Image Feature Extraction Method Research Articles

Diagnosis of anomalies based on hybrid features extraction in thyroid images.

Diagnosing benign and malignant glands in thyroid ultrasound images is considered a challenging issue. Recently, deep learning techniques have significantly resulted in extracting features from medical images and classifying them. Convolutional neural networks ignore the hierarchical structure of entities within images and do not pay attention to spatial information as well as the need for a large number of training samples. Capsule networks consist of different hierarchical capsules equivalent to the same layers in the convolutional neural networks. We propose a feature extraction method for ultrasound images based on the capsule network. Then, we combine those deep features with conventional features such as Histogram of Oriented Gradients and Local Binary Pattern together to form a hybrid feature space. We increase the accuracy percentage of a support vector machine (SVM) by balancing and reducing the data dimensions of samples. Since the SVM provides different training kernels according to the sample distribution method, the extracted textural features were categorized using each of these kernels to obtain the result. The parameters of classification evaluation using the researcher-made model have outperformed the other methods in this field. Experimental results showed that the combination of HOG, LBP, and CapsNet methods outperformed the others, with 83.95% accuracy in the SVM with a linear kernel.

Analysis of Different Image Enhancement and Feature Extraction Methods

This paper describes an image enhancement method for reliable image feature matching. Image features such as SIFT and SURF have been widely used in various computer vision tasks such as image registration and object recognition. However, the reliable extraction of such features is difficult in poorly illuminated scenes. One promising approach is to apply an image enhancement method before feature extraction, which preserves the original characteristics of the scene. We thus propose to use the Multi-Scale Retinex algorithm, which is aimed to emulate the human visual system and it provides more information of a poorly illuminated scene. We experimentally assessed various combinations of image enhancement (MSR, Gamma correction, Histogram Equalization and Sharpening) and feature extraction methods (SIFT, SURF, ORB, AKAZE) using images of a large variety of scenes, demonstrating that the combination of the Multi-Scale Retinex and SIFT provides the best results in terms of the number of reliable feature matches.

A dual quantum image feature extraction method: PSQIFE

A dual quantum image feature extraction method: PSQIFE

EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification, and Detection Method Evaluation.

Environmental microorganisms (EMs) are ubiquitous around us and have an important impact on the survival and development of human society. However, the high standards and strict requirements for the preparation of environmental microorganism (EM) data have led to the insufficient of existing related datasets, not to mention the datasets with ground truth (GT) images. This problem seriously affects the progress of related experiments. Therefore, This study develops the Environmental Microorganism Dataset Sixth Version (EMDS-6), which contains 21 types of EMs. Each type of EM contains 40 original and 40 GT images, in total 1680 EM images. In this study, in order to test the effectiveness of EMDS-6. We choose the classic algorithms of image processing methods such as image denoising, image segmentation and object detection. The experimental result shows that EMDS-6 can be used to evaluate the performance of image denoising, image segmentation, image feature extraction, image classification, and object detection methods. EMDS-6 is available at the https://figshare.com/articles/dataset/EMDS6/17125025/1.

Learning Texture Features from GLCM for Classification of Brain Tumor MRI Images using Random Forest Classifier

In computer vision, image feature extraction methods are used to extract features so that the features are learnt for classification tasks. In biomedical images, the choice of a particular feature extractor from a diverse range of feature extractors is not only subjective but also it is time consuming to choose the optimum parameters for a particular feature extraction algorithm. In this paper, the focus is on the Grey-level co-occurrence matrix (GLCM) feature extractor for classification of brain tumor MRI images using random forest classifier. A dataset of brain MRI images (245 images) consisting of two classes viz. images with tumor (154 images) and images without tumor (91 images) has been used to assess the performance of GLCM features on random forest classifier in terms of accuracy, true positive rate, true negative rate, false positive rate, false negative rate derived from the confusion matrix. The results show that by using optimum parameters, the GLCM feature extracts significant texture component in brain MRI images for promising accuracy and other performance metrics.

Intelligent collection of rice disease images based on convolutional neural network and feature matching

Rapid and accurate determination of rice diseases is the key to accurate monitoring of agricultural conditions and timely prevention of agricultural yield reduction. Aiming at the problems of low identification accuracy of rice blast and low efficiency of manual detection, we propose an identification method for the six main diseases of rice in the natural environment. At the same time, the identification algorithm of rice false smut is studied. The purpose is to improve the efficiency of the intelligent collection of rice disease images based on convolutional neural network (CNN) and feature matching, so as to identify rice diseases faster. We propose to use SURF and HOG for feature extraction respectively. Then, 20 models were selected using K-nearest neighbors and support vector machine, respectively, for experiments using cross-validation. At the same time, residual network (ResNet) was used to conduct experimental research on six diseases of rice, and the samples were expanded and enhanced. The image scale is increased, and ResNet-20 is used to train the sample data. The experimental model achieved 96.7% accuracy on the test set. The new network achieved 97.4% accuracy. It is nearly 8% points higher than traditional image feature extraction methods. The experimental results show that the improved CNN has high accuracy and a good effect in the identification of main rice diseases.

Genetic programming for automatic skin cancer image classification

Developing a computer-aided diagnostic system for detecting various types of skin malignancies from images has attracted many researchers. However, analyzing the behaviors of algorithms is as important as developing new systems in order to establish the effectiveness of a system in real-time situations which impacts greatly how well it can assist the dermatologist in making a diagnosis. Unlike many machine learning approaches such as Artificial Neural Networks, Genetic Programming (GP) automatically evolves models with its dynamic representation and flexibility. This study aims at analyzing recently developed GP-based approaches to skin image classification. These approaches have utilized the intrinsic feature selection and feature construction ability of GP to effectively construct informative features from a variety of pre-extracted features. These features encompass local, global, texture, color and multi-scale image properties of skin images. The performance of these GP methods is assessed using two real-world skin image datasets captured from standard camera and specialized instruments, and compared with six commonly used classification algorithms as well as existing GP methods. The results reveal that these constructed features greatly help improve the performance of the machine learning classification algorithms. Unlike “black-box” algorithms like deep neural networks, GP models are interpretable, therefore, our analysis shows that these methods can help dermatologists identify prominent skin image features. Further, it can help researchers identify suitable feature extraction methods for images captured from a specific instrument. Being fast, these methods can be deployed for making a quick and effective diagnosis in actual clinic situations.

Partial discharge fault diagnosis based on zernike moment and improved bacterial foraging optimization algorithm

Feature extraction and classifier optimization are important parts in the diagnosis of partial discharge (PD). Traditional feature extraction methods generally target not the images but structured data. Traditional classifier optimization methods have many disadvantages such as the many parameters that need to be adjusted, difficulty in determining the best parameters, and the ease in falling into local optimal solutions. To eliminate these defects, a PD diagnosis method of gas-insulated switchgear (GIS) based on the Zernike moment and improved support vector machine (SVM) is proposed. Firstly, five typical PD models of corona discharge, metal particle discharge, floating electrode discharge, void discharge, and surface discharge were designed. Then, the UHF sensor was used to collect discharge signals of different defects and different types of interference signals to build a PD phase-resolved pulse sequence (PRPS) patterns library. After that, the Zernike moment of the PRPS images were extracted as the PD features. Finally, the SVM model based on the differential evolution adaptive bacterial foraging optimization (DEABFO) algorithm was used to fulfill the GIS PD diagnosis. The results show that the Zernike moment feature extraction method is suitable for PD PRPS images, and DEABFO improves the convergence speed of the SVM parameter optimization process and can effectively avoid the probability of falling into the local optimum. Compared with other image feature extraction methods and other SVM optimization algorithms, this method has high accuracy in GIS PD fault diagnosis, with the recognition rate reaching 91.23%.

Buried target detection method for ground penetrating radar based on deep learning

Deep learning method has been extensively applied to ground penetrating radar two-dimensional profile (GPR B-SCAN) hyperbola detection recently. We propose a B-SCAN image feature extraction method based on the constraints of the GPR physical model, and further detect the weak boundary feature curve of the target in the local space. A deep convolutional neural network (DCNN) is first designed to extract high-level semantic features from B-SCAN images to remove direct wave. Next, a multiscale feature fusion DCNN is used to extract the features of the B-SCAN image with the direct wave removed, and the classifier network is used to identify the hyperbola of the upper boundary feature of the target. Finally, according to the hyperbola, the local space corresponding to the target in the B-SCAN image is determined. On this basis, the amplitude and phase information of the scattered electric field are used to segment the lower boundary characteristic curve of the target through convolution operation. Experimental results on simulation and field data show that feature information of the buried target in the GPR B-SCAN image can be efficiently extracted when the proposed method is adopted.

Using Image Feature Extraction to Identification of Ancient Ceramics Based on Partial Differential Equation

This paper presents an in-depth study and analysis of the image feature extraction technique for ancient ceramic identification using an algorithm of partial differential equations. Image features of ancient ceramics are closely related to specific raw material selection and process technology, and complete acquisition of image features of ancient ceramics is a prerequisite for achieving image feature identification of ancient ceramics, since the quality of extracted area-grown ancient ceramic image feature extraction method is closely related to the background pixels and does not have generalizability. In this paper, we propose a deep learning-based extraction method, using Eased as a deep learning support platform, to extract and validate 5834 images of 272 types of ancient ceramics from kilns, celadon, and Yue kilns after manual labelling and training learning, and the results show that the average complete extraction rate is higher than 99%. The implementation of the deep learning method is summarized and compared with the traditional region growth extraction method, and the results show that the method is robust with the increase of the learning amount and has generalizability, which is a new method to effectively achieve the complete image feature extraction of ancient ceramics. The main content of the finite difference method is to use the ratio of the difference between the function values of two adjacent points and the distance between the two points to approximate the partial derivative of the function with respect to the variable. This idea was used to turn the problem of division into a problem of difference. Recognition of ancient ceramic image features was realized based on the extraction of the overall image features of ancient ceramics, the extraction and recognition of vessel type features, the quantitative recognition of multidimensional feature fusion ornamentation image features, and the implementation of deep learning based on inscription model recognition image feature classification recognition method; three-layer B/S architecture web application system and cross-platform system language called as the architectural support; and database services, deep learning packaging, and digital image processing. The specific implementation method is based on database service, deep learning encapsulation, digital image processing, and third-party invocation, and the service layer fusion and relearning mechanism is proposed to achieve the preliminary intelligent recognition system of ancient ceramic vessel type and ornament image features. The results of the validation test meet the expectation and verify the effectiveness of the ancient ceramic vessel type and ornament image feature recognition system.

Edge Detection of COVID-19 CT Image Based on GF_SSR, Improved Multiscale Morphology, and Adaptive Threshold

Edge detection is an effective method for image segmentation and feature extraction. Therefore, extracting weak edges with the inhomogeneous gray of Corona Virus Disease 2019 (COVID-19) CT images is extremely important. Multiscale morphology has been widely used in the edge detection of medical images due to its excellent boundary detection accuracy. In this paper, we propose a weak edge detection method based on Gaussian filtering and singlescale Retinex (GF_SSR), and improved multiscale morphology and adaptive threshold binarization (IMSM_ATB). As all the CT images have noise, we propose to remove image noise by Gaussian filtering. The edge of CT images is enhanced using the SSR algorithm. In addition, based on the extracted edge of CT images using improved Multiscale morphology, a particle swarm optimization (PSO) algorithm is introduced to binarize the image by automatically getting the optimal threshold. To evaluate our method, we use images from three datasets, namely COVID-19, Kaggle-COVID-19, and COVID-Chestxray, respectively. The average values of results are worthy of reference, with the Shannon information entropy of 1.8539, the Precision of 0.9992, the Recall of 0.8224, the F-Score of 1.9158, running time of 11.3000. Finally, three types of lesion images in the COVID-19 dataset are selected to evaluate the visual effects of the proposed algorithm. Compared with the other four algorithms, the proposed algorithm effectively detects the weak edge of the lesion and provides help for image segmentation and feature extraction.

Past, present and future of gene feature selection for breast cancer classification – a survey

Computational-based analysis of gene expression to evaluate the genetic pattern provides better breast cancer prediction. It is a challenge to identify these samples correctly and effectively. Overcoming the curse of dimensionality is another challenge in feature selection. It has gained a lot of interest in the classification of cancer-based on a molecular level as it offers a systematic, precise and reliable diagnosis for different types of cancer. Machine learning (ML) algorithms are applied in a wide range of applications such as drug discovery, prediction of cancer and diagnosis. This survey paper focused on the critical steps of computer-aided detection systems: image acquisition procedures, techniques, feature extraction, and classification methods used in 2010-2020 in the field of gene expression-based cancer diagnosis. Finally, this paper ends with concluding notes and future directions. This survey is intended to be a guide for the real-time use of recent advances in gene expression-based cancer diagnosis.

Research on Multi-View Image Reconstruction Technology Based on Auto-Encoding Learning

Traditional three-dimensional (3D) image reconstruction method, which highly dependent on the environment and has poor reconstruction effect, is easy to lead to mismatch and poor real-time performance. The accuracy of feature extraction from multiple images affects the reliability and real-time performance of 3D reconstruction technology. To solve the problem, a multi-view image 3D reconstruction algorithm based on self-encoding convolutional neural network is proposed in this paper. The algorithm first extracts the feature information of multiple two-dimensional (2D) images based on scale and rotation invariance parameters of Scale-invariant feature transform (SIFT) operator. Secondly, self-encoding learning neural network is introduced into the feature refinement process to take full advantage of its feature extraction ability. Then, Fish-Net is used to replace the U-Net structure inside the self-encoding network to improve gradient propagation between U-Net structures, and Generative Adversarial Networks (GAN) loss function is used to replace mean square error (MSE) to better express image features, discarding useless features to obtain effective image features. Finally, an incremental structure from motion (SFM) algorithm is performed to calculate rotation matrix and translation vector of the camera, and the feature points are triangulated to obtain a sparse spatial point cloud, and meshlab software is used to display the results. Simulation experiments show that compared with the traditional method, the image feature extraction method proposed in this paper can significantly improve the rendering effect of 3D point cloud, with an accuracy rate of 92.5% and a reconstruction complete rate of 83.6%.

Comprehensive edge direction descriptor for fingerprint liveness detection

The edge direction is one of the most discriminative image information. The existing edge direction based feature extraction methods only extract the explicit edge direction information but ignore the complementary implicit edge direction information. In this paper, we propose a comprehensive edge direction information based image feature extraction method for fingerprint liveness detection. The main novelties of our method can be summarized as follows. (1) We propose the singular value decomposition (SVD) based image Log-Gabor transform energy extraction method, with the energy image preserving the most dominant convolution response. (2) We extract the explicit and implicit edge direction information from the Log-Gabor transform of original image and SVD energy image respectively. (3) Adopting the Log-Gabor filters as the codewords, we propose the orientation normalization based scale Non-K-Maximum suppression Log-Gabor transform encoding method and the positive–negative separation mean pooling method. Our method is of lower computational complexity compared with existing codeword based image representation methods. Extensive experimental evaluations on three benchmark databases show that the proposed method yields desirable performance compared with the state-of-the-art methods.

JOINT AND INDIVIDUAL ANALYSIS OF BREAST CANCER HISTOLOGIC IMAGES AND GENOMIC COVARIATES.

The two main approaches in the study of breast cancer are histopathology (analyzing visual characteristics of tumors) and genomics. While both histopathology and genomics are fundamental to cancer research, the connections between these fields have been relatively superficial. We bridge this gap by investigating the Carolina Breast Cancer Study through the development of an integrative, exploratory analysis framework. Our analysis gives insights - some known, some novel - that are engaging to both pathologists and geneticists. Our analysis framework is based on Angle-based Joint and Individual Variation Explained (AJIVE) for statistical data integration and exploits Convolutional Neural Networks (CNNs) as a powerful, automatic method for image feature extraction. CNNs raise interpretability issues that we address by developing novel methods to explore visual modes of variation captured by statistical algorithms (e.g. PCA or AJIVE) applied to CNN features.

A novel image‐orientation feature extraction method for partial discharges

Partial discharge identification is of great significance in monitoring power equipment. Although substantial work has been done in partial discharge pattern recognition, most studies have been performed in noise-free environments. To improve the accuracy of partial discharge pattern recognition, this paper introduces a partial discharge image feature extraction method based on upright speeded-up robust features. Each group of phase-resolved pulse sequence data is converted into grayscale images to construct a sample library of partial discharge defects. Upright speeded-up robust features is used to extract features in grayscale images. The improved support vector machine is used to achieve the best classification of partial discharge sources. The sensitivity of local features to different phase resolutions and different image resolutions of partial discharge phase-resolved pulse sequence patterns was investigated, and the optimal phase resolution and image resolution were used to construct phase-resolved pulse sequence patterns. In addition, the recognition effect of this feature extraction method under different noise conditions was also analysed. The results prove that upright speeded-up robust features can effectively deal with noisy data. The results of this research can provide references for the storage setting and recognition of three-dimensional images of on-site partial discharge data.

Automatic Algorithm for Fractal Plant Art Image Similarity Feature Generation

With the popularity of smart devices and the Internet, the volume of multimedia data is growing rapidly, and content-based image retrieval (CBIR) can search for similar images from large-scale images to realize the utilization of the data. For data owners, outsourcing the management and maintenance of image data to cloud service providers can effectively reduce costs, but there is a privacy leakage problem. In this paper, we focus on image feature extraction, index design, and image similarity recognition methods under a dual server model with content-based image security similarity recognition as the research topic, the work done such as proposing a BOVW (Bag of Visual Word) feature-based image security similarity recognition scheme. The scheme combines SIFT (scale-invariant feature transform) feature secure extraction and locally sensitive hashing algorithm to achieve secure extraction of BOVW features of images. To protect the BOVW features of images, an inverted index based on word frequency division is designed, the index is stored in chunks, and an image secure similarity recognition scheme based on CNN (convolutional neural networks) features is proposed. The scalable hash index based on dimensional division is designed based on the image CNN features secure extraction algorithm. The security and performance of the proposed scheme are theoretically analyzed and experimentally verified. Based on different image datasets, the impact of different parameters on the performance of the scheme is tested, and optimized parameters are given. The experimental results show that the proposed scheme in this paper can effectively improve the efficiency of analyzing the similarity of plant botanical art images compared to the existing schemes.

Study on wear state evaluation of friction stir welding tools based on image of surface topography

The status of the friction stir welding tool is an important factor affecting weld quality. The texture feature of the weld surface is the result of friction between tool and material. In this paper, friction stir welding experiments were performed on 2219 aluminum alloys with tools under different wear conditions to observe the changes in surface topography characteristics. The results show that the tool wear will lead to the confusion of the weld texture profile and the appearance of the local burr. Furthermore, we proposed a feature extraction method for weld surface images based on an improved local binary pattern algorithm, which can obtain local subtle feature changes. Euclidean distance similarity was used to evaluate the weld surface image, the results show that it has a good correlation with the wear state of the tool.

Multi-source image target detection technology based on salient feature fusion

The ground target can be easily affected by the complexity of ground objects and photoelectric interference, so the accuracy of target detection in complex background is not always satisfying. To this end, joint target detection of Infrared/Visible image, IR/VI, is adopted, and the feature representation is achieved by applying the method of deep image feature extraction. According to the different imaging characteristics of the target, the feature fusion is carried out to form a unified target feature representation. As a result, target detection based on deep learning can be achieved by the model established by such fused feature. Experiments show that the proposed method can effectively improve the accuracy of target detection.

Traffic sign recognition based on HOG feature extraction

The substantial increase in the number of motor vehicles in recent years has caused many traffic safety problems and has aroused widespread concern. As the basis of intelligent vehicle environment perception and a necessary condition for realizing the functions of assisted driving system, traffic sign recognition is of great significance for realizing automatic driving of vehicles, improving intelligent transportation systems, and promoting the development of smart cities.This paper mainly identifies traffic signs, using histogram of gradient feature extraction method. The image is collected and preprocessed by a vision sensor. The color threshold segmentation method and morphological processing are used to reduce the interference of the background area and enhance the contour of the sign area. Finally, HOG method is used to collect the gradient of each pixel point in the cell unit or the direction histogram of the edge to identify traffic signs. Through MATALB simulation, it is obtained that the HOG image feature extraction method has high accuracy, small error and short recognition time, which shows the effectiveness of the algorithm.