Image Classification Results Research Articles

Evolutionary Approach for AutoAugment Using the Thermodynamical Genetic Algorithm

Data augmentation is one of the most effective ways to stabilize learning by improving the generalization of machine-learning models. In recent years, automatic data augmentation methods, such as AutoAugment or Fast AutoAugment have been attracting attention; and these methods improved the results of image classification and object detection tasks. However, several problems remain. Most notably, a larger training dataset requires higher computational costs. When searching with a small dataset in an attempt to determine the data augmentation approach, the true data space and sampling data space do not fully correspond with each other, thereby causing the generalization performance to deteriorate. Moreover, in the existing automatic augmentation methods, the search phase is often dominated by an exceptional sub-policy, which results in a loss of diversity of operations. In this study, we solved these problems by introducing evolutionary computation to previous methods. As mentioned earlier, maintaining diversity is essential. Therefore, we adopted the thermodynamical genetic algorithm (TDGA), which can control the population diversity with a specific genetic operator, known as the thermodynamical selection rule. To confirm the effectiveness of the proposed method, computational experiments were conducted using two benchmark datasets, CIFAR-10 and SVHN, as examples. The experimental results show that the proposed method can obtain various useful augmentation sub-policies for the problems while reducing the computational cost.

Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks.

Audio signal classification finds various applications in detecting and monitoring health conditions in healthcare. Convolutional neural networks (CNN) have produced state-of-the-art results in image classification and are being increasingly used in other tasks, including signal classification. However, audio signal classification using CNN presents various challenges. In image classification tasks, raw images of equal dimensions can be used as a direct input to CNN. Raw time-domain signals, on the other hand, can be of varying dimensions. In addition, the temporal signal often has to be transformed to frequency-domain to reveal unique spectral characteristics, therefore requiring signal transformation. In this work, we overview and benchmark various audio signal representation techniques for classification using CNN, including approaches that deal with signals of different lengths and combine multiple representations to improve the classification accuracy. Hence, this work surfaces important empirical evidence that may guide future works deploying CNN for audio signal classification purposes.

UAV image crop classification based on deep learning with spatial and spectral features

Unmanned Aerial Vehicle image analysis technology has become an effective means to classify crops. However, the UAV image classification mostly adopts shallow learning algorithm, with few computing units. These methods have low recognition accuracy and poor generalization ability. Deep learning has powerful function expression and excellent feature learning abilities. The learned features have more essential character for data and have achieved remarkable results in image classification. Therefore, the study proposes a crop classification method based on Unmanned Aerial Vehicle image with deep learning and spatial and spectral feature fusion. The method uses deep convolutional neural network to classify Unmanned Aerial Vehicle images. Simplified AlexNet network structure, which reduces the number of network layers, was used to accelerate the convergence speed of the model while ensuring the accuracy of crop classification in practical applications. Then, the vegetation index and height features of the Unmanned Aerial Vehicle image were extracted. Feature combination and comparative analyses were carried out to find the most effective feature combination and improve the accuracy of crop classification through spatial and spectral feature fusion. In addition, a Sample Expansion Strategy was used to optimize the classification model and further improve the classification result to achieve a perfect performance in the crop classification of drone images. The experimental results showed that the deep learning method can effectively identify crop types in Unmanned Aerial Vehicle images, and the overall classification accuracy is raised from 86.07% to 92.76% when combining spatial and spectral feature fusion with Sample Expansion Strategy.

Kernel-Based MPCM Algorithm with Spatial Constraints and Local Contextual Information for Mapping Paddy Burnt Fields

In remote sensing images, isolated pixels in the form of salt-and-pepper noisy pixels deteriorates the image classification results. To handle these noisy pixels, spatial constraints along with local contextual information were added in Gaussian kernel-based Modified Possibilistic c-Means (MPCM) algorithm. The spatial constraints added in MPCM results as MPCM-S (MPCM with spatial constraints) which is used as base classifier added with Modified Possibilistic Spatial constraint Local Information c-Means (MPSLICM) and Adaptive Modified Possibilistic Spatial constraint Local Information c-Means (ADMPSLICM). Along with the ability to handle noise and nonlinearity in the data, this research work aims at using these algorithms for extraction of paddy burnt fields as a single land cover class. The cross-validation of results has been done using Normalized Burnt Ratio (NBR). Further, a quantitative assessment for the recognition of paddy stubble burnt field was done using Mean Membership Difference (MMD) method from soft classified output. From this research work, it was finally concluded that fuzzy learning algorithm gave higher accuracy and performs better when local contextual information is incorporated along with spatial constraint.

Classification of Anemia with Digital Images of Nails and Palms using the Naive Bayes Method

Purpose: Early detection of anemia based on nails and palms images by applying the Naive Bayes method, as well as to measure the level of accuracy in detecting anemia.Design/methodology/approach: Using the Naive Bayes method. System development uses the waterfall method.Findings/result: Based on the results of the tests that have been carried out, the resulting accuracy is 87.5% with varying light intensities and is 92.3% by using a light intensity of 5362 Lux.Originality/value/state of the art: The difference between this study and previous research is in the image pre-processing method and classification method. In this study, the images of the nails and palms were converted to the YCbCr color space to be segmented and color features extracted. Then the color features will be classified using the Naive Bayes classification method. The output of this system is the result of the input image classification, whether normal or anemic.

Classification of Anemia with Digital Images of Nails and Palms using the Naive Bayes Method

Purpose : Early detection of anemia based on nails and palms images by applying the Naive Bayes method, as well as to measure the level of accuracy in detecting anemia. Design/methodology/approach : Using the Naive Bayes method. System development uses the waterfall method. Findings/result : Based on the results of the tests that have been carried out, the resulting accuracy is 87.5% with varying light intensities and is 92.3% by using a light intensity of 5362 Lux. Originality/value/state of the art : The difference between this study and previous research is in the image pre-processing method and classification method. In this study, the images of the nails and palms were converted to the YCbCr color space to be segmented and color features extracted. Then the color features will be classified using the Naive Bayes classification method. The output of this system is the result of the input image classification, whether normal or anemic.

Evaluation of graphic data corruptions impact on artificial intelligence applications

The article is devoted to the problem of the reliability of applications based on artificial intelligence. The authors made an attempt to evaluate the impact of the graphic data distortion at the input of a convolutional neural network on the result of image classification. The experiment is based on the fault injection method. A series of independent tests were carried out for such distortions as Gaussian noise, salt and pepper, speckle and Poisson noise, as well as median blur, motion blur, scene brightness changing, rotation, rain, and snow. The results showed that Gaussian noise was the least critical distortion; environmental conditions (rain, snow, brightness) and image rotation up to 20 degrees are less critical than focus losing and motion blur, while the most critical distortion is speckle noise. It was verified that preprocessing the input data of the neural network improves the accuracy of image recognition.

Dropout technique for image classification based on extreme learning machine

An extreme learning machine is a feed-forward neural network is a feature learning method used in image classification efficiently because of the faster learning rate, speed, good generalization ability, ease of implementation, and efficiency in classifications. This paper presents a new model for the classification of images by using an extreme learning machine classifier which works in two stages using deep learning techniques. A new framework is built by using the dropout technique of CNN for classifying images with less training time and also no need to over train neurons. The proposed model has a high accuracy of 98% using 1000 images. The proposed paper accomplishes the best results in image classification compare with other related methods on image classification.

Efficient Pneumonia Detection for Chest Radiography Using ResNet-Based SVM

Chest radiography has a significant clinical utility in the medical imaging diagnosis, as it is one of the most basic examination tools. Pneumonia is a common infection that rapidly affects human lung areas. So, finding an advanced automated method to detect Pneumonia is assigned to be one of the most recent issues, which is still prohibitively expensive to mass adoption, especially in the developing countries. This article presents an innovative approach for distinguishing the residence of pneumonia by embedding computational techniques to chest x-rays images which eliminating the demands for single-image investigation and significantly decrease the total costs. Recent advances in deep learning achieved remarkable results in image classification on different domains; however, its application for Pneumonia diagnosis is still restricted. Hence, the main focus is to provide an investigation that will improve the research in this area, presenting a new proposal to the applications of pre-trained convolutional neural networks (CNNs) as a stage of features extraction to detect this disease. Specifically, we propose to combine deep residual neural networks (ResNets), which extract the hierarchical features from the individual x-ray images with the boosting algorithm to select the salient features, and support vector machine for classification (AdaBoost-SVM). After conducting the performance analysis on the available dataset, we have concluded that the precision of the introduced scheme in Pneumonia classification is superior to the most concurrent approaches, resulting in a great improvement in clinical outcomes.

Predicting Impact of COVID-19 on Crude Oil Price Image with Directed Acyclic Graph Deep Convolution Neural Network

Deep learning methods have achieved amazing results in sequential input, prediction and image classification. In this study, we propose image transformation of time series crude oil price by incorporating 2-D Directed Acyclic Graph to Convolutional Neural Network (DAG) based on image processing properties. Crude oil price time series is converted into 2-D images, utilizing 10 distinctive technical indicators. Geometric Brownian Motion was utilized to produces data for a 10-day time span. Thus, 10x10 sized 2-D images are constructed. Each image is then labelled as Buy or Sell depending on the returns of the time series. The results show that integrating DAG with CNN improves the prediction accuracy by 14.18%. DAG perform best with an accuracy of 99.16%, sensitivity of 100% and specificity of 99.19%. COVID-19 has negatively affected Nigeria crude oil price which indicates a downward trend of crude oil price. The study recommends poly-cultural economy of Nigeria economy for national development of the nation.

Studying the Applicability of Generative Adversarial Networks on HEp-2 Cell Image Augmentation

The Anti-Nuclear Antibodies (ANAs) testing is the primary serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted mainly by the Indirect Immunofluorescence (IIF) on Human Epithelial cell-substrate (HEp-2) protocol. However, due to its high variability, human-subjectivity, and low throughput, there is an insistent need to develop an efficient Computer-Aided Diagnosis system (CADs) to automate this protocol. Many recently proposed Convolutional Neural Networks (CNNs) demonstrated promising results in HEp-2 cell image classification, which is the main task of the HE-p2 IIF protocol. However, the lack of large labeled datasets is still the main challenge in this field. This work provides a detailed study of the applicability of using generative adversarial networks (GANs) algorithms as an augmentation method. Different types of GANs were employed to synthesize HEp-2 cell images to address the data scarcity problem. For systematic comparison, empirical quantitative metrics were implemented to evaluate different GAN models' performance of learning the real data representations. The results of this work showed that though the high visual similarity with the real images, GANs' capacity to generate diverse data is still limited. This deficiency in the generated data diversity is found to be of a crucial impact when used as a standalone method for augmentation. However, combining limited-size GANs-generated data with classic augmentation improves the classification accuracy across different variants of CNNs. Our results demonstrated a competitive performance for the overall classification accuracy and the mean class accuracy of the HEp-2 cell image classification task.

Global Consistent Graph Convolutional Network for Hyperspectral Image Classification

While semisupervised methods based on graph convolutional networks (GCNs) can achieve good results in hyperspectral image (HSI) classification, their performance is limited as they rely only on spatial-spectral similarity when constructing local adjacency graphs. Moreover, relying on local adjacency graphs can limit the ability of the methods to ensure the consistency of global feature in complex hyperspectral remote sensing environments. Using the spatial-spectral information is typically not sufficient for providing a reliable similarity measurement to construct a global graph when the spectral variability is large and the spatial distance is long in intraclass pixels. To address this issue, this article presents a novel globally consistent GCN (GCGCN) for HSI classification. According to the proposed method, a local reliable initial graph is first built from inherent spatial-spectral information by considering this graph as a variable to optimize. Then, adaptive global high-order neighbors are explored to capture the underlying rich spatial contextual information by utilizing the graph topological consistent connectivity instead of the common strategy of using only the spatial-spectral similarity measurement. Finally, the adaptive global high-order graph structure and two-layer networks are combined to achieve the global feature smoothing of the same class samples and maintain high global feature consistency. The proposed GCGCN method is evaluated on three real HSI data sets to demonstrate its superiority compared to ten different classification methods. Moreover, the proposed GCGCN method achieves state-of-the-art classification results on three data sets in terms of four classification evaluation metrics, including overall accuracy (OA), kappa coefficient (KC), average accuracy (AA), and class accuracy (CA).

An Efficient CNN Model for COVID‐19 Disease Detection Based on X‐Ray Image Classification

Artificial intelligence (AI) techniques in general and convolutional neural networks (CNNs) in particular have attained successful results in medical image analysis and classification. A deep CNN architecture has been proposed in this paper for the diagnosis of COVID‐19 based on the chest X‐ray image classification. Due to the nonavailability of sufficient‐size and good‐quality chest X‐ray image dataset, an effective and accurate CNN classification was a challenge. To deal with these complexities such as the availability of a very‐small‐sized and imbalanced dataset with image‐quality issues, the dataset has been preprocessed in different phases using different techniques to achieve an effective training dataset for the proposed CNN model to attain its best performance. The preprocessing stages of the datasets performed in this study include dataset balancing, medical experts’ image analysis, and data augmentation. The experimental results have shown the overall accuracy as high as 99.5% which demonstrates the good capability of the proposed CNN model in the current application domain. The CNN model has been tested in two scenarios. In the first scenario, the model has been tested using the 100 X‐ray images of the original processed dataset which achieved an accuracy of 100%. In the second scenario, the model has been tested using an independent dataset of COVID‐19 X‐ray images. The performance in this test scenario was as high as 99.5%. To further prove that the proposed model outperforms other models, a comparative analysis has been done with some of the machine learning algorithms. The proposed model has outperformed all the models generally and specifically when the model testing was done using an independent testing set.

Classification and comparison of malignancy detection of cervical cells based on nucleus and textural features in microscopic images of uterine cervix

Cervical cancer is one of the major causes of death among women worldwide. Pap smear is the cytology based screening test which is used to detect abnormal cervical cells including pre-cancerous lesions. Accurate classification of Pap smear images is one of the challenging tasks in medical image processing and its performance can be enhanced by extracting and selecting the well-defined features and classifiers. The irregular chromatin structure is one of the prominent diagnostic features of abnormal cells. Classification is performed based on the extracted textural features and the benchmark Herlev dataset features. Radial basis function (RBF), polynomial and sigmoid SVM kernels are used for classification and comparison is performed with the features in benchmark database. Precision, recall and accuracy were calculated for all the combinations of the features. The classifier gives promising results when benchmark features are combined with textural features and also benchmark nucleus features with textural features. An effective integration of features for cervical cell classification had given good results for fast abnormal cell detection and primary Pap smear cell image classification.

Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification

Recently, graph convolutional network (GCN) has achieved promising results in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is difficult to aggregate the new node. Besides, the existing GCN-based methods divide graph construction and graph classification into two stages ignoring the influence of constructed graph error on classification results. Moreover, the available GCN-based methods fail to understand the global and contextual information of the graph. In this article, we propose a novel multiscale graph sample and aggregate network with a context-aware learning method for HSI classification. The proposed network adopts a multiscale graph sample and aggregate network (graphSAGE) to learn the multiscale features from the local regions graph, which improves the diversity of network input information and effectively solves the impact of original input graph errors on classification. By employing a context-aware mechanism to characterize the importance among spatially neighboring regions, deep contextual and global information of the graph can be learned automatically by focusing on important spatial targets. Meanwhile, the graph structure is reconstructed automatically based on the classified objects as network training, which is able to effectively reduce the influence of the initial graph error on the classification result. Extensive experiments are conducted on three real HSI datasets, which are demonstrated to outperform the compared state-of-the-art methods.

Signal processing algorithm for neural networks with integrodifferential splines as an activation function and its particular case of image classification

Classic neural networks suppose trainable parameters to include just weights of neurons. This paper proposes parabolic integrodifferential splines (ID-splines), developed by author, as a new kind of activation function (AF) for neural networks, where ID-splines coefficients are also trainable parameters. Parameters of ID-spline AF together with weights of neurons are vary during the training in order to minimize the loss function thus reducing the training time and increasing the operation speed of the neural network. The newly developed algorithm enables software implementation of the ID-spline AF as a tool for neural networks construction, training and operation. It is proposed to use the same ID-spline AF for neurons in the same layer, but different for different layers. In this case, the parameters of the ID-spline AF for a particular layer change during the training process independently of the activation functions (AFs) of other network layers. In order to comply with the continuity condition for the derivative of the parabolic ID-spline on the interval (x x0, n) , its parameters fi (i= 0,...,n) should be calculated using the tridiagonal system of linear algebraic equations: To solve the system it is necessary to use two more equations arising from the boundary conditions for specific problems. For exam- ple the values of the grid function (if they are known) in the points (x x0, n) may be used for solving the system above: f f x0 = ( 0) , f f xn = ( n) . The parameters Iii+1 (i= 0,...,n−1 ) are used as trainable parameters of neural networks. The grid boundaries and spacing of the nodes of ID-spline AF are best chosen experimentally. The optimal selection of grid nodes allows improving the quality of results produced by the neural network. The formula for a parabolic ID-spline is such that the complexity of the calculations does not depend on whether the grid of nodes is uniform or non-uniform. An experimental comparison of the results of image classification from the popular FashionMNIST dataset by convolutional neural 0, x< 0 networks with the ID-spline AFs and the well-known ReLUx( ) =AF was carried out. The results reveal that the usage x x, ≥ 0 of the ID-spline AFs provides better accuracy of neural network operation than the ReLU AF. The training time for two convolutional layers network with two ID-spline AFs is just about 2 times longer than with two instances of ReLU AF. Doubling of the training time due to complexity of the ID-spline formula is the acceptable price for significantly better accuracy of the network. Wherein the difference of an operation speed of the networks with ID-spline and ReLU AFs will be negligible. The use of trainable ID-spline AFs makes it possible to simplify the architecture of neural networks without losing their efficiency. The modification of the well-known neural networks (ResNet etc.) by replacing traditional AFs with ID-spline AFs is a promising approach to increase the neural network operation accuracy. In a majority of cases, such a substitution does not require to train the network from scratch because it allows to use pre-trained on large datasets neuron weights supplied by standard software libraries for neural network construction thus substantially shortening training time.

Random Neighbor Pixel-Block-Based Deep Recurrent Learning for Polarimetric SAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification is an important part of SAR data interpretation and provides more intuitive and detailed SAR polarization information. To bridge the PolSAR data and applications, it is necessary to design a comprehensive PolSAR classification framework to achieve satisfactory results. The deep neural network (DNN) appears to be a solution for the classification issue, in which it outperforms the classical supervised classifiers under the condition of sufficient training data. However, the volume of training data will greatly limit the effectiveness of practical applications. In this article, we try to solve the dependence issue on training data in three different ways: recurrent learning, data augmentation, and postprocessing. First, the long short-term memory (LSTM) network is introduced to achieve pixel sequence learning by taking into account the spatial and polarimetric features. Second, the random neighbor pixel-block (RNPB) method is proposed to increase the number of training samples for sequence learning. Third, the conditional random field (CRF) model is employed to further improve the classification accuracy. In the experiments, three sets of PolSAR data are used to evaluate the small sample performance of the proposed classification method. With only 0.5% labeled pixels for training, the proposed RNPB-LSTM-CRF method can approach 99% overall classification accuracy for all the data sets. Compared with the existing methods, the proposed method can achieve state-of-the-art results for PolSAR image classification under the condition of 1% training samples.

Identifying patterns in urban housing density in developing countries using convolutional networks and satellite imagery

The use of Deep Neural Networks for remote sensing scene image analysis is growing fast. Despite this, data sets on developing countries are conspicuously absent in the public domain for benchmarking machine learning algorithms, rendering existing data sets unrepresentative. Secondly, current literature uses low-level semantic scene image class definitions, which may not have many relevant applications in certain domains. To examine these problems, we applied Convolutional Neural Networks (CNN) to high-level scene image classification for identifying patterns in urban housing density in a developing country setting. An end-to-end model training workflow is proposed for this purpose. A method for quantifying spatial extent of urban housing classes which gives insight into settlement patterns is also proposed. The method consists of computing the ratio between area covered by a given housing class and total area occupied by all classes. In the current work this method is implemented based on grid count, whereby the number of predicted grids for one housing class is divided by the total grid count for all classes. Results from the proposed method were validated against building density data computed on OpenStreetMap data. Our results for scene image classification are comparable to current state-of-the-art, despite focusing only on most difficult classes in those works. We also contribute a new satellite scene image data set that captures some general characteristics of urban housing in developing countries. The data set has similar but also some distinct attributes to existing data sets.

Classification and comparison of malignancy detection of cervical cells based on nucleus and textural features in microscopic images of uterine cervix

Cervical cancer is one of the major causes of death among women worldwide. Pap smear is the cytology based screening test which is used to detect abnormal cervical cells including pre-cancerous lesions. Accurate classification of Pap smear images is one of the challenging tasks in medical image processing and its performance can be enhanced by extracting and selecting the well-defined features and classifiers. The irregular chromatin structure is one of the prominent diagnostic features of abnormal cells. Classification is performed based on the extracted textural features and the benchmark Herlev dataset features. Radial basis function (RBF), polynomial and sigmoid SVM kernels are used for classification and comparison is performed with the features in benchmark database. Precision, recall and accuracy were calculated for all the combinations of the features. The classifier gives promising results when benchmark features are combined with textural features and also benchmark nucleus features with textural features. An effective integration of features for cervical cell classification had given good results for fast abnormal cell detection and primary Pap smear cell image classification.

A New Approach of Ensemble Learning Technique to Resolve the Uncertainties of Paddy Area through Image Classification

Remote sensing technology has rendered lots of information in agriculture. It has usually been used to monitor paddy growing ecosystems in the past few decades. However, there are uncertainties in data fusion techniques which can be resolved in image classification on paddy rice. In this study, a series of learning concepts integrated by a probability progress Fuzzy Dempster-Shafer (FDS) analysis is presented to upgrade various models and different types of image data which is the goal of this study. More specifically, the study utilized the FDS to generate a series of probability models in the classification of the system. In addition, Logistic Regression (LR), Support Vector Machine (SVM), and Neural Network (NN) approaches are employed into the developed FDS system. Furthermore, two different image types are Satellite Image and Aerial Photo used as the analysis material. The overall classification accuracy has been improved to 97.27%, and the kappa value is 0.93. The overall accuracy of the paddy field image classification for a multi-period of mid-scale satellite images is between 85% and 90%. The overall accuracy of the classification using multi-spectral numerical aerial photos can be between 91% and 95%. The FDS improves the accuracy of the above image classification results.