfs is mostly a steel structure system composed of steel pipe piles, whose corrosion level directly affects the structural safety performance of steel wharfs in service. The currently common corrosion detection methods can only sample and inspect steel pile after it has been dismantled, making it impractical for in-service monitoring during the operational period of the steel pile. In this paper, a deep learning-based image classification model is first established to recognize the type of corroded area on steel pipe piles. The model achieves a recognition accuracy of 99.14 % in automatically identifying different types of corroded areas, including full immersion zone, tidal range zone, and splash zone. Subsequently, digital image processing technology is utilized to automatically calculate the corroded area of steel pipe piles. The method proposed in this paper can obtain the key information, such as type of corrosion area and area of the steel pipe pile corrosion area, without damaging their structural performance during the service. With this data, the mechanical performance of steel pipe piles can be analyzed, and the structural safety of the in-service steel pipe piles can be determined, thereby ensuring the safety of the construction wharf.

Deep learning-based image classification of MRI brain image

This article reviews the latest research on MRI brain image classification techniques based on deep learning. Firstly, MRI brain image classification and traditional machine learning methods applied to MRI image classification were briefly introduced. Then, a review was conducted on existing MRI brain image classification methods based on deep learning. The article reviews past and recent related research and provides a detailed introduction to the application of deep learning methods in MRI brain image classification. This includes some traditional machine learning methods and research achievements in deep neural networks (DNN), convolutional neural networks (CNN), and transfer learning. The most commonly used deep learning architecture for image classification is CNN. Research has shown that deep learning methods have high accuracy and performance in MRI brain image classification and can automatically extract image features for effective classification. Therefore, deep learning methods provide doctors with more comprehensive information, help them make more accurate diagnoses and formulate treatment plans, and have broad prospects for application in MRI brain image classification. In the future, the further development of deep learning technology will achieve better auxiliary effects on diagnosis, treatment, and scientific research related to the brain.

Using green background for dermatological images to improve deep learning-based image classification.

Using green background for dermatological images to improve deep learning-based image classification.

Deep learning-based image classification of turtles imported into Korea

Although turtles play a key role in maintaining healthy and balanced environments, these are endangered due to global trade to meet the high demand for food, medicine, and pets in Asia. In addition, imported non-native turtles have been controlled as alien invasive species in various countries, including Korea. Therefore, a rapid and accurate classification of imported turtles is needed to conserve and detect those in native ecosystems. In this study, eight Single Shot MultiBox Detector (SSD) models using different backbone networks were used to classify 36 imported turtles in Korea. The images of these species were collected from Google and were identified using morphological features. Then, these were divided into 70% for training, 15% for validation, and 15% for test sets. In addition, data augmentation was applied to the training set to prevent overfitting. Among the eight models, the Resnet18 model showed the highest mean Average Precision (mAP) at 88.1% and the fastest inference time at 0.024 s. The average correct classification rate of 36 turtles in this model was 82.8%. The results of this study could help in management of the turtle trade, specifically in improving detection of alien invasive species in the wild.

Indoor/Outdoor Deep Learning Based Image Classification for Object Recognition Applications

With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor sets, resulting in four trained models. The test sets are used to evaluate the trained models using many evaluation metrics (accuracy, TPR, FNR, PPR, FDR). Results of Google Net model indicate the high performance of the designed models with 99.34% and 99.76% accuracies for indoor and outdoor datasets, respectively. For Mobile Net models, the result accuracies are 99.27% and 99.68% for indoor and outdoor sets, respectively. The proposed methodology is compared with similar ones in the field of object recognition and image classification, and the comparative study proves the transcendence of the propsed system.

Benign and Malignant Oral Lesion Image Classification Using Fine-Tuned Transfer Learning Techniques.

Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral lesions is imperative for effective intervention. Fortunately, deep learning algorithms have shown great potential for automated lesion detection. The primary aim of this study was to employ deep learning-based image classification algorithms to identify oral lesions. We used three deep learning models, namely VGG19, DeIT, and MobileNet, to assess the efficacy of various categorization methods. To evaluate the accuracy and reliability of the models, we employed a dataset consisting of oral pictures encompassing two distinct categories: benign and malignant lesions. The experimental findings indicate that VGG19 and MobileNet attained an almost perfect accuracy rate of 100%, while DeIT achieved a slightly lower accuracy rate of 98.73%. The results of this study indicate that deep learning algorithms for picture classification demonstrate a high level of effectiveness in detecting oral lesions by achieving 100% for VGG19 and MobileNet and 98.73% for DeIT. Specifically, the VGG19 and MobileNet models exhibit notable suitability for this particular task.

MRI Kidney Tumor Image Classification with SMOTE Preprocessing and SIFT-tSNE Features using CNN

Kidney tumor detection is a challenging task due to the complexity of tumor characteristics and variability in imaging modalities. In this paper, we propose a deep learning-based approach for detecting kidney tumors with 98.5% accuracy. Our method addresses the issue of an imbalanced dataset by applying the Synthetic Minority Over-sampling Technique (SMOTE) to balance the distribution of images. SMOTE generates synthetic samples of the minority class to increase the number of samples, thus providing a balanced dataset. We utilize a convolutional neural network (CNN) architecture that is trained on this balanced dataset of kidney tumor images. The CNN can learn and extract relevant features from the images, resulting in precise tumor classification. We evaluated our approach on a separate dataset and compared it with state-of-the-art methods. The results demonstrate that our method not only outperforms other methods but also shows robustness in detecting kidney tumors with a high degree of accuracy. By enabling early detection and diagnosis of kidney tumors, our proposed method can potentially improve patient outcomes. Additionally, addressing the imbalance in the dataset using SMOTE demonstrates the usefulness of this technique in improving the performance of deep learning-based image classification systems.