Training Image Samples Research Articles

Multitarget Intelligent Recognition of Petrographic Thin Section Images Based on Faster RCNN

The optical features of mineral composition and texture in petrographic thin sections are an important basis for rock identification and rock evolution analysis. However, the efficiency and accuracy of human visual interpretation of petrographic thin section images have depended on the experience of experts for a long time. The application of image-based computer vision and deep-learning algorithms to the intelligent analysis of the optical properties of mineral composition and texture in petrographic thin section images (in plane polarizing light) has the potential to significantly improve the efficiency and accuracy of rock identification and classification. This study completed the transition from simple petrographic thin image classification to multitarget detection, to address more complex research tasks and more refined research scales that contain more abundant information, such as spatial, quantitative and category target information. Oolitic texture is an important paleoenvironmental indicator that widely exists in sedimentary records and is related to shallow water hydraulic conditions. We used transfer learning and image data augmentation in this paper to identify the oolitic texture of petrographic thin section images based on the faster region-based convolutional neural network (Faster RCNN) method. In this study, we evaluated the performance of Faster RCNN, a two-stage object detection algorithm, using VGG16 and ResNet50 as backbones for image feature extraction. Our findings indicate that ResNet50 outperformed VGG16 in this regard. Specifically, the Faster RCNN model with ResNet50 as the backbone achieved an average precision (AP) of 92.25% for the ooids test set, demonstrating the accuracy and reliability of this approach for detecting ooids. The experimental results also showed that the uneven distribution of training sample images and the complexity of images both significantly affect detection performance; however, the uneven distribution of training sample images has a greater impact. Our work is preliminary for intelligent recognition of multiple mineral texture targets in petrographic thin section images. We hope that it will inspire further research in this field.

Improving remote sensing scene classification using quality-based data augmentation

ABSTRACT This study presents an improved data augmentation technique for the classification of remote sensing (RS) scenes. The method is called Quality-based Sample Selection (QSS) data augmentation technique. It is based on generating a large number of samples using geometric transformations and then selecting the best ones based on a quality criterion. Sample images are generated online, i.e. during training of the convolutional neural network (CNN) model. For each training sample image, a few images are generated randomly using a set of geometric transformations. Then, the generated images are passed to the CNN model being trained, and the predicted probabilities are used to evaluate the quality of the images. The motivation behind this research is that we aim to augment the training set with new images that will benefit the learning of the CNN model. Therefore, an objective method to evaluate the quality of the new images is the CNN model itself. The image with the best criteria score is used to augment the training set. Several quality criteria based on the prediction probabilities of the CNN model are considered including entropy, breaking-ties and our own proposed criteria called True Label Probability (TLP). QSS is tested on five common RS scene classification datasets: UCMerced, Optimal31, RSSCN7, AID and NWPU-RS45. It has outperformed all previous methods except for one case involving NWPU-RS45 dataset. For the 10%–90% train–test split, QSS achieved 94.51, 81.72, 89.89, 94.09 and 93.98, respectively, for the mentioned datasets. While for the 20%–80% train–test split, it achieved 97.09, 88.37, 94.01, 95.71 and 94.71, respectively, for the listed datasets. Thus, this work presents a novel data augmentation method that uses data with higher quality instead of randomly selected. The paper proves experimentally that the proposed method improves the classification accuracy of RS scene classification.

Picasso: An Open-Source Machine Learning Schema for Annotating Images in Hematology

Background: Prediction models to support clinical decision-making are an integral part of medicine. Image recognition and diagnosis are essential in multiple diseases, especially malignant hematologic diseases, where histopathological images are reviewed manually, and an opportunity to automate image analysis with diagnosis-supporting tools exists. Machine learning (ML) is a process where an algorithm creates a predictive model by learning from training data and uncovering relationships between input variables (X) and output variables (Y). For this, a training dataset with labeled examples is necessary. After the learning has occurred, a predictive model is generated that can now be used to make predictions on new input that the model has never seen before. To train a machine learning model appropriately, all input should be annotated in a standard manner, and this process is very time-consuming. One way to make it simpler is by using a schema. A schema is a collected set of rules that must be followed each time in describing the relevant features of an image. For every training image in a dataset, the relevant components are labeled manually to fit the schema and reviewed by trained human examiners, making the process tedious, time-consuming, and difficult to standardize. We created a programmatic approach to annotation where a machine learning algorithm can detect significant features in AML images, annotate the images with features that fit a schema, and feed them forward into training data. Moreover, we have created this on an open-source platform that can be widely used in a resource-limited setting across the globe. Methods: A supervised machine learning approach with a convolutional neural network (CNN) was used for image processing based on a dataset that contained 270 pathological images (confirmed AML) and 30 non-pathological images (no AML) from the public Munich AML Morphology Dataset. The pathological images were from peripheral blood smears of patients diagnosed with AML at Munich University Hospital between 2014 and 2017. The non-pathological controls were taken from patients without hematological malignancy. Initially, for training, all annotation features from the Munich AML dataset are included for both pathological and non-pathological images. The neural network was written and trained on open-source software, TensorFlow using the open-source Keras library with parallel threading and on a multicore GPU machine. The resulting predictive model answers two questions: Does a given image have cells that resemble a blast character, or if the image has cells that belong to non-pathological blood smears. Results: The neural network trained on 300 total images, and for external validation, we used another subset of 100 unlabeled images from the Munich AML Morphology Dataset. Our model could predict blast-like features accurately in 89% of the new images, 6% of new images were unclassifiable, the false positive rate was 3%, and the false negative rate was 2%. After initial prediction, the neural network could accurately annotate unlabeled images 86% of the time in pathological samples and 96% in non-pathological samples. Our training model achieved an AUC of 0.82. Conclusion: A CNN trained on a modest dataset with supervised learning, enhanced with ensemble learning and K-fold cross-validation, can be used to recognize features such as blast cells from histopathological images and label images with a high degree of accuracy. In a data-driven machine learning algorithm such as a neural network, classification performance significantly increases with more available training sample images. Therefore, a more extensive training dataset with more robust hardware is necessary to generate a more sophisticated predictive model. Using CNN-enhancing methodologies can allow for model training in a resource-limiting setting. Future work will focus on using a more extensive pre-trained database to evaluate the performance of our network in a real-world setting. The annotation framework can be expanded to include disease-associated features for use in other domains, such as hematological education, patient resources, and patient education. This open-source platform can support several niches in the future that are currently only served by expensive commercial applications. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Prediction of Elephant Movement Using Intellectual Virtual Fencing Model

The capability to navigate and orientate is crucially a significant factor to determine the survival of all migratory animals like elephants. The sustainability of animals is constrained with a limited amount of techniques available for analysis of complex animals’ behavioral responses. Various approaches are used to track animals’ movement like elephants crossing the railway track, roads have to be varied based on the degree of accuracy that is needed essentially. However, the existing approaches fail to trigger an alert in some cases. To overcome these limitations, a novel Intellectual Inertial Measurement Unit (IIMU) is proposed where the data are acquired from the aerial elephant dataset with a set of training and testing image samples. Data collected with these dataset are analyzed for triggering Virtual Fencing (VF) and to alert animals to avoid danger. This work attempts to validate that this IIMU installed with animals’ bodies can be used to evaluate patterns related to the animal’s movement. The collected data are provided for filtering using Levenberg Marquardt Algorithm to reduce the noise over the data and to enhance the prediction accuracy. The pattern set undergoes training with Artificial Neural Network (ANN) and optimized with Elephant Optimization to evaluate the prediction accuracy. Based on the evaluation, the model shows better prediction accuracy in case of emergency and alert is triggered to save the life of elephants. Here, some performance metrics like accuracy, precision, F-measure, recall, ROC are evaluated to show the significance of EPO-ANN model. The model outperforms the existing standard SVM model and gives higher prediction accuracy.

Image denoising using block matching and convolutional neural network

Image noise removal (denoising) is a significant preprocessing step in image processing research domain. In past decades, various noise removal algorithms have been developed, and they are categorized into conventional and deep learning denoising methods. Most recently, deep learning-based denoising methods outperform the conventional methods. However, deep learning methods have the limitations of requiring large training sample images, difficult to train the deep convolution neural network (DeCNN), and the majority of the convolutional neural network suffers from the performance saturation. Hence, using combination of block matching (BM) and dilated convolutional neural network (DCNN), a unique method for reducing noise in still images is proposed. In this approach, initially, existing algorithm used to preprocess the image. Then, BM technique uses a sliding window size of a four-by-four block and moves it across the image to select for blocks that are similar in the image. The matching blocks are highly correlated with one another. The matching blocks are then fed to the deep DCNN to remove noise and obtain a better noiseless image. Finally, the noiseless image performances are evaluated using standard metrics. From the experimental results, it is observed that the proposed BM and deep DCNN yielded substantially better results than existing state-of-the-art methods to remove the image’s noise.

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

The majority of digital images are stored in compressed form. Generally, image classification using convolution neural network (CNN) is done in uncompressed form rather than compressed one. Training the CNN in the compressed domain eliminates the requirement for decompression process and results in improved efficiency, minimal storage, and lesser cost. Compressive sensing (CS) is one of the effective and efficient method for signal acquisition and recovery and CNN training on CS measurements makes the entire process compact. The most popular sensing phenomenon used in CS is based on image acquisition using single pixel camera (SPC) which has complex design implementation and usually a matrix simulation is used to represent the SPC process in numerical demonstration. The CS measurements using this phenomenon are visually different from the image and to add this in the training set of the compressed learning framework, there is a need for an inverse SPC process that is to be applied all through the training and testing dataset image samples. In this paper we proposed a simple sensing phenomenon which can be implemented using the image output of a standard digital camera by retaining few pixels and forcing the rest of the pixels to zero and this reduced set of pixels is assumed as CS measurements. This process is modeled by a binary mask application on the image and the resultant image still subjectively legible for human vision and can be used directly in the training dataset. This sensing mask has very few active pixels at arbitrary locations and there is a lot of scope to heuristically learn the sensing mask suitable for the dataset. Only very few attempts had been made to learn the sensing matrix and the sole effect of this learning process on the improvement of CNN model accuracy is not reported. We proposed to have an ablation approach to study how this sensing matrix learning improves the accuracy of the basic CNN architecture. We applied CS for two class image dataset by applying a Primitive Walsh Hadamard (PWH) binary mask function and performed the classification experiment using a basic CNN. By retaining arbitrary amount of pixel in the training and testing dataset we applied CNN on the compressed measurements to perform image classification and studied and reported the model performance in terms of training and validation accuracies by varying the amount of pixels retained. A novel Genetic Algorithm-based compressive learning (GACL) method is proposed to learn the PWH mask to optimize the model training accuracy by using two different crossover techniques. In the experiment conducted for the case of compression ratio (CR) 90% by retaining only 10% of the pixels in every images both in training and testing dataset that represent two classes, the training accuracy is improved from 67% to 85% by using diagonal crossover in offspring creation of GACL. The robustness of the method is examined by applying GACL for user defined multiclass dataset and achieved better CNN model accuracies. This work will bring out the strength of sensing matrix learning which can be integrated with advanced training models to minimize the amount of information that is to be sent to central servers and will be suitable for a typical IoT frame work.

Intelligent tuberculosis activity assessment system based on an ensemble of neural networks

This article proposes a novel approach to assess the degree of activity of pulmonary tuberculosis by active tuberculoma foci. It includes the development of a new method for processing lung CT images using an ensemble of deep convolutional neural networks using such special algorithms: an optimized algorithm for preliminary segmentation and selection of informative scans, a new algorithm for refining segmented masks to improve the final accuracy, an efficient fuzzy inference system for more weighted activity assessment. The approach also includes the use of medical classification of disease activity based on densitometric measures of tuberculomas. The selection and markup of the training sample images were performed manually by qualified pulmonologists from a base of approximately 9,000 CT lung scans of patients who had been enrolled in the dispensary for 15 years.The first basic step of the proposed approach is the developed algorithm for preprocessing CT lung scans. It consists in segmentation of intrapulmonary regions, which contain vessels, bronchi, lung walls to detect complex cases of ingrown tuberculomas.To minimize computational cost, the proposed approach includes a new method for selecting informative lung scans, i.e., those that potentially contain tuberculomas.The main processing step is binary segmentation of tuberculomas, which is proposed to be performed optimally by a certain ensemble of neural networks. Optimization of the ensemble size and its composition is achieved by using an algorithm for calculating individual contributions. A modification of this algorithm using new effective heuristic metrics has been proposed which improves the performance of the algorithm for this problem.A special algorithm was developed for post-processing of tuberculoma masks obtained during the segmentation step. The goal of this step is to refine the calculated mask for the physical placement of the tuberculoma. The algorithm consists in cleaning the mask from noisy formations on the scan, as well as expanding the mask area to maximize the capture of the tuberculoma location area.A simplified fuzzy inference system was developed to provide a more accurate final calculation of the degree of disease activity, which reflects data from current medical studies.The accuracy of the system was also tested on a test sample of independent patients, showing more than 96% correct calculations of disease activity, confirming the effectiveness and feasibility of introducing the system into clinical practice.

Topology-Aware Differential Privacy for Decentralized Image Classification

Image classification is a fundamental artificial intelligence task that labels images into one of some predefined classes. However, training complex image classification models requires a large amount of computation resources and data in order to reach state-of-the-art performance. This demand drives the growth of distributed deep learning, where multiple agents cooperatively train global models with their individual datasets. Among such learning systems, decentralized learning is particularly attractive, as it can improve the efficiency and fault tolerance by eliminating the centralized parameter server, which could be the single point of failure or performance bottleneck. Although the agents do not need to disclose their training image samples, they exchange parameters with each other at each iteration, which can put them at the risk of data privacy leakage. Past works demonstrated the possibility of recovering training images from the exchanged parameters. One common defense direction is to adopt Differential Privacy (DP) to secure the optimization algorithms such as Stochastic Gradient Descent (SGD). Those DP-based methods mainly focus on standalone systems, or centralized distributed learning. How to enforce and optimize DP protection in decentralized learning systems is unknown and challenging, due to their complex communication topologies and distinct learning characteristics. In this paper, we design TOP- DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">topology-aware</i> noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies.

Expression Recognition of Classroom Children’s Game Video Based on Improved Convolutional Neural Network

Humans express emotions in many ways, such as gestures, limbs, and expressions. Among them, facial expressions are the most intuitive way to express human inner emotional activities in human-to-human communication. With the rapid development of computer vision, facial expression recognition is an important research topic in the field of computer vision. It plays a key role in nonverbal communication and can be applied to human-computer interaction, social robotics, video games, and other fields. Traditional expression recognition algorithms require complex manual feature extraction, which takes a long time, and the accuracy of expression recognition in complex scenes is not high. However, with the development of deep learning, especially the convolutional neural network, facial expression recognition technology has also developed rapidly, and the recognition accuracy has been greatly improved. This paper studies the facial expression recognition method of classroom children’s game video based on convolutional neural network and proposes a convolutional neural network with deeper layers. The full connection is modified to 4 layers of convolution, 4 layers of pooling, and 2 layers of full connection. Firstly, the facial expression image is preprocessed by, for example, key point location, face cropping, and image normalization; then, the convolutional layer is used to extract the low-dimensional and high-dimensional feature information of the face image; and the pooling layer is used to extract the face image. The feature information is dimensionally reduced. Finally, the softmax classifier is used to classify and recognize the expressions of the training sample images. In order to improve the accuracy of expression recognition, a self-made set of labeled pictures was added to the expression training set. Simulation and comparison experiments show that the improved model has higher accuracy and smoother loss curve, which verifies the effectiveness of the improved network.

High-accuracy acoustic sediment classification using sub-bottom profile data

Sub-bottom sediment classifications have been widely used in marine science and engineering to obtain high-resolution information on types of sediments; however, these are often plagued by inaccuracies. Classification difficulties arise from the inability to effectively filter multiple reflections, extract representative lithology characteristic parameters, identify sub-bottom layer interfaces, extract image samples, control sample quality, optimise characteristic parameters, etc. To generate a highly accurate sub-bottom profile sediment map, a five-step classification method that considers two key lithology characteristic parameters of sub-bottom profile acoustic data was proposed. First, multiple reflections were filtered from the sea surface and sub-bottom layer interfaces of the primary signal. Second, two key characteristic parameters (relative backscattering intensity difference and attenuation compensation residual) were calculated. These reflect the relative differences in backscattering intensity and the attenuation compensation between adjacent interfaces based on the sound intensity attenuation model of a sub-bottom profile. Third, a combined method based on the sediment quality factor and peak trough of the echo signal loss level curve was employed to identify the actual interfaces between layers. An additional technique was proposed to determine the image sample width and preferred characteristic parameters. The resulting high-quality image samples and preferred characteristic parameters not only resulted in a faster convergence rate and increased ability of self-aggregation and identification, but also ensured that the training results met the convergence accuracy requirement. Ultimately, the preferred image samples were trained to classify the overall sub-bottom map of a selected test area of approximately 36 km2 in Bahai Bay, China. Compared with traditional methods, a considerably higher sediment identification accuracy was obtained. The experimental results indicate that the contribution rate of the two key lithology characteristic parameters was 65.49% according to principal component analysis, and the internal and external compatibilities were 97.98% and 84.76% for the training image samples, respectively. The total identification accuracy for the sub-bottom profile map was 98.2%. The two key characteristic parameters accurately captured the acoustic characteristics of sub-bottom sediments, significantly improving sediment classification. These results show that this method could be used to help refine the distributional estimates of submarine mineral resources.

A Discriminative Target Equation-Based Face Recognition Method for Teaching Attendance

In this paper, we use discriminative objective equations to conduct an in-depth study and analysis of face recognition methods in teaching attendance and use the model in actual teaching attendance. It focuses on the design and implementation of the attendance module, which uses wireless network technology to record students’ access to classrooms in real time, and relies on face recognition technology to identify students’ sign-in images to achieve attendance records of students’ independent attendance sign-in. Real-time detection of student attendance is achieved by combining face detection and face recognition technology through regular camera photography and automatic attendance check-in by the server. Based on the recognition results of the attendance check-in image, an attendance mechanism is proposed, and the attendance score of the student for the current course can be calculated using the attendance mechanism, which realizes the automatic management of student attendance. For the face recognition process, the system uses the Ad boost algorithm based on Hear features to achieve face detection, preprocesses the face samples with gray normalization, rotation correction, and size correction, and uses the method based on LBP features to achieve face recognition. Firstly, a combination of histogram equalization and wavelet denoising is chosen to preprocess the training sample images to obtain the face image light invariance description, and then, the initial dictionary is constructed using the dimensionality reduction performance of the PCA method; next, the initial dictionary is updated, and a new dictionary with representation and discrimination capabilities is obtained using the LC-KSVD algorithm that makes improvements in the dictionary update stage. The sparse coefficients of the feature matrix of the test sample image under the new dictionary are calculated, and the class correlation reconstruction is performed on the feature matrix of the test sample image, and the corresponding reconstruction error is solved; finally, the discriminative classification of the test sample image is achieved according to the solved class correlation reconstruction error. The relevant experiments on the face database prove that the algorithm can improve the recognition accuracy to a certain extent and better solve the influence of changing lighting conditions on the face recognition accuracy.

A terahertz time-domain super-resolution imaging method using a local-pixel graph neural network for biological products

The low image acquisition speed of terahertz (THz) time-domain imaging systems limits their application in biological products analysis. In the current study, a local pixel graph neural network was built for THz time-domain imaging super-resolution. The method could be applied to the analysis of any heterogeneous biological products as it only required a small number of sample images for training and particularly it focused on THz feature frequencies. The graph network applied the Fourier transform to graphs extracted from low-resolution (LR) images bringing an invariance of rotation and flip for local pixels, and the network then learnt the relationship between the state of graphs and the corresponding pixels to be reconstructed. With wood cores and seeds as examples, the images of these samples were captured by a THz time-domain imaging system for training and analysed by the method, achieving the root mean square error (RMSE) of pixels of 0.0957 and 0.1061 for the wood core and seed images, respectively. In addition, the reconstructed high-resolution (HR) images, LR images and true HR images at several feature frequencies were also compared in the current study. Results indicated that the method could not only reconstruct the spatial details and the useful signals from high noise signals at high feature frequencies but could also operate super-resolution in both spatial and spectral aspects.

Optimum Feature Selection with Particle Swarm Optimization to Face Recognition System Using Gabor Wavelet Transform and Deep Learning.

In this study, Gabor wavelet transform on the strength of deep learning which is a new approach for the symmetry face database is presented. A proposed face recognition system was developed to be used for different purposes. We used Gabor wavelet transform for feature extraction of symmetry face training data, and then, we used the deep learning method for recognition. We implemented and evaluated the proposed method on ORL and YALE databases with MATLAB 2020a. Moreover, the same experiments were conducted applying particle swarm optimization (PSO) for the feature selection approach. The implementation of Gabor wavelet feature extraction with a high number of training image samples has proved to be more effective than other methods in our study. The recognition rate when implementing the PSO methods on the ORL database is 85.42% while it is 92% with the three methods on the YALE database. However, the use of the PSO algorithm has increased the accuracy rate to 96.22% for the ORL database and 94.66% for the YALE database.

Multi-Scale and Multi-Direction GAN for CNN-Based Single Palm-Vein Identification

Despite recent advances of deep neural networks in hand vein identification, the existing solutions assume the availability of a large and rich set of training image samples. These solutions, therefore, still lack the capability to extract robust and discriminative hand-vein features from a single training image sample. To overcome this problem, we propose a single-sample-per-person (SSPP) palm-vein identification approach, where only a single sample per class is enrolled in the gallery set for training. Our approach, named MSMDGAN + CNN, consists of a multi-scale and multi-direction generative adversarial network (MSMDGAN) for data augmentation and a convolutional neural network (CNN) for palm-vein identification. First, a novel data augmentation approach, MSMDGAN, is developed to learn the internal distribution of patches in a single image. The proposed MSMDGAN consists of multiple fully convolutional GANs, each of which is responsible for learning the patch distribution within an image at a different scale and at a different direction. Second, given the resulting augmented data by MSMDGAN, we design a CNN for single sample palm-vein recognition. The experimental results on two public hand-vein databases demonstrate that MSMDGAN is able to generate realistic and diverse samples, which, in turn, improves the stability of the CNN. In terms of accuracy, MSMDGAN + CNN outperforms other representative approaches and achieves state-of-the-art recognition results.

Ensemble of Multiscale Fine-Tuning Convolutional Neural Networks for Recognition of Benign and Malignant Thyroid Nodules

<p indent=0mm>Aiming at the problem of poor classification performance due to the small number of training image samples and ignoring multiscale structure and texture information, in order to improve the accuracy of diagnosis of benign and malignant thyroid nodule, this paper proposes a method for thyroid nodule ultrasound image recognition based on ensemble of multiscale fine-tuning convolutional neural networks. Firstly, the image is converted into three different scales of information as input data, so that the model can learn the feature information of different scales of the image, and improve the feature extraction ability of the model. Secondly, nine fine-tuning models of three different scales were constructed by optimizing the full-connection layer structure of three kinds of pretraining models (AlexNet, VGG16 and ResNet50) and the transfer learning and fine-tuning strategy, so that the model could better learn the characteristic differences of source domain (ImageNet) and target domain (thyroid ultrasound image). Finally, the optimal fine-tuning model combination is selected and the final integration model is obtained by the weighted fusion method of model output category probability, and the classification performance is further improved by utilizing the diversity of models. The proposed algorithm was compared with other algorithms on the real data set, and the accuracy, sensitivity, specificity and area under curve (AUC) of benign and malignant thyroid nodules were 96.0%, 94.1%, 97.7% and 0.98. The experimental results show that the algorithm is superior to the traditional machine learning algorithm and other algorithms in the field of benign and malignant thyroid nodule identification, and can effectively extract complementary visual feature information with satisfactory classification performance.

A New Mask R-CNN-Based Method for Improved Landslide Detection

This article presents a novel method of landslide detection by exploiting the Mask R-CNN capability of identifying an object layout by using a pixel-based segmentation, along with transfer learning used to train the proposed model. A data set of 160 elements is created containing landslide and nonlandslide images. The proposed method consists of three steps: augmenting training image samples to increase the volume of the training data; fine-tuning with limited image samples; and performance evaluation of the algorithm in terms of precision, recall, and F1 measure, on the considered landslide images, by adopting ResNet-50 and 101 as backbone models. The experimental results are quite encouraging as the proposed method achieves precision equals to 1.00, recall 0.93, and F1 measure 0.97, when ResNet-101 is used as backbone model, and with a low number of landslide photographs used as training samples. The proposed algorithm can be potentially useful for land-use planners and policymakers of hilly areas where intermittent slope deformations necessitate landslide detection as a prerequisite before planning.

Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network

Abstract The fault detection of rotating machinery systems especially its typical components such as bearings and gears is of special importance for maintaining machine systems working normally and safely. However, due to the change of working conditions, the disturbance of environment noise, the weakness of early features and various unseen compound failure modes, it is quite hard to achieve high-accuracy intelligent failure monitoring task of rotating machinery using existing intelligent fault diagnosis approaches in real industrial applications. In the paper, a novel and high-accuracy fault detection approach named WT-GAN-CNN for rotating machinery is presented based on Wavelet Transform (WT), Generative Adversarial Nets (GANs) and convolutional neural network (CNN). The proposed WT-GAN-CNN approach includes three parts. To begin with, WT is employed for extracting time-frequency image features from one-dimension raw time domain signals. Secondly, GANs are used to generate more training image samples. Finally, the built CNN model is used to accomplish the fault detection of rotating machinery by the original training time-frequency images and the generated fake training time-frequency images. Two experiment studies are implemented to assess the effectiveness of our proposed approach and the results demonstrate it is higher in testing accuracy than other intelligent failure detection approaches in the literatures even in the interference of strong environment noise or when working conditions are changed. Furthermore, its result in the stability of testing accuracy is also quite excellent.

An Improved SAR Image Target Recognition Algorithm

Target recognition is a key step in the interpretation of SAR images. For existing SAR image recognition methods based on sparse representation, the recognition rate is still not high enough. Based on the analysis of the impact recognition rate, the target region and shadow region characteristics in SAR images are combined. In this paper, a SAR image target recognition method based on sparse representation and stretching is proposed. In this method, a new training sample image is generated by stretching the training sample image, a sparse dictionary is constructed by using the existing training sample image and a new training sample image, and the joint sparse representation of the target region and the shadow region is solved by the reconstruction. The minimum error criterion completes the SAR image target recognition. The target recognition method of this paper is tested by using MSTAR real-measured SAR image. The results show that the recognition rate of this method is higher than that of existing methods, which verifies the effectiveness of the proposed method.

Remote Sensing Image Super-resolution Based on Sparse Representation

In order to obtain higher resolution remote sensing images with more details, an improved sparse representation remote sensing image super-resolution reconstruction(SRR) algorithm is proposed. First, remote sensing image is preprocessed to obtain the required training sample image; then, the KSVD algorithm is used for dictionary training to obtain the high-low resolution dictionary pairs; finally, the image feature extraction block is represented, which is improved by using adaptive filtering method. At the same time, the mean value filtering method is used to improve the super-resolution reconstruction iterative calculation. Experiment results show that, compared with the most advanced sparse representation super-resolution algorithm, the improved sparse representation super-resolution method can effectively avoid the loss of edge information of SRR image and obtain a better super-resolution reconstruction effect. The texture details are more abundant in subjective vision, the PSNR is increased about 1 dB, and the structure similarity (SSIM) is increased about 0.01.

Fusion linear representation-based classification

Representation-based classification methods have brought into sharp focus in recent years and achieved better classification performance. Both collaborative representation-based classification (CRC) algorithm and linear regression classification (LRC) algorithm are two typical representation-based classification methods. However, patterns from a single object are requested to lie on a linear subspace in representation-based classification methods. There are not enough samples in reality for face recognition, and it is difficult for the limited data to meet the requirement. The mirror images and the inverse images of the original images are still an effective description of the face. The problem of insufficient sample can be solved well by means of mirror image and inverse image. Based on this idea, a novel fusion linear representation-based classification method is proposed in the paper. The mirror image of each training sample is firstly generated, and the original training samples and the new obtained mirror images corresponding to the original training sample images are used for acting as training set for LRC. Then, the inverse image of each image is generated and the inverse training images are used to perform CRC. Lastly, the score-level fusion scheme is taken to complete classification task. The extensive experiment results on four public image databases clearly indicate that our method has very competitive classification results.