Classification of X-Ray images of shipping containers

Smuggling has long played an important role in the inefficiency of economies. To secure the borders against this illegal act, X-Ray Inspection Systems are often deployed at the borders and customs. In this paper, we present a new method for classification of shipping containers X-Ray images, produced in the inspection lines. The aim is to improve the matching accuracy of the presented manifest, which lists the claimed contents of the shipping containers, with the real contents of the container. The proposed method is based on utilizing Scale Invariant Feature Transforms (SIFT) feature vectors, Bag of visual words (BOVW) and tree augmented naive Bayes (TAN) approach for classifying containers X-Ray images. The prior research on classification of X-Ray images of shipping containers has focused mostly on working with greedy algorithms such as sliding windows for task of classification. More recent studies introduced filter banks and visual words for extraction of features. The proposed method for the first time considers the salient points and keypoints for the task of feature extraction. In addition, this paper presents a framework using the tree augmented naive Bayes based on the theory of learning Bayesian networks, which is proved to have a significant improvements upon the prior designed systems by considering the correlations among the extracted features. For experimental evaluations, our method is compared with two recently proposed methods on containers X-Ray images categorization. The results show that the proposed method is more accurate and time-efficient in categorization of X-Ray images.     

Improved Beam Steering Method Using OAM Waves

Orbital Angular Momentum (OAM) is an intrinsic feature of electromagnetic waves which has recently found many applications in several areas in radio and optics. In this paper, we use OAM wave characteristics to present a simple method for beam steering over both elevation and azimuth planes. The design overcomes some limitations of traditional steering methods, such as limited dynamic range of steering, the design complexity, bulky size of the steering structure, the limited bandwidth of operation, and low gain. Based on OAM wave characteristics, the proposed steering method avoids design complexities by adopting a simple method for generating the OAM-carrying waves. The waves are generated by an array of Planar Circular Dipole (PCD) elements. These elements are designed to cover a wide bandwidth range between 3 and 30 GHz. The transmitting array shows an enhanced gain value from 8.5 dBi to almost 11.5 dBi at the broadside angle. Besides the enhanced PCD-based OAM generation, the novelty of the design lies in a new method of beam steering. Beam steering is then performed by controlling the electrical feeding of the PCD elements; the beam azimuthal location is managed by turning off some of the PCD elements, while the elevation is determined by changing the gradient phase of excitation for the turned-on PCD elements. Detailed analysis of the steering method is carried out by finding the mathematical model of the system and the generated waves. The performance has been verified through numerical simulators.     

Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is neovascularisation, the growth of abnormal new vessels. This paper describes an automated method for the detection of new vessels in retinal images. Two vessel segmentation approaches are applied, using the standard line operator and a novel modified line operator. The latter is designed to reduce false responses to non-vessel edges. Both generated binary vessel maps hold vital information which must be processed separately. This is achieved with a dual classification system. Local morphology features are measured from each binary vessel map to produce two separate feature sets. Independent classification is performed for each feature set using a support vector machine (SVM) classifier. The system then combines these individual classification outcomes to produce a final decision. Sensitivity and specificity results using a dataset of 60 images are 0.862 and 0.944 respectively on a per patch basis and 1.00 and 0.90 respectively on a per image basis.     

MSMD: maximum separability and minimum dependency feature selection for cropland classification from optical and radar data

Cropland classification using optical and full polarimetric synthetic aperture radar (PolSAR) images is a topic of considerable interest in the remote-sensing community. These two data sources can provide a diverse set of temporal, spectral, textural and polarimetric features which can be invaluable for cropland classification. However, some optical features or some radar features may have a relatively high correlation with other features. Hence, it seems to be necessary to choose the optimum features in order to reduce the dimensions of the data and to improve cropland classification accuracy. This article proposes a strategic feature selection method from a feature set of bitemporal RapidEye and Uninhabited Aerial Vehicle synthetic aperture radar (UAVSAR) images. The proposed method is designed to select the most relevant features and to remove redundant features based on the two concepts of separability and dependency. The proposed method is therefore referred to as maximum separability and minimum dependency (MSMD). For evaluating efficiency, MSMD and some well-known filter and wrapper feature selection methods are compared using a random forest classifier. Experimental tests confirmed that the classification results obtained from the MSMD feature selection method were more accurate than those achieved by filter methods. Moreover, they had an accuracy comparable to that of the results from the wrapper method. Furthermore, with regard to running time, MSMD operated as fast as the filter methods. It had a straightforward structure compared to the wrapper method, and as a result was faster than this method.     

Parallel supervised land-cover classification system for hyperspectral and multispectral images

Hyperspectral and multispectral imagery allows remote-sensing applications such as the land-cover mapping, which is a significant baseline to understand and to monitor the Earth. Furthermore, it is a relevant process for socio-economic activities. For that reason, high land-classification accuracies are imperative, and minor image processing time is essential. In addition, the process of gathering classes’ documented samples is complicated. This implies that the classification system is required to perform with a limited number of training observations. Another point worth mentioning is that there are hardly any methods that can be used analogously for hyperspectral or multispectral images. This paper aims to propose a novel classification system that can be used for both types of images. The designed classification system is composed of a novel parallel feature extraction algorithm, which utilises a cluster of two graphics processing units in combination with a multicore central processing unit (CPU), and an artificial neural network (ANN) particularly devised for the classification of the features ensued by the implemented feature extraction method. To prove the performance of the proposed classification system, it is compared with non-parallel and CPU-only-parallel implementations employing multispectral and hyperspectral databases. Moreover, experiments with different number of samples for training the classifier are performed. Finally, the proposed ANN is compared with a state-of-the-art support vector machine in classification and processing time results.     

融合空间和通道特征的高精度乳腺癌分类方法

组织病理学图像是鉴别乳腺癌的黄金标准,所以对乳腺癌组织病理学图像的自动、精确的分类具有重要的临床应用价值。为了提高乳腺组织病理图像的分类准确率,从而满足临床应用的需求,提出了一种融合空间和通道特征的高精度乳腺癌分类方法。该方法使用颜色归一化来处理病理图像并使用数据增强扩充数据集,基于卷积神经网络（CNN）模型DenseNet和压缩和激励网络（SENet）融合病理图像的空间特征信息和通道特征信息,并根据压缩-激励（SE）模块的插入位置和数量,设计了三种不同的BCSCNet模型,分别为BCSCNetⅠ、BCSCNetⅡ、BCSCNetⅢ。在乳腺癌癌组织病理图像数据集（BreaKHis）上展开实验。通过实验对比,先是验证了对图像进行颜色归一化和数据增强能提高乳腺的分类准确率,然后发现所设计的三种乳腺癌分类模型中精度最高为BCSCNetⅢ。实验结果表明,BCSCNetⅢ的二分类准确率在99.05%~99.89%,比乳腺癌组织病理学图像分类网络（BHCNet）提升了0.42个百分点;其多分类的准确率在93.06%~95.72%,比BHCNet提升了2.41个百分点。证明了BCSCNet能准确地对乳腺癌组织病理图像进行分类,同时也为计算机辅助乳腺癌诊断提供了可靠的理论支撑。     

一种新的退化交通标志图像的分类算法研究

为了识别退化的交通标志图像,提出了一种新的分类算法。该算法在处理图像的退化问题时,采用模糊—仿射不变距直接提取图像的特征而不需要图像的清晰化处理;在利用模糊—仿射不变距提取图像特征的基础上,采用递归正交最小二乘算法设计了一种新的径向基概率神经网络分类器。仿真结果表明:模糊—仿射不变距是一种有效的处理退化的交通标志图像的方法,所设计的径向基概率神经网络分类器不仅具有精简的结构,而且,具有较好分类和推广性能。     

GP-based secondary classifiers

Genetic programming (GP) is used to evolve secondary classifiers for disambiguating between pairs of handwritten digit images. The inherent property of feature selection accorded by GP is exploited to make sharper decision between conflicting classes. Classification can be done in several steps with an available feature set and a mixture of strategies. A two-step classification strategy is presented in this paper. After the first step of the classification using the full feature set, the high confidence recognition result will lead to an end of the recognition process. Otherwise a secondary classifier designed using a sub-set of the original feature set and the information available from the earlier classification step will help classify the input further. The feature selection mechanism employed by GP selects important features that provide maximum separability between classes under consideration. In this way, a sharper decision on fewer classes is obtained at the secondary classification stage. The full feature set is still available in both stages of classification to retain complete information. An intuitive motivation and detailed analysis using confusion matrices between digit classes is presented to describe how this strategy leads to improved recognition performance. In comparison with the existing methods, our method is aimed for increasing recognition accuracy and reliability. Results are reported for the BHA test-set and the NIST test-set of handwritten digits.     

Joint spectral-spatial hyperspectral image classification based on hierarchical subspace switch ensemble learning algorithm

In this paper, a novel spectral-spatial hyperspectral image classification method has been proposed by designing hierarchical subspace switch ensemble learning algorithm. First, the hyperspectral images are processed by fast bilateral filtering to get the spatial features. The spectral features and spatial features are combined to form the initial feature set. Second, Hierarchical instance learning based on iterative means clustering method is designed to obtain hierarchical instance space. Third, random subspace method (RSM) is used for sampling the features and samples, thereby forming multiple sub sample set. After that, semi-supervised learning (S²L) is applied to choose test samples for improving classification performance without touching the class labels. Then, micro noise linear dimension reduction (mNLDR) is used for dimension reduction. Afterwards, ensemble multiple kernels SVM(EMK_SVM) are used for stable classification results. Finally, final classification results are obtained by combining classification results with voting strategy. Experimental results on real hyperspectral scenes demonstrate that the proposed method can effectively improve the classification performance apparently.     

MMM: classification of schizophrenia using multi-modality multi-atlas feature representation and multi-kernel learning

Schizophrenia (SZ) is a complex neuropsychiatric disorder that seriously affects the daily life of patients. Therefore, accurate diagnosis of SZ is essential for patient care. Several T1-weighted magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) markers (e.g., cortical thickness (CT), mean diffusivity (MD)) for SZ have been identified by using some existing brain atlases, and have been used successfully to discriminate patients with SZ from healthy controls (HCs). Currently, these markers have mainly been used separately. Thus, the full potential of T1-weighted MRI images and DTI images for SZ diagnosis might not yet have been used comprehensively. Furthermore, the extraction of these markers based on single brain atlas might not yet be able to use the full potential of these images. Therefore, in this study, we propose a multi-modality multi-atlas feature representation and a multi-kernel learning method (MMM) to perform SZ/HC classification. Firstly, we extract 8 feature sets from T1-weighted MRI images and DTI images via 4 existing brain atlases and 4 markers. Then, a two-step feature selection method is proposed to select the most discriminative features of each feature set for SZ/HC classification. Finally, a multiple feature sets based multi-kernel SVM learning method (MFMK-SVM) is proposed to combine all feature sets for SZ/HC classification. Experimental results show that our proposed method achieves an accuracy of 91.28%, a sensitivity of 90.85%, a specificity of 92.17% and an AUC of 0.9485 for SZ/HC classification. Experimental results illustrate that our proposed classification method is efficient and promising for clinical diagnosis of SZ.

     

Texture classification with combined rotation and scale invariant wavelet features

In this work, a new rotational and scale invariant feature set for textural image classification, combined invariant feature (CIF) set has been introduced. It is an integration of the crude wavelets like Gaussian, Mexican Hat and orthogonal wavelets like Daubechies to achieve a high quality rotational and scale invariant feature set. Also it is added with features obtained using the newly proposed weighted smoothening Gaussian filter masks to improve the classification results. To reduce the effect of overlapping features, the variations among the feature set are analyzed and the eigenfeatures are extracted to produce good classification result.The rotational invariance is achieved by using these two wavelets with their directional properties and the scale invariance is achieved by a method, which is an extension to fractal dimension (FD) features. The first- and second-order statistical parameter and entropy characterize the quality of the features extracted. Furthermore, a comparison that shows the higher recognition rate achieved with the newly proposed method for the set of 6720 samples collected from 105 different textures of Brodatz, Vistek, Indezine databases and some additional images collected from other resources of indexed and true color images is shown.     

Iterative curved surface fitting algorithm using a raster-scanning window

In this paper, an iterative curved surface fitting method using a small sliding window is first proposed to smooth the original organized point cloud data (PCD) with noise and fluctuation. Samples included in a small sliding window positioned in PCD are successively fitted to a quadratic surface from upper left to lower right using a least squares method. In the iterative process, outliers of samples are asymptotically removed based on an evaluation index. This proposed method allows original PCD to be smoothed keeping its own shape feature. Then, the already developed stereolithography (STL) generator is used to produce triangulated patches from the smoothed PCD. The process allows to reconstruct 3D digital data of a real object written with STL format for reverse engineering from original PCD with noise. The effectiveness and usefulness of the proposed curved surface fitting method are demonstrated through actual smoothing experiments.     

Hybridized approach of image segmentation in classification of fruit mango using BPNN and discriminant analyzer

In machine learning, image classification accuracy generally depends on image segmentation and feature extraction methods with the extracted features and its qualities. The main focus of this paper is to determine the defected area of mangoes using image segmentation algorithm for improving the classification accuracy. The Enhanced Fuzzy based K-means clustering algorithm is designed for increasing the efficiency of segmentation. Proposed segmentation method is compared with K-means and Fuzzy C-means clustering methods. The geometric, texture and colour based features are used in the feature extraction. Process of feature selection is done by Maximally Correlated Principal Component Analysis (MCPCA). Finally, in the classification step, severe portions of the affected area are analyzed by Backpropagation Based Discriminant Classifier (BBDC). Proposed classifier is compared with BPNN and Naive Bayes classifiers. The images are classified into three classes in final output like Class A –good quality mango, Class B-average quality mango, and Class C-poor quality mango. Finally, the evaluated results of the proposed model examine various defected and healthy mango images and prove that the proposed method has the highest accuracy when compared with existing methods.

     

Discriminative training approaches to fabric defect classification based on wavelet transform

Wavelet transform is able to characterize the fabric texture at multiscale and multiorientation, which provides a promising way to the classification of fabric defects. For the objective of minimum error rate in the defect classification, this paper compares six wavelet transform-based classification methods, using different discriminative training approaches to the design of the feature extractor and classifier. These six classification methods are: methods of using an Euclidean distance classifier and a neural network classifier trained by maximum likelihood method and backpropagation algorithm, respectively; methods of using an Euclidean distance classifier and a neural network classifier trained by minimum classification error method, respectively; method of using a linear transformation matrix-based feature extractor and an Euclidean distance classifier, designed by discriminative feature extraction (DFE) method; method of using an adaptive wavelet-based feature extractor and an Euclidean distance classifier, designed by the DFE method. These six approaches have been evaluated on the classification of 466 defect samples containing eight classes of fabric defects, and 434 nondefect samples. The DFE training approach using adaptive wavelet has been shown to outperform the other approaches, where 95.8% classification accuracy was achieved.     

特征重用和注意力机制下肝肿瘤自动分类

目的 肝肿瘤分类计算机辅助诊断技术在临床医学中具有重要意义,但样本缺乏、标注成本高及肝脏图像的敏感性等原因,限制了深度学习的分类潜能,使得肝肿瘤分类依然是医学图像处理领域中具有挑战性的任务。针对上述问题,本文提出了一种结合特征重用和注意力机制的肝肿瘤自动分类方法。方法 利用特征重用模块对计算机断层扫描（computed tomography,CT）图像进行伪自然图像的预处理,复制经Hounsfield处理后的原通道信息,并通过数据增强扩充现有数据;引入基于注意力机制的特征提取模块,从全局和局部两个方面分别对原始数据进行加权处理,充分挖掘现有样本的高维语义特征;通过迁移学习的训练策略训练提出的网络模型,并使用Softmax分类器实现肝肿瘤的精准分类。结果 在120个病人的514幅CT扫描切片上进行了综合实验。与基准方法相比,本文方法平均分类准确率为87.78%,提高了9.73%;与肝肿瘤分类算法相比,本文算法针对转移性肝腺癌、血管瘤、肝细胞癌及正常肝组织的分类召回率分别达到79.47%、79.67%、85.73%和98.31%;与主流分类模型相比,本文模型在多种评价指标中均表现优异,平均准确率、召回率、精确率、F1-score及AUC（area under ROC curve）分别为87.78%、84.43%、84.59%、84.44%和97.50%。消融实验表明了本文设计的有效性。结论 本文方法能提高肝脏肿瘤的分类结果,可为临床诊断提供依据。     

多特征融合的遥感图像分类

针对高分辨率遥感图像特点,提出了一种多特征融合的分类方法。该方法首先改进了原始的视觉词袋生成算法;然后,分别提取图像的视觉词袋局部特征、颜色直方图特征以及Gabor纹理特征;最后采用支持向量机进行分类,并对多特征分类结果进行自适应综合。采用一个具有2 100幅图像的大型遥感图像分类公共测试数据集进行分类实验,与仅用单一特征分类方法的最高分类精度相比,本文多特征融合的遥感影像分类方法总体平均分类精度提高了10%,表明本文提出方法是一种有效的高分辨率遥感图像分类方法     

基于角度径向变换的旋转不变纹理分类

纹理分类广泛的应用于医学图像分析等领域,纹理图像的采集因拍摄角度的变化产生一定的旋转,本文提出一种基于角度径向变换的旋转不变纹理分类方法。首先采用角度径向变换方法对图像进行特征提取,分别得到图像的角向特征向量和径向特征向量;然后将提取出的2组特征向量结合起来作为图像的整体特征向量,利用K近邻特征空间距离的分类方法进行纹理分类。选取Brodatz纹理库中的图像进行纹理分类测试,实验结果表明,该算法具有较好的旋转不变纹理分类效果。     

A shape–size index extraction for classification of high resolution multispectral satellite images

We propose a new spatial feature extraction method for supervised classification of satellite images with high spatial resolution. The proposed shape–size index (SSI) feature combines homogeneous areas using spectral similarity between one central pixel and its neighbouring pixels. A spatial index considers the shape and size of the homogeneous area, and suitable spatial features are parametrically selected. The generated SSI feature is integrated with the original high resolution multispectral bands to improve the overall classification accuracy. A support vector machine (SVM) is employed as a classifier. In order to evaluate the proposed feature extraction method, KOMPSAT-2 (Korea Multipurpose Satellite 2), QuickBird-2 and IKONOS-2 high resolution satellite images are used. The experiments show that the SSI algorithm leads to a notable increase in classification accuracy over the grey level co-occurrence matrix (GLCM) and pixel shape index (PSI) algorithms, and an increase when compared with using multispectral bands only.     

Latent Space Representational Learning of Deep Features for Acute Lymphoblastic Leukemia Diagnosis

Acute Lymphoblastic Leukemia (ALL) is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow. Early prognosis of ALL is indispensable for the effectual remediation of this disease. Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images, a process which is time-consuming and prone to errors. Therefore, many deep learning-based computer-aided diagnosis (CAD) systems have been established to automatically diagnose ALL. This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images. The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks (CNNs) to identify the existence of ALL in blood smears. An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images. A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set. The latent features are used to perform image classification using Support Vector Machine (SVM) classifier. The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features. Moreover, the classification performance of the system with various sizes of the latent feature set is evaluated. The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.