基于光谱特征和纹理特征协同学习的高光谱图像数据分类

高光谱遥感图像中包含有大量的高维数据,传统的有监督学习算法在对这些数据进行分类时要求获取足够多的有标记样本用于分类器的训练.然而,对高光谱图像中大量的复杂地物像元所属类别进行准确标注通常需要耗费极大的人力.在本文中,我们提出了一种基于半监督学习的光谱和纹理特征协同学习(STF-CT)--法,利用协同学习机制将高光谱图像光谱特征和空间纹理特征这两种不同的特征结合起来,用于小训练样本集下的高光谱图像数据分类问题.STF-CT算法充分利用了高光谱图像的光谱和纹理特征这两个独立视图,构建起一种有效的半监督分类方法,用于提升分类器在小训练样本集情况下的分类精度.实验结果表明该算法在小训练样本集下的高光谱地物分类问题上具有很好的效果.     

基于流形学习和K-最近邻分类器的旋转机械故障诊断方法

针对旋转机械故障诊断需人工干预、精度低、故障样本难以获取等问题,提出基于流形学习和K-最近邻分类器（KNNC）的故障诊断模型。提取振动信号多域信息熵以全面反映设备运行状态并构造高维特征集;利用正交邻域保持嵌入(ONPE)非线性流形学习算法的二次特征提取特性进行维数约简使特征具有更好的聚类特性;基于改进的更适用于小样本分类KNNC进行模式识别,用轴承故障诊断案例证明该模型的有效性。     

一种用于高光谱图像分类的空谱协同编码方法

针对现有基于协同表示的分类算法对于高光谱遥感图像的空间光谱信息利用不充分而造成较低分类精度的问题,该文提出一种空谱协同编码方法用于高光谱图像分类。算法首先利用空间光谱信息对图像进行加权滤波。随后,对于协同编码模型,将空间光谱信息转化为空间光谱权重以对模型进行正则约束。在Indian Pines和University of Pavia真实数据集上的实验结果表明提出的算法能分别获得98.82%和99.09%的总体精度。实验证明了所提出的算法对高光谱遥感图像进行分类的有效性。     

基于半监督邻域自适应正交判别投影的转子故障诊断

针对故障特征集维数过高导致故障难以辨识的问题,提出一种基于半监督邻域自适应正交判别投影(SSNA-ODP)的转子故障诊断方法.提取原始振动信号的时域、频域、时频域特征构造混合域特征集;利用SSNA-ODP方法对混合域特征集进行维数约简,提取出有利于实施分类的低维特征子集;输入到支持向量机(SVM)中进行模式识别.典型故...     

融合夹角度量的局部线性嵌入算法

局部线性嵌入(LLE)等流形学习算法中需要通过欧氏距离来度量数据点之间的近邻关系,但欧氏距离只表示两点间的直线距离,在高维空间中不一定能真实反映出图像数据点之间的空间分布情况.针对此问题,本文提出了融合数据间夹角和欧氏距离度量LLE近邻和分类的方法.该方法通过融合图像数据间的夹角和欧氏距离来度量图像数据点之间的近邻关系,寻找k个近邻点,实现更有效的局部重构,提取鉴别特征,然后用融合了数据间夹角的最近邻分类器对数据进行分类.在KSC和Indian Pine高光谱遥感影像数据集上的实验结果表明:在总体分类精度上,本文算法比LLE提升了1.54%～6.91％.     

影像调色技术分类方法的研究

本文论述了影像调色的机理、种类与方法,并对影像调色的分类方法进行了讨论。     

一种新的高光谱图像波段选择方法

提出了一种新的高光谱图像波段选择方法-波段最大筛选法(Maximum Band Screening,MBS),它将每个波段的像元光谱分量看成一条波段向量,利用光谱相似性度量比较波段与已选波段的不相似性,从而从原始波段中选择信息量既大、又有区别性的波段.为了验证MBS的有效性,将其用于高光谱图像异常探测,设计了异常探测算法.该算法首先从高光谱图像中提取异常目标光谱,噪声白化后,进行MBS波段选择,最后将选出的波段用于自适应余弦估计(Adaptive Coherence Estimator,ACE)目标探测.采用AVIRIS高光谱图像将MBS与另外两种波段选择算法进行比较分析,实验结果表明,在MBS选出的仅占全部波段8%的波段上,ACE算子具有较高的探测性能.     

基于Bagged CART和Boosted CART的高光谱影像分类技术研究

本文针对高光谱影像数据光谱分辨率高,数据量大的特点,采用以CART决策树为弱分类器的Bagging和Boosting集成学习算法对该影像进行分类,通过实验分析比较,体现出了Bagged CART和Boosted CART算法用于分类时的有效性和准确性。     

基于谱聚类波段选择的高光谱图像分类

高光谱图像在地物观测领域得到了广泛的应用。由于高光谱图像具有数据量大、波段间相关度高等特性,波段选择技术成为降低地物识别计算复杂度的重要方法。根据不同波段数据之间的非线性关系,提出了基于谱聚类(SC)的波段选择技术。该方法首先以波段图像为样本点生成近邻图和相似度矩阵,然后借助谱聚类方法将所有数据样本分成 k类,从中选择 k个代表波段参与后继的分类识别任务。实验数据表明,新方法减小了计算复杂度,提高了地物识别的精度。     

基于子空间字典偶学习的高光谱图像分类

针对高光谱高分辨率带来巨大数据量和空间分辨率引起混合像元的问题,提出了基于子空间(subspace)的字典偶学习(DPL)算法,简称DPLsub算法。DPL算法是对字典学习的改进,它通过学习得到综合字典和分析字典,在模式识别中体现了高效性,而子空间投影的方法能更好地表征噪声和高度混合的像元。将光谱和空间特征融合的方法用于分类研究试验。实验数据是两幅高光谱影像,比较了子空间字典偶学习(DPLsub)模型和其他三种分类器即最小二乘支持向量机(LS-SVM)、稀疏多分类回归(SMLR)和字典学习(DL-OMP)的分类结果。实验结果显示,DPLsub算法无论在时间上还是精度上都优于其他算法,证明了这种子空间字典偶学习方法对高光谱图像分类的可行性与高效性。     

基于邻域相似比的图形图像分类方法研究

通过研究图像邻域相似关系,提出了"邻域相似比"的概念。邻域相似比能够表征图像邻域颜色的相似程度。然后以此为核心构建了图形图像分类模型,在Matlab环境中编译算法进行了仿真实验。结果表明,利用邻域相似比进行图形图像分类,算法简单快捷,运算成本低,正确率高。     

基于V-矩的图像分类算法

基于一类不仅含有连续函数,还含有间断函数的正交完备函数系——V-系统,提出相应的V-矩函数,并将之应用到图像分类中.V-系统中基函数的间断特性,使得V-矩函数在描述含有多个闭合边界的形状时有特别的优势,这种优势表现为对这类复杂形状的特征提取更加准确.因此用V-矩可以得到一种图像分类的有效算法.在几个通用数据库中的图像分类实验表明,本文算法较Zernike矩、不变矩和几何中心矩有更高的准确率,对噪声不敏感,特别在含有多个闭合边界的复杂形状分类问题中,本文方法优势更为显著.     

一种非一致小波基的超光谱图像压缩方法

传统的三维小波变换在不同维采用相同的小波基且频谱分辨能力也是相同的,这不能与超光谱图像的特性相匹配.本文提出了一种新的采用非一致小波基的去偶结构的三维小波变换的超光谱压缩方法.由于超光谱图像光谱维和空间维具有明显不同的特性而设计的,本文采用一种非一致小波基设计思路,对不同维使用不同的小波基并与去偶的小波变换结构结合在一起进行小波变换.为了获得符合不同维特性的最优的小波基组,本文通过评估指标来测试各种小波基组合的性能.实验结果表明,本文提出的方法能够明显提高超光谱图像的压缩比,且不需牺牲计算复杂度、可扩展性等额外代价.     

基于感兴趣谱段的LASIS高光谱图像3DSPIHT压缩算法

针对大孔径静态干涉成像光谱仪LASIS的成像特点,提出了一种基于三维小波变换的无链表SPITH算法结合感兴趣谱段保护的图像压缩方案.首先,对高光谱干涉图像序列进行三维非对称等长树离散小波变换.其次,采用感兴趣谱段方法保护重要光谱信息.最后,对无链表三维SPITH算法进行改进,以有效编码高光谱干涉图像的小波变换域.实验结...     

基于APEX算法改进的图像复原算法

在高斯类点扩函数退化图像复原的研究中,提出了一种基于降晰图像频谱特征改进的APEX图像复原算法.该算法采用APEX算法的基本原理,根据图像频谱信息特征,对点扩散函数(PSF)估计过程进行了改进,采用加权最小二乘算法拟合出降晰图像频谱主方向,采用图像频谱主方向上的数据进行PSF估计,以利用更多的有效数据,从而减少PSF的估计误差.针对模拟和实际采集的降晰图像进行实验,采用主观视觉和峰值信噪比进行评价.实验结果表明,改进的算法较使用非主频谱方向上的频谱数据的复原算法在复原效果上有一定的提高.     

Plant Disease Diagnosis and Image Classification Using Deep Learning

Indian agriculture is striving to achieve sustainable intensification, the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem. Modern farming employs technology to improve productivity. Early and accurate analysis and diagnosis of plant disease is very helpful in reducing plant diseases and improving plant health and food crop productivity. Plant disease experts are not available in remote areas thus there is a requirement of automatic low-cost, approachable and reliable solutions to identify the plant diseases without the laboratory inspection and expert's opinion. Deep learning-based computer vision techniques like Convolutional Neural Network (CNN) and traditional machine learning-based image classification approaches are being applied to identify plant diseases. In this paper, the CNN model is proposed for the classification of rice and potato plant leaf diseases. Rice leaves are diagnosed with bacterial blight, blast, brown spot and tungro diseases. Potato leaf images are classified into three classes: healthy leaves, early blight and late blight diseases. Rice leaf dataset with 5932 images and 1500 potato leaf images are used in the study. The proposed CNN model was able to learn hidden patterns from the raw images and classify rice images with 99.58% accuracy and potato leaves with 97.66% accuracy. The results demonstrate that the proposed CNN model performed better when compared with other machine learning image classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree and Random Forest.     

Using Informative Score for Instance Selection Strategy in Semi-Supervised Sentiment Classification

Sentiment classification is a useful tool to classify reviews about sentiments and attitudes towards a product or service. Existing studies heavily rely on sentiment classification methods that require fully annotated inputs. However, there is limited labelled text available, making the acquirement process of the fully annotated input costly and labour-intensive. Lately, semi-supervised methods emerge as they require only partially labelled input but perform comparably to supervised methods. Nevertheless, some works reported that the performance of the semi-supervised model degraded after adding unlabelled instances into training. Literature also shows that not all unlabelled instances are equally useful; thus identifying the informative unlabelled instances is beneficial in training a semi-supervised model. To achieve this, an informative score is proposed and incorporated into semi-supervised sentiment classification. The evaluation is performed on a semi-supervised method without an informative score and with an informative score. By using the informative score in the instance selection strategy to identify informative unlabelled instances, semi-supervised models perform better compared to models that do not incorporate informative scores into their training. Although the performance of semi-supervised models incorporated with an informative score is not able to surpass the supervised models, the results are still found promising as the differences in performance are subtle with a small difference of 2% to 5%, but the number of labelled instances used is greatly reduced from 100% to 40%. The best finding of the proposed instance selection strategy is achieved when incorporating an informative score with a baseline confidence score at a 0.5:0.5 ratio using only 40% labelled data.     

基于分类器链的产品多标签意象识别方法

目的 为快速准确识别消费者对产品意象的认知,提出一种基于分类器链的产品意象识别方法.方法 首先,构建产品意象数据集,通过相似性聚类和网络爬虫得到产品意象词与产品图像,在此基础上,进行产品意象实验,获得消费者对于产品意象的认知,构建产品意象数据集;然后,提取图像特征,利用卷积神经网络RestNet50提取产品图像特征;最后,使用分类器链算法构建产品意象识别模型,提出基于混淆矩阵与条件熵的分类器链标签顺序确定方法,确定产品意象标签顺序.结论 为了验证所述标签顺序确定方法在识别产品意象中具有优越性设计了对比实验.实验结果表明,相较于其他方法,基于分类器链的产品多标签意象识别方法考虑了标签的识别结果与相关关系,能显著提升模型对于产品多标签意象的预测性能.     

A Deep Learning Hierarchical Ensemble for Remote Sensing Image Classification

Artificial intelligence, which has recently emerged with the rapid development of information technology, is drawing attention as a tool for solving various problems demanded by society and industry. In particular, convolutional neural networks (CNNs), a type of deep learning technology, are highlighted in computer vision fields, such as image classification and recognition and object tracking. Training these CNN models requires a large amount of data, and a lack of data can lead to performance degradation problems due to overfitting. As CNN architecture development and optimization studies become active, ensemble techniques have emerged to perform image classification by combining features extracted from multiple CNN models. In this study, data augmentation and contour image extraction were performed to overcome the data shortage problem. In addition, we propose a hierarchical ensemble technique to achieve high image classification accuracy, even if trained from a small amount of data. First, we trained the UC-Merced land use dataset and the contour images for each image on pretrained VGGNet, GoogLeNet, ResNet, DenseNet, and EfficientNet. We then apply a hierarchical ensemble technique to the number of cases in which each model can be deployed. These experiments were performed in cases where the proportion of training datasets was 30%, 50%, and 70%, resulting in a performance improvement of up to 4.68% compared to the average accuracy of the entire model.