Image Classification Approach Research Articles

ParticleAugment: Sampling-based data augmentation

We present an automated data augmentation approach for image classification. The problem is formulated as a Monte Carlo sampling problem where the goal is to approximate the optimal augmentation policies using a policy mixture distribution. We propose a particle filter scheme for the policy search where the probability of applying a set of augmentation operations forms the state of the filter. The policy performance is measured based on the loss function difference between a reference model and the actual model. This performance measure is then used to re-weight the particles and finally update the policy distribution. In our experiments, we show that our formulation for automated augmentation reaches promising results on CIFAR-10, CIFAR-100, and ImageNet datasets using the standard network architectures for this problem. By comparing with the related work, our method reaches a balance between the computational cost of policy search and the model performance. The source code of our approach is publicly available.

A deep neural network and machine learning approach for retinal fundus image classification

Diabetes is a common chronic disease and a major public health problem approaching epidemic proportions globally. People with diabetes are more likely to suffer from glaucoma than people without diabetes. Glaucoma can lead to loss of vision if not diagnosed at an early stage. This study proposes an intelligent computer-aided triage system with a deep neural network and machine learning to develop and analyze color retinal fundus images and classify glaucomatous retinal images. Deep features of retinal images from the fundus retinal image are extracted using a deep neural network, and the classification of features is performed and analyzed using different machine learning classifiers. Experimental results show that the combination of deep neural network and logistic regression-based classifier outperforms all existing glaucomatous triage systems, improving classification accuracy, sensitivity, and specificity.

(Compress and Restore) N : A Robust Defense Against Adversarial Attacks on Image Classification

Modern image classification approaches often rely on deep neural networks, which have shown pronounced weakness to adversarial examples: images corrupted with specifically designed yet imperceptible noise that causes the network to misclassify. In this article, we propose a conceptually simple yet robust solution to tackle adversarial attacks on image classification. Our defense works by first applying a JPEG compression with a random quality factor; compression artifacts are subsequently removed by means of a generative model Artifact Restoration GAN. The process can be iterated ensuring the image is not degraded and hence the classification not compromised. We train different AR-GANs for different compression factors, so that we can change its parameters dynamically at each iteration depending on the current compression, making the gradient approximation difficult. We experiment with our defense against three white-box and two black-box attacks, with a particular focus on the state-of-the-art BPDA attack. Our method does not require any adversarial training, and is independent of both the classifier and the attack. Experiments demonstrate that dynamically changing the AR-GAN parameters is of fundamental importance to obtain significant robustness.

Enhanced motor fault detection system based on a dual-signature image classification method using CNN

This paper proposes a new Motor Image Classification (MIC) approach based on a multi-signal conversion technique using Convolutional Neural Network (CNN). In this regard, two one-dimensional (1D) signals are combined and converted into a (2D) color image with motor information pixels. Initially, the vibration signal is converted into the frequency domain. Each point of this signal is firstly assigned a color according to its amplitude and then placed successively on a specific column to obtain a pixilated image. An outline is added to the image representing the internal motor temperature. Therefore, the vibratory and thermal situation of the engine is clearly represented in a Dual-Signature Image (DSI). Our system proves the efficiency of the color compared to grayscale images. It ensures fast and effective prevention, which results in a long service lifetime and maximum motor availability. The diagnostic success rate of our system is 99.93%.

Performance Evaluation of Different Decision Fusion Approaches for Image Classification

Image classification is one of the major data mining tasks in smart city applications. However, deploying classification models that have good generalization accuracy is highly crucial for reliable decision-making in such applications. One of the ways to achieve good generalization accuracy is through the use of multiple classifiers and the fusion of their decisions. This approach is known as “decision fusion”. The requirement for achieving good results with decision fusion is that there should be dissimilarity between the outputs of the classifiers. This paper proposes and evaluates two ways of attaining the aforementioned dissimilarity. One is using dissimilar classifiers with different architectures, and the other is using similar classifiers with similar architectures but trained with different batch sizes. The paper also compares a number of decision fusion strategies.

CWC-transformer: a visual transformer approach for compressed whole slide image classification

CWC-transformer: a visual transformer approach for compressed whole slide image classification

Multiclass Diagnosis of Alzheimer’s Disease Analysis Using Machine Learning and Deep Learning Techniques

Alzheimer’s disease (AD) is a popular neurological disorder affecting a critical part of the world’s population. Its early diagnosis is extremely imperative for enhancing the quality of patients’ lives. Recently, improved technologies like image processing, artificial intelligence involving machine learning, deep learning, and transfer learning have been introduced for detecting AD. This review describes the contribution of image processing, feature extraction, optimization, and classification approach in AD recognition. It deeply investigates different methods adopted for multiclass diagnosis of AD. The paper further presents a brief comparison of existing AD studies in terms of techniques adopted, performance measures, classification accuracy, publication year, and datasets. It then summarizes the important technical barriers in reviewed works. This paper allows the readers to gain profound knowledge regarding AD diagnosis for promoting extensive research in this field.

MobileNet-SVM: A Lightweight Deep Transfer Learning Model to Diagnose BCH Scans for IoMT-Based Imaging Sensors.

Many individuals worldwide pass away as a result of inadequate procedures for prompt illness identification and subsequent treatment. A valuable life can be saved or at least extended with the early identification of serious illnesses, such as various cancers and other life-threatening conditions. The development of the Internet of Medical Things (IoMT) has made it possible for healthcare technology to offer the general public efficient medical services and make a significant contribution to patients' recoveries. By using IoMT to diagnose and examine BreakHis v1 400× breast cancer histology (BCH) scans, disorders may be quickly identified and appropriate treatment can be given to a patient. Imaging equipment having the capability of auto-analyzing acquired pictures can be used to achieve this. However, the majority of deep learning (DL)-based image classification approaches are of a large number of parameters and unsuitable for application in IoMT-centered imaging sensors. The goal of this study is to create a lightweight deep transfer learning (DTL) model suited for BCH scan examination and has a good level of accuracy. In this study, a lightweight DTL-based model "MobileNet-SVM", which is the hybridization of MobileNet and Support Vector Machine (SVM), for auto-classifying BreakHis v1 400× BCH images is presented. When tested against a real dataset of BreakHis v1 400× BCH images, the suggested technique achieved a training accuracy of 100% on the training dataset. It also obtained an accuracy of 91% and an F1-score of 91.35 on the test dataset. Considering how complicated BCH scans are, the findings are encouraging. The MobileNet-SVM model is ideal for IoMT imaging equipment in addition to having a high degree of precision. According to the simulation findings, the suggested model requires a small computation speed and time.

Deep Learning based Analysis of MRI Images for Brain Tumor Diagnosis

This Identification and examination of brain tumour are critical components of any indication system, as evidenced by extensive research and methodological advancement over the years. As part of this approach, an efficient automated system must be put in place to enhance the rate of tumor identification. Today, manually examining thousands of MRI images to locate a brain tumor is arduous and imprecise. It may impair patient care. Since it incorporates several picture datasets, it might be time-consuming. Tumor cells present in the brain look a lot like healthy tissue, making it hard to distinguish between the two while doing segmentation. In this study, we present an approach for classification and prediction of MRI images of the brain using a convolutional neural network, conventional classifiers, and deep learning. Here we have proposed a new method for the automatic and exact categorization of brain tumour utilizing a two-stage feature composition of deep convolutional neural networks (CNNs). We used a deep learning approach to categorize MRI scans into several pathologies, including gliomas, meningiomas, benign lesions, and pituitary tumour, after first extracting characteristics from the scans. Additionally, the most accurate classifier is selected from a pool of five possible classifiers. The principal components analysis (PCA) is used to identify the most important characteristics from the retrieved features, which are then used to train the classifier. We develop our proposed model in Python, utilizing TensorFlow and Keras since it is an effective language for programming and performing work quickly. In our work, CNN got a 98.6% accuracy rate, which is better than what has been done so far.

A Unique Discrete Wavelet & Deterministic Walk-Based Glaucoma Classification Approach Using Image-Specific Enhanced Retinal Images

Glaucoma is a group of ocular atrophy diseases that cause progressive vision loss by affecting the optic nerve. Because of its asymptomatic nature, glaucoma has become the leading cause of human blindness worldwide. In this paper, a novel computer-aided diagnosis (CAD) approach for glaucomatous retinal image classification has been introduced. It extracts graph-based texture features from structurally improved fundus images using discrete wavelet-transformation (DWT) and deterministic tree-walk (DTW) procedures. Retinal images are considered from both public repositories and eye hospitals. Images are enhanced with image-specific luminance and gradient transitions for both contrast and texture improvement. The enhanced images are mapped into undirected graphs using DTW trajectories formed by the image’s wavelet coefficients. Graph-based features are extracted from these graphs to capture image texture patterns. Machine learning (ML) classifiers use these features to label retinal images. This approach has attained an accuracy range of 93.5% to 100%, 82.1% to 99.3%, 95.4% to 100%, 83.3% to 96.6%, 77.7% to 88.8%, and 91.4% to 100% on the ACRIMA, ORIGA, RIM-ONE, Drishti, HRF, and HOSPITAL datasets, respectively. The major strength of this approach is texture pattern identification using various topological graphs. It has achieved optimal performance with SVM and RF classifiers using biorthogonal DWT combinations on both public and patients’ fundus datasets. The classification performance of the DWT-DTW approach is on par with the contemporary state-of-the-art methods, which can be helpful for ophthalmologists in glaucoma screening.

A Robust Feature Downsampling Module for Remote-Sensing Visual Tasks

Remote sensing (RS) images present unique challenges for computer vision due to lower resolution, smaller objects, and fewer features. Mainstream backbone networks show promising results for traditional visual tasks. However, they use convolution to reduce feature map dimensionality, which can result in information loss for small objects in RS images and decreased performance. To address this problem, we propose a new and universal downsampling module named Robust Feature Downsampling (RFD). RFD fuses multiple feature maps extracted by different downsampling techniques, creating a more robust feature map with a complementary set of features. Leveraging this, we overcome the limitations of conventional convolutional downsampling, resulting in more accurate and robust analysis of RS images. We develop two versions of RFD module, Shallow RFD (SRFD) and Deep RFD (DRFD), tailored to adapt to different stages of feature capture and improve feature robustness. We replace the downsampling layers of existing mainstream backbones with RFD module and conduct comparative experiments on several public RS image datasets. The results show significant improvements compared to baseline approaches in RS image classification, object detection, and semantic segmentation. Specifically, our RFD module achieved an average performance gain of 1.5% on NWPU-RESISC45 classification dataset without utilizing any additional pretraining data, resulting in state-of-the-art performance on this dataset. Moreover, in detection and segmentation tasks on DOTA and iSAID datasets, our RFD module outperforms the baseline approaches by 2-7% when utilizing pretraining data from NWPU-RESISC45. These results highlight the value of RFD module in enhancing the performance of RS visual tasks.

Retracted: A Precise Medical Imaging Approach for Brain MRI Image Classification

Retracted: A Precise Medical Imaging Approach for Brain MRI Image Classification

СОВРЕМЕННЫЕ АРХИТЕКТУРЫ СВЕРТОЧНЫХ НЕЙРОННЫХ СЕТЕЙ, ПРИМЕНЯЕМЫЕ ДЛЯ ЗАДАЧ КЛАССИФИКАЦИИ ИЗОБРАЖЕНИЙ

Convolutional neural networks (CNNs) are one of the most common approaches for image classification. They allow you to automatically extract features from images and use them to determine the category to which each image belongs. This article will review several architectures of deep neural networks with high computing power – such as AlexNet, VGG and ResNet – and summarize the main advantages of each of these architectures.

Optimal Fuzzy Wavelet Neural Network Based Road Damage Detection

Floods are one of the most severe and most frequent natural calamities. It causes enormous economic damage and even leads to higher mortality rates. Studies on damage detection of roads using artificial intelligence (AI) methods gained more attention currently, especially in the development of smart cities. Therefore, this study designs an optimal Fuzzy Wavelet Neural Network based Road Damage Detection (OFWNN-RDD) technique for Flooding Management. The OFWNN-RDD technique aims to exploit the remote sensing images to classify different kinds of roads. For noise removal process, the OFWNN-RDD technique utilizes Gabor filtering (GF) technique. In addition, the OFWNN-RDD technique uses the DenseNet121 model for feature vector generation with modified barnacles mating optimization (MBMO) based hyperparameter optimizer. Finally, FWNN image classification approach is used for road damage detection. The simulation values exhibit the supremacy of the OFWNN-RDD technique over other models with improved road damage detection accuracy of 98.56%.

Secure Multi-Party Computation for Magnetic Resonance Imaging Classification

Accessing private data always requires a complex negotiation process. This process becomes even more challenging under privacy regulations such as the General Data Protection Regulation and the California Consumer Privacy Act. However, in most cases, the availability of greater amounts of data leads to significant technological breakthroughs. The perfect example is the ImageNet classification challenge, which leads to significant improvements in the image recognition area. The combination of these concerns raises the question of performing computations on data that cannot be seen, and a whole new research field that consolidates privacy-preserving concepts and modern data mining techniques comes into place. This is also the purpose of the work presented in this paper, the discovery of Secure Multi-Party Computation (SMPC) capabilities on protecting privacy during the machine learning process. The main attention is paid towards the combination of SMPC and image classification approach based on the convolutional neural network, especially the secure inference process on the encrypted magnetic resonance images.

Light weight convolutional neural network and low-dimensional images transformation approach for classification of thermal images

Thermal energy is emitted in the infrared range between X-ray and Gamma rays, which are invisible to the human eye. Thermal cameras can detect the temperature that arises due to the heat emitted by the objects in a non-contact way and transform it into an image. These images ensure to detection of objects regardless of ambient occlusion. Based on this problem, five different classification models were proposed within the scope of the study. New low-dimensional images were obtained by extracting the features of thermal images with HOG (Histogram Oriented of Gradients), LBP (Local Binary Pattern), SIFT (Scale Invariant Feature Transform), and GF (Gabor Filter) methods. These images are classified by a CNN (Convolutional Neural Network) model called LW-CNN (Light Weight CNN). Raw thermal images were classified with the LW-CNN model without pre-processing. In order to analyze the efficiency of the proposed models, the results were compared via the pre-trained VGG16 model. Three different datasets containing thermal images were used in classification processes. The highest classification accuracy was obtained from the LW-CNN model in the performance evaluations carried out on the three datasets. With this model, the classification accuracies obtained from the datasets are 98.58%, 95.56%, and 100%, respectively.

A Deep Learning Model Based on Concatenation Approach for Classification of MRI Images

A Deep Learning Model Based on Concatenation Approach for Classification of MRI Images

Graph Convolutional Networks based on manifold learning for semi-supervised image classification

Due to a huge volume of information in many domains, the need for classification methods is imperious. In spite of many advances, most of the approaches require a large amount of labeled data, which is often not available, due to costs and difficulties of manual labeling processes. In this scenario, unsupervised and semi-supervised approaches have been gaining increasing attention. The GCNs (Graph Convolutional Neural Networks) represent a promising solution since they encode the neighborhood information and have achieved state-of-the-art results on scenarios with limited labeled data. However, since GCNs require graph-structured data, their use for semi-supervised image classification is still scarce in the literature. In this work, we propose a novel approach, the Manifold-GCN, based on GCNs for semi-supervised image classification. The main hypothesis of this paper is that the use of manifold learning to model the graph structure can further improve the GCN classification. To the best of our knowledge, this is the first framework that allows the combination of GCNs with different types of manifold learning approaches for image classification. All manifold learning algorithms employed are completely unsupervised, which is especially useful for scenarios where the availability of labeled data is a concern. A broad experimental evaluation was conducted considering 5 GCN models, 3 manifold learning approaches, 3 image datasets, and 5 deep features. The results reveal that our approach presents better accuracy than traditional and recent state-of-the-art methods with very efficient run times for both training and testing.

A hybrid approach for medical images classification and segmentation to reduce complexity

A hybrid approach for medical images classification and segmentation to reduce complexity

Hyperspectral image classification using meta-heuristics and artificial neural network

Hyperspectral images usually comprise several continuous spectral bands that represent the category of similar objects or material within the captured scene. These high-dimensional data structures have a high level of correlation and possess unique information that can be used for precise image classification. The precise selection of useful features from these high dimensional band information is very important to reduce the challenge of hyper spectral image classification approaches. Nowadays, metaheuristic algorithms are immensely utilized as a promising tool for hyperspectral image classification. In the present research work, hyperspectral images are classified with the various combinations of meta-heuristic approaches and the neural network including the mostly used Cuckoo Search (CS) optimization algorithm to resolve the global optimization search problems considering the improvement needed in image classification. Further, the strength of CS is improved using the integration of the Genetic Algorithm (GA) fitness function within the CS. The feature selection is performed by the hybrid CS and GA algorithm and the optimized features are then fed to ANN for training and classification. The paper has shown a comparative analysis of various meta heuristics techniques with ANN on parameters like kappa coefficient, Class accuracy and overall Accuracy and the designed algorithms are tested on the Indian Pines dataset. The proposed CS and GA with ANN outperformed the two already existing works with an overall average accuracy of 97.30% and a kappa coefficient of 0.9760.