Deep Learning For Image Classification Research Articles

Research on aluminum defect classification algorithm based on deep learning with attention mechanism

Product quality is an important indicator for determining the quality of industrial products. Defects on the surface of aluminum profiles are inevitably caused in the actual production process due to the influence of various factors such as environment and equipment, and these defects seriously affect the quality of aluminum profiles. The focus and difficulty of research have shifted to how to quickly and accurately identify and classify surface defects in aluminum profiles. To address this issue, this paper proposes an aluminum defect classification algorithm that uses an attention mechanism in conjunction with the traditional Inception V4 network model for deep learning image classification, to accurately identify and classify aluminum defect areas. Experiments and comparative analysis are performed on the aluminum defect recognition dataset from the Alias Tianchi platform, and the results show that the algorithm with the addition of the attention mechanism improves accuracy by 1.24% over the original model.

Identification of dangerous driving state based on lightweight deep learning model

Dangerous driving state is a significant cause of traffic accidents and traffic safety problems., and the relevant detection means are lacking at present. In order to monitor the status of drivers in real time, timely judge the dangerous driving time and give reminders, this paper proposes a hazardous driving image classification system based on a modified ShuffleNet lightweight model to deploy it flexibly inside a vehicle or in a particular detection device, which is trained, tested and applied on a professionally collected image dataset. The experimental results demonstrate that the proposed system can effectively reduce the model complexity, increase the speed of model operations and usage without significantly affecting the classification effect through comparing with traditional deep learning models. Various visualization schemes are used to analyze and compare the image feature information extracted by the various models to investigate the feature extraction effectiveness of lightweight deep learning image classification models.

CASVM: An Efficient Deep Learning Image Classification Method Combined with SVM

Recent advances in convolutional neural networks (CNNs) for image feature extraction have achieved extraordinary performance, but back-propagation algorithms tend to fall into local minima. To alleviate this problem, this paper proposes a coordinate attention-support vector machine-convolutional neural network (CASVM). This proposed to enhance the model’s ability by introducing coordinate attention while obtaining enhanced image features. Training is carried out by back-propagating the loss function of support vector machines (SVMs) to improve the generalization capability, which can effectively avoid falling into local optima. The image datasets used in this study for benchmark experiments are Fashion-MNIST, Cifar10, Cifar100, and Animal10. Experimental results show that compared with softmax, CASVM can improve the image classification accuracy of the original model under different image resolution datasets. Under the same structure, CASVM shows better performance and robustness and has higher accuracy. Under the same network parameters, the loss function of CASVM enables the model to realize a lower loss value. Among the standard CNN models, the highest accuracy rate can reach 99%, and the optimal number of accuracy indicators is 5.5 times that of softmax, whose accuracy rate can be improved by up to 56%.

Application of Deep Convolution Neural Network for Image Classification: A Review

With the development of big data information and success in computer vision problems, more hidden layers in CNNs give it a greater and complicated structure and more powerful characteristic. Convolutional Neural Networks (CNN) provide an opportunity for automatically gaining knowledge of the domain specific features. The convolutional neural network is model and skilled by means of the deep leaning of neural networks and the set of rules has made great achievements in computer vision considering the fact that it’s a creation. This paper first explains the upward push and structure of deep learning and convolution neural network (CNN), and summarizes the structure or shape of CNN, and its different operations like convolution, feature extraction and pooling operation of convolution neural network. Development of convolution neural network model primarily based on deep learning in image classification are reviewed, an intensive literature survey of Convolution Neural Networks which is the broadly used framework of deep learning. With Alex Net or ImageNet because the base model of image classification in CNN model, we've got reviewed all the versions emerged over the years to fit various programs and a small discussion on structure and working of CNN.

A Machine Learning Applied Diagnosis Method for Subcutaneous Cyst by Ultrasonography.

For decades, ultrasound images have been widely used in the detection of various diseases due to their high security and efficiency. However, reading ultrasound images requires years of experience and training. In order to support the diagnosis of clinicians and reduce the workload of doctors, many ultrasonic computer aided diagnostic systems have been proposed. In recent years, the success of deep learning in image classification and segmentation has made more and more scholars realize the potential performance improvement brought by the application of deep learning in ultrasonic computer-aided diagnosis systems. This study is aimed at applying several machine learning algorithms and develop a machine learning method to diagnose subcutaneous cyst. Clinical features are extracted from datasets and images of ultrasonography of 132 patients from Hunan Provincial People's Hospital in China. All datasets are separated into 70% training and 30% testing. Four kinds of machine learning algorithms including decision tree (DT), support vector machine (SVM), K-nearest neighbors (KNN), and neural networks (NN) had been approached to determine the best performance. Compared with all the results from each feature, SVM achieved the best performance from 91.7% to 100%. Results show that SVM performed the highest accuracy in the diagnosis of subcutaneous cyst by ultrasonography, which provide a good reference in further application to clinical practice of ultrasonography of subcutaneous cyst.

Hierarchical fuzzy deep learning for image classification

Considerable interest has been shown over the last several decades for fuzzy logic and its application. The intelligent and deep learning systems are gaining breakthroughs in all walks of life to solve real-life problems for the future. The conventional fuzzy has the constraint to work with limited rule dimensions, whereas deep neural networks are unable to handle uncertain and imprecise data implicitly in the system. The objective of this paper is to develop a generalized algorithm for intelligent systems that can handle uncertainty and imprecise behavior especially for processing of large image datasets. In this paper, the hierarchical fuzzy approach is suggested, as it is gaining attention to tackle large real-life problems. The strategy used is to partition a large image dataset into small data samples and connect all the fuzzy subsystems in a hierarchical manner. In the literature, as far as authors know, no one has developed a hierarchical fuzzy approach to handle a large image dataset of real images. The algorithm for hierarchical fuzzy logic for a large image data using image thresholding has been discussed. To make the assessment, the real image database has been considered. The image classification has attained the potential applications to defense and security especially for target identification and classification. The accuracy and computational time comparisons of hierarchical fuzzy systems with existing methodologies such as deep neural networks have been discussed.

Framing Network Flow for Anomaly Detection Using Image Recognition and Federated Learning

The intrusion detection system (IDS) must be able to handle the increase in attack volume, increasing Internet traffic, and accelerating detection speeds. Network flow feature (NTF) records are the input of flow-based IDSs that are used to determine whether network traffic is normal or malicious in order to avoid IDS from difficult and time-consuming packet content inspection processing since only flow records are examined. To reduce computational power and training time, this paper proposes a novel pre-processing method merging a specific amount of NTF records into frames, and frame transformation into images. Federated learning (FL) enables multiple users to share the learned models while maintaining the privacy of their training data. This research suggests federated transfer learning and federated learning methods for NIDS employing deep learning for image classification and conducting tests on the BOUN DDoS dataset to address the issue of training data privacy. Our experimental results indicate that the proposed Federated transfer learning (FTL) and FL methods for training do not require data centralization and preserve participant data privacy while achieving acceptable accuracy in DDoS attack identification: FTL (92.99%) and FL (88.42%) in comparison with Traditional transfer learning (93.95%).

Evaluation of Disability Progression in Multiple Sclerosis via Magnetic-Resonance-Based Deep Learning Techniques.

Short-term disability progression was predicted from a baseline evaluation in patients with multiple sclerosis (MS) using their three-dimensional T1-weighted (3DT1) magnetic resonance images (MRI). One-hundred-and-eighty-one subjects diagnosed with MS underwent 3T-MRI and were followed up for two to six years at two sites, with disability progression defined according to the expanded-disability-status-scale (EDSS) increment at the follow-up. The patients’ 3DT1 images were bias-corrected, brain-extracted, registered onto MNI space, and divided into slices along coronal, sagittal, and axial projections. Deep learning image classification models were applied on slices and devised as ResNet50 fine-tuned adaptations at first on a large independent dataset and secondly on the study sample. The final classifiers’ performance was evaluated via the area under the curve (AUC) of the false versus true positive diagram. Each model was also tested against its null model, obtained by reshuffling patients’ labels in the training set. Informative areas were found by intersecting slices corresponding to models fulfilling the disability progression prediction criteria. At follow-up, 34% of patients had disability progression. Five coronal and five sagittal slices had one classifier surviving the AUC evaluation and null test and predicted disability progression (AUC > 0.72 and AUC > 0.81, respectively). Likewise, fifteen combinations of classifiers and axial slices predicted disability progression in patients (AUC > 0.69). Informative areas were the frontal areas, mainly within the grey matter. Briefly, 3DT1 images may give hints on disability progression in MS patients, exploiting the information hidden in the MRI of specific areas of the brain.

Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus.

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Residual one-dimensional convolutional neural network for neuromuscular disorder classification from needle electromyography signals with explainability

Background and ObjectiveNeuromuscular disorders are diseases that damage our ability to control body movements. Needle electromyography (nEMG) is often used to diagnose neuromuscular disorders, which is an electrophysiological test measuring electric signals generated from a muscle using an invasive needle. Characteristics of nEMG signals are manually analyzed by an electromyographer to diagnose the types of neuromuscular disorders, and this process is highly dependent on the subjective experience of the electromyographer. Contemporary computer-aided methods utilized deep learning image classification models to classify nEMG signals which are not optimized for classifying signals. Additionally, model explainability was not addressed which is crucial in medical applications. This study aims to improve prediction accuracy, inference time, and explain model predictions in nEMG neuromuscular disorder classification. MethodsThis study introduces the nEMGNet, a one-dimensional convolutional neural network with residual connections designed to extract features from raw signals with higher accuracy and faster speed compared to image classification models from previous works. Next, the divide-and-vote (DiVote) algorithm was designed to integrate each subject's heterogeneous nEMG signal data structures and to utilize muscle subtype information for higher accuracy. Finally, feature visualization was used to identify the causality of nEMGNet diagnosis predictions, to ensure that nEMGNet made predictions on valid features, not artifacts. ResultsThe proposed method was tested using 376 nEMG signals measured from 57 subjects between June 2015 to July 2020 in Seoul National University Hospital. The results from the three-class classification task demonstrated that nEMGNet's prediction accuracy of nEMG signal segments was 62.35%, and the subject diagnosis prediction accuracy of nEMGNet and the DiVote algorithm was 83.69 %, over 5-fold cross-validation. nEMGNet outperformed all models from previous works on nEMG diagnosis classification, and heuristic analysis of feature visualization results indicate that nEMGNet learned relevant nEMG signal characteristics. ConclusionsThis study introduced nEMGNet and DiVote algorithm which demonstrated fast and accurate performance in predicting neuromuscular disorders based on nEMG signals. The proposed method may be applied in medicine to support real-time electrophysiologic diagnosis.

CDLX: An Efficient novel approach for COVİD detection lung x-rays throw transfer learning based on State of the art deep learning image classification models

When compared to the general population, lung cancer patients have a higher incidence of COVID-19 infection, pulmonary problems, and poorer survival results. As a reference for prioritising cancer care issues during the epidemic, the world's main professional organisations issued new recommendations for the diagnosis, treatment, and follow-up of lung cancer patients. In today's world, we are fighting one of the greatest pandemics in human history, known as COVID-2019, which is caused by a coronavirus. The patient can be treated promptly if the infection is detected early (before it enters the lower respiratory tract). To observe ground-glass opacity in the chest X-ray due to fibrosis in the lungs once the virus has reached the lungs. Artificial intelligence techniques can be utilised to detect the presence and degree of illness based on the major discrepancies between X-ray images of an infected and non-infected person. For this study, I employed feature extraction from Transfer Learning, which entails importing a pre-trained CNN model, such as Distributed Deep Convolutional VGGNet or Distributed Deep Convolutional with ResNet Model, and changing the last layer to meet my needs.

Deep and Machine Learning Image Classification of Coastal Wetlands Using Unpiloted Aircraft System Multispectral Images and Lidar Datasets

The recent developments of new deep learning architectures create opportunities to accurately classify high-resolution unoccupied aerial system (UAS) images of natural coastal systems and mandate continuous evaluation of algorithm performance. We evaluated the performance of the U-Net and DeepLabv3 deep convolutional network architectures and two traditional machine learning techniques (support vector machine (SVM) and random forest (RF)) applied to seventeen coastal land cover types in west Florida using UAS multispectral aerial imagery and canopy height models (CHM). Twelve combinations of spectral bands and CHMs were used. Our results using the spectral bands showed that the U-Net (83.80–85.27% overall accuracy) and the DeepLabV3 (75.20–83.50% overall accuracy) deep learning techniques outperformed the SVM (60.50–71.10% overall accuracy) and the RF (57.40–71.0%) machine learning algorithms. The addition of the CHM to the spectral bands slightly increased the overall accuracy as a whole in the deep learning models, while the addition of a CHM notably improved the SVM and RF results. Similarly, using bands outside the three spectral bands, namely, near-infrared and red edge, increased the performance of the machine learning classifiers but had minimal impact on the deep learning classification results. The difference in the overall accuracies produced by using UAS-based lidar and SfM point clouds, as supplementary geometrical information, in the classification process was minimal across all classification techniques. Our results highlight the advantage of using deep learning networks to classify high-resolution UAS images in highly diverse coastal landscapes. We also found that low-cost, three-visible-band imagery produces results comparable to multispectral imagery that do not risk a significant reduction in classification accuracy when adopting deep learning models.

A Novel Deep Learning Model for Sea State Classification Using Visual-Range Sea Images

Wind-waves exhibit variations both in shape and steepness, and their asymmetrical nature is a well-known feature. One of the important characteristics of the sea surface is the front-back asymmetry of wind-wave crests. The wind-wave conditions on the surface of the sea constitute a sea state, which is listed as an essential climate variable by the Global Climate Observing System and is considered a critical factor for structural safety and optimal operations of offshore oil and gas platforms. Methods such as statistical representations of sensor-based wave parameters observations and numerical modeling are used to classify sea states. However, for offshore structures such as oil and gas platforms, these methods induce high capital expenditures (CAPEX) and operating expenses (OPEX), along with extensive computational power and time requirements. To address this issue, in this paper, we propose a novel, low-cost deep learning-based sea state classification model using visual-range sea images. Firstly, a novel visual-range sea state image dataset was designed and developed for this purpose. The dataset consists of 100,800 images covering four sea states. The dataset was then benchmarked on state-of-the-art deep learning image classification models. The highest classification accuracy of 81.8% was yielded by NASNet-Mobile. Secondly, a novel sea state classification model was proposed. The model took design inspiration from GoogLeNet, which was identified as the optimal reference model for sea state classification. Systematic changes in GoogLeNet’s inception block were proposed, which resulted in an 8.5% overall classification accuracy improvement in comparison with NASNet-Mobile and a 7% improvement from the reference model (i.e., GoogLeNet). Additionally, the proposed model took 26% less training time, and its per-image classification time remains competitive.

3D Inundation Mapping: A Comparison Between Deep Learning Image Classification and Geomorphic Flood Index Approaches

Inundation mapping is a critical task for damage assessment, emergency management, and prioritizing relief efforts during a flooding event. Remote sensing has been an effective tool for interpreting and analyzing water bodies and detecting floods over the past decades. In recent years, deep learning algorithms such as convolutional neural networks (CNNs) have demonstrated promising performance for remote sensing image classification for many applications, including inundation mapping. Unlike conventional algorithms, deep learning can learn features automatically from large datasets. This research aims to compare and investigate the performance of two state-of-the-art methods for 3D inundation mapping: a deep learning-based image analysis and a Geomorphic Flood Index (GFI). The first method, deep learning image analysis involves three steps: 1) image classification to delineate flood boundaries, 2) integrate the flood boundaries and topography data to create a three-dimensional (3D) water surface, and 3) compare the 3D water surface with pre-flood topography to estimate floodwater depth. The second method, i.e., GFI, involves three phases: 1) calculate a river basin morphological information, such as river height (hr) and elevation difference (H), 2) calibrate and measure GFI to delineate flood boundaries, and 3) calculate the coefficient parameter (α), and correct the value of hr to estimate inundation depth. The methods were implemented to generate 3D inundation maps over Princeville, North Carolina, United States during hurricane Matthew in 2016. The deep learning method demonstrated better performance with a root mean square error (RMSE) of 0.26 m for water depth. It also achieved about 98% in delineating the flood boundaries using UAV imagery. This approach is efficient in extracting and creating a 3D flood extent map at a different scale to support emergency response and recovery activities during a flood event.

Deep Learning Image Classification for Fashion Design

Fashion has always been an essential feature in our daily routine. It also plays a significant role in everyone’s lives. In this research, convolutional neural networks (CNN) were used to train images of different fashion styles, which were attempted to be predicted with a high success rate. Deep learning has been widely applied in a variety of fields recently. A CNN is a deep neural network that delivers the most accurate answers when tackling real-world situations. Apparel manufacturers have employed CNN to tackle various difficulties on their e-commerce sites, including clothing recognition, search, and suggestion. A set of photos from the Fashion-MNIST dataset is used to train a series of CNN-based deep learning architectures to distinguish between photographs. CNN design, batch normalization, and residual skip connections reduce the time it takes to learn. The CNN model’s findings are evaluated using the Fashion-MNIST datasets. In this paper, classification is done with a convolutional layer, filter size, and ultimately connected layers. Experiments are run with different activation functions, optimizers, learning rates, dropout rates, and batch sizes. The results showed that the choice of activation function, optimizer, and dropout rate impacts the correctness of the results.

Individual Beef Cattle Identification Using Muzzle Images and Deep Learning Techniques.

Simple SummaryThe ability to identify individual animals has gained great interest in beef feedlots to allow for animal tracking and all applications for precision management of individuals. This study assessed the feasibility and performance of a total of 59 deep learning models in identifying individual cattle with muzzle images. The best identification accuracy was 98.7%, and the fastest processing speed was 28.3 ms/image. A dataset containing 268 US feedlot cattle and 4923 muzzle images was published along with this article. This study demonstrates the great potential of using deep learning techniques to identify individual cattle using muzzle images and to support precision beef cattle management.Individual feedlot beef cattle identification represents a critical component in cattle traceability in the supply food chain. It also provides insights into tracking disease trajectories, ascertaining ownership, and managing cattle production and distribution. Animal biometric solutions, e.g., identifying cattle muzzle patterns (unique features comparable to human fingerprints), may offer noninvasive and unique methods for cattle identification and tracking, but need validation with advancement in machine learning modeling. The objectives of this research were to (1) collect and publish a high-quality dataset for beef cattle muzzle images, and (2) evaluate and benchmark the performance of recognizing individual beef cattle with a variety of deep learning models. A total of 4923 muzzle images for 268 US feedlot finishing cattle (>12 images per animal on average) were taken with a mirrorless digital camera and processed to form the dataset. A total of 59 deep learning image classification models were comparatively evaluated for identifying individual cattle. The best accuracy for identifying the 268 cattle was 98.7%, and the fastest processing speed was 28.3 ms/image. Weighted cross-entropy loss function and data augmentation can increase the identification accuracy of individual cattle with fewer muzzle images for model development. In conclusion, this study demonstrates the great potential of deep learning applications for individual cattle identification and is favorable for precision livestock management. Scholars are encouraged to utilize the published dataset to develop better models tailored for the beef cattle industry.

Using ensemble methods to improve the robustness of deep learning for image classification in marine environments

Abstract Deep learning has been shown to be effective for classification of coral in benthic imagery, and is becoming a tool for use in many monitoring programs around the world. Although deep learning accuracy for coral reef classification has been well published for studies where validation metrics are generated from data within surveys, little research has been done on the transferability and generalisability of deep learned models to data never seen by the trained model. Examples include data across multiple capture methods, camera systems, habitat types, water quality conditions and temporal studies. In this paper we investigate the use of deep ensembling to measure the reliability of predictions in new or unseen environments. In this paper we show that ensemble methods are more stable in their calibration across dataset shifts compared with other approaches. Ensembles show more robust uncertainty quantification in unseen environments compared to alternative methods, thus providing more confidence in the use of pre‐trained models in unconstrained environments. These results show that ensembles should be the de facto standard for any practitioner using deep learning for benthic image automation, and applying deep learning approaches to coral classification.

Multi-Stream Convolutional Neural Network-Based Wearable, Flexible Bionic Gesture Surface Muscle Feature Extraction and Recognition.

Surface electromyographic (sEMG) signals are weak physiological electrical signals, which are highly susceptible to coupling external noise and cause major difficulties in signal acquisition and processing. The study of using sEMG signals to analyze human motion intention mainly involves data preprocessing, feature extraction, and model classification. Feature extraction is an extremely critical part; however, this often involves many manually designed features with specialized domain knowledge, so the experimenter will spend time and effort on feature extraction. To address this problem, deep learning methods that can automatically extract features are applied to the sEMG-based gesture recognition problem, drawing on the success of deep learning for image classification. In this paper, sEMG is captured using a wearable, flexible bionic device, which is simple to operate and highly secure. A multi-stream convolutional neural network algorithm is proposed to enhance the ability of sEMG to characterize hand actions in gesture recognition. The algorithm virtually augments the signal channels by reconstructing the sample structure of the sEMG to provide richer input information for gesture recognition. The methods for noise processing, active segment detection, and feature extraction are investigated, and a basic method for gesture recognition based on the combination of multichannel sEMG signals and inertial signals is proposed. Suitable filters are designed for the common noise in the signal. An improved moving average method based on the valve domain is used to reduce the segmentation error rate caused by the short resting signal time in continuous gesture signals. In this paper, three machine learning algorithms, K-nearest neighbor, linear discriminant method, and multi-stream convolutional neural network, are used for hand action classification experiments, and the effectiveness of the multi-stream convolutional neural network algorithm is demonstrated by comparison of the results. To improve the accuracy of hand action recognition, a final 10 gesture classification accuracy of up to 93.69% was obtained. The separability analysis showed significant differences in the signals of the two cognitive-behavioral tasks when the optimal electrode combination was used. A cross-subject analysis of the test set subjects illustrated that the average correct classification rate using the pervasive electrode combination could reach 93.18%.

Comparison among Four Deep Learning Image Classification Algorithms in AI-based Diatom Test.

To select four algorithms with relatively balanced complexity and accuracy among deep learning image classification algorithms for automatic diatom recognition, and to explore the most suitable classification algorithm for diatom recognition to provide data reference for automatic diatom testing research in forensic medicine. The "diatom" and "background" small sample size data set (20 000 images) of digestive fluid smear of corpse lung tissue in water were built to train, validate and test four convolutional neural network (CNN) models, including VGG16, ResNet50, InceptionV3 and Inception-ResNet-V2. The receiver operating characteristic curve (ROC) of subjects and confusion matrixes were drawn, recall rate, precision rate, specificity, accuracy rate and F1 score were calculated, and the performance of each model was systematically evaluated. The InceptionV3 model achieved much better results than the other three models with a balanced recall rate of 89.80%, a precision rate of 92.58%. The VGG16 and Inception-ResNet-V2 had similar diatom recognition performance. Although the performance of diatom recall and precision detection could not be balanced, the recognition ability was acceptable. ResNet50 had the lowest diatom recognition performance, with a recall rate of 55.35%. In terms of feature extraction, the four models all extracted the features of diatom and background and mainly focused on diatom region as the main identification basis. Including the Inception-dependent model, which has stronger directivity and targeting in feature extraction of diatom. The InceptionV3 achieved the best performance on diatom identification and feature extraction compared to the other three models. The InceptionV3 is more suitable for daily forensic diatom examination.

Beyond the AJR: Potential of Deep Learning Image Classification for Chest Radiography.

Beyond the AJR: Potential of Deep Learning Image Classification for Chest Radiography.