Supervised parametric and non-parametric classification of chromosome images

This paper describes a fully automatic chromosome classification algorithm for Multiplex Fluorescence In Situ Hybridization (M-FISH) images using supervised parametric and non-parametric techniques. M-FISH is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and a DNA stain. The classification problem is modelled as a 25-class 6-feature pixel-by-pixel classification task. The 25 classes are the 24 types of human chromosomes and the background, while the six features correspond to the brightness of the dyes at each pixel. Maximum likelihood estimation, nearest neighbor and k-nearest neighbor methods are implemented for the classification. The highest classification accuracy is achieved with the k-nearest neighbor method and k=7 is an optimal value for this classification task.     

Using an unsupervised approach of Probabilistic Neural Network (PNN) for land use classification from multitemporal satellite images

The aim of this work is to develop an unsupervised approach based on Probabilistic Neural Network (PNN) for land use classification. A time series of high spatial resolution acquired by LANDSAT and SPOT images has been used to firstly generate the profiles of Normalized Difference Vegetation Index (NDVI) and then used for the classification procedure.The proposed method allows the implementation of cluster validity technique in PNN using Ward's method to get clusters. This procedure is completely automatic with no parameter adjusting and instantaneous training, has high ability in producing a good cluster number estimates and provides a new point of view to use PNN as unsupervised classifier. The obtained results showed that this approach gives an accurate classification with about 3.44% of error through a comparison with the real land use and provides a better performance when comparing to usual unsupervised classification methods (fuzzy c-means (FCM) and K-means).     

An end-user-oriented framework for the classification of multitemporal SAR images

In this article, we present an end-user-oriented framework for multitemporal synthetic aperture radar (SAR) data classification. It accepts as input the recently introduced Level-1α products, whose peculiarities are a high degree of interpretability and increased class separability with respect to single greyscale images. These properties make the Level-1α products very attractive in the application of simple supervised classification algorithms. Specifically, (1) the high degree of interpretability of the maps makes the training phase extremely simple; and (2) the good separation between classes gives excellent results using simple discrimination rules. The end product is a simple, fast, accurate, and repeatable framework.     

Laplace Beltrami eigen value based classification of normal and Alzheimer MR images using parametric and non-parametric classifiers

Automated study of brain sub-anatomic region like Corpus Callosum (CC) is challenging due to its complex topology and varying shape. The development of reliable Computer Aided Diagnosis (CAD) systems would help in the early detection of Alzheimer's Disease (AD) and to perform drug trails to palliate the effect of AD. In this work, an attempt has been made to analyse the shape changes of CC using shape based Laplace Beltrami (LB) eigen value features and machine learning techniques. CC from the normal and AD T1-weighted magnetic resonance images are segmented using Reaction Diffusion (RD) level set method and the obtained results are validated against the Ground Truth (GT) images. Ten LB eigen values are extracted from the segmented CC images. LB eigen values are positive sequence of infinite series that describe the intrinsic geometry of objects. These values capture the shape information of CC by solving the eigen value problem of LB operator on the triangular meshes. The significant features are selected based on Information Gain (IG) ranking and subjected to classification using K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Naïve Bayes (NB). The performance of LB eigen values in the AD diagnosis is evaluated using classifiers’ accuracy, specificity and sensitivity measures.Results show that, RD level set is able to segment CC in normal and AD images with high percentage of similarity with GT. The extracted LB eigen values are found to show high difference in the mean values between normal and AD subjects with high statistical significance. The LB eigen modes λ2, λ7 and λ8 are identified as prominent features by IG based ranking. KNN is able to give maximum classification accuracy of 93.37% compared to linear SVM and NB classifiers. This value is observed to be high than the results obtained using geometric features. The proposed CAD system focuses solely on the geometric variations of CC extracted using LB eigen value spectrum. The extraction of eigen modes in the LB spectrum is easy to compute, does not involve too many parameters and less time consuming. Thus this CAD study seems to be clinically significant in the shape investigation of brain structures for AD diagnosis.     

Local SVM approaches for fast and accurate classification of remote-sensing images

In this article, the task of remote-sensing image classification is tackled with local maximal margin approaches. First, we introduce a set of local kernel-based classifiers that alleviate the computational limitations of local support vector machines (SVMs), maintaining at the same time high classification accuracies. Such methods rely on the following idea: (a) during training, build a set of local models covering the considered data and (b) during prediction, choose the most appropriate local model for each sample to evaluate. Additionally, we present a family of operators on kernels aiming to integrate the local information into existing (input) kernels in order to obtain a quasi-local (QL) kernel. To compare the performances achieved by the different local approaches, an experimental analysis was conducted on three distinct remote-sensing data sets. The obtained results show that interesting performances can be achieved in terms of both classification accuracy and computational cost.     

An incremental-learning neural network for the classification of remote-sensing images

A novel classifier for the analysis of remote-sensing images is proposed. Such a classifier is based on Radial Basis Function (RBF) neural networks and relies on an incremental-learning technique. This technique allows the periodical acquisition of new information whenever a new training set becomes available, while preserving the knowledge learnt by the network on previous training sets. In addition, in each retraining phase, the network architecture is automatically updated so that new classes may be considered. These characteristics make the proposed neural classifier a promising tool for several remote-sensing applications.     

Markovian modelling and Fisher distribution for unsupervised classification of radar images

Statistical segmentation techniques based on hidden Markov field modelling have generated considerable interest in past years. They take contextual information into account in a particularly elegant and rigorous way. Although these models have been thoroughly tested, they can fail in some cases such as the non-stationary one. In this article, we propose use of the recently developed triplet Markov field, which models non-stationary images, and that of Fisher distribution, which is adapted to a wide range of surfaces for modelling synthetic aperture radar (SAR) image noise. Examples illustrate the difference between the approach proposed and classical ones. Various experiments indicate that the new model and its associated unsupervised algorithm perform better than classical ones.     

Experimental comparison of parametric,non-parametric,and hybrid multigroup classification

This study evaluates the relative performance of some well-known classification techniques, as well as a proposed hybrid method. The proposed hybrid method is a combination of k-nearest neighbor (kNN) and linear programming (LP) method for four group classification. Computational experiments are conducted to evaluate the performances of these classification techniques. Monte Carlo simulation is used to generate dataset with varying characteristics such as multicollinearity, nonlinearity, etc. for the experiments. The experimental results indicate that LP approaches, in general, and the proposed hybrid method, in particular, consistently have lower misclassification rates for most data characteristics. Furthermore, the hybrid method utilizes the strengths of both methods – k-NN and linear programming – resulting in considerable improvement in the classification accuracy. The results of this study can aid in the design of various hybrid techniques that combine the strengths of different methods to improve classification accuracy and reliability.     

Fuzzy clustering algorithms for unsupervised change detection in remote sensing images

In this paper, we propose a context-sensitive technique for unsupervised change detection in multitemporal remote sensing images. The technique is based on fuzzy clustering approach and takes care of spatial correlation between neighboring pixels of the difference image produced by comparing two images acquired on the same geographical area at different times. Since the ranges of pixel values of the difference image belonging to the two clusters (changed and unchanged) generally have overlap, fuzzy clustering techniques seem to be an appropriate and realistic choice to identify them (as we already know from pattern recognition literatures that fuzzy set can handle this type of situation very well). Two fuzzy clustering algorithms, namely fuzzy c-means (FCM) and Gustafson-Kessel clustering (GKC) algorithms have been used for this task in the proposed work. For clustering purpose various image features are extracted using the neighborhood information of pixels. Hybridization of FCM and GKC with two other optimization techniques, genetic algorithm (GA) and simulated annealing (SA), is made to further enhance the performance. To show the effectiveness of the proposed technique, experiments are conducted on two multispectral and multitemporal remote sensing images. A fuzzy cluster validity index (Xie-Beni) is used to quantitatively evaluate the performance. Results are compared with those of existing Markov random field (MRF) and neural network based algorithms and found to be superior. The proposed technique is less time consuming and unlike MRF does not require any a priori knowledge of distributions of changed and unchanged pixels.     

GPU classification of remote-sensing images using kernel ELM and extended morphological profiles

Nowadays, the use of hyperspectral sensors has been extended to a variety of applications such as the classification of remote-sensing images. Recently, a spectral–spatial classification scheme (ELM-EMP) based on Extreme Learning Machine (ELM) and Extended Morphological Profiles (EMPs) computed using Principal Component Analysis (PCA) and morphological operations has been introduced. In this work, an efficient implementation of this scheme over commodity Graphics Processing Units (GPUs) is shown. Additionally, several techniques and optimizations are introduced to improve the accuracy of the classification. In particular, a scheme using an ELM classifier based on kernels (KELM) and EMP is presented (KELM-EMP). Similar schemes adding a spatial regularization process (KELM-EMP-S and ELM-EMP-S) are also proposed. Moreover, two PCA algorithms have been compared in both accuracy and speed terms. Regarding the GPU projection, different techniques and optimizations have been applied such as the use of optimized Compute Unified Device Architecture (CUDA) libraries or a block-asynchronous execution technique. As a result, the accuracy obtained by the two proposed schemes (ELM-EMP-S and KELM-EMP-S) is better than for the original scheme ELM-EMP and the execution time has been significantly reduced.     

Contribution of multispectral and multitemporal information from MODIS images to land cover classification

The goal of this study is to evaluate the relative usefulness of high spectral and temporal resolutions of MODIS imagery data for land cover classification. In particular, we highlight the individual and combinatorial influence of spectral and temporal components of MODIS reflectance data in land cover classification. Our study relies on an annual time series of twelve MODIS 8-days composited images (MOD09A1) monthly acquired during the year 2000, at a 500 m nominal resolution. As our aim is not to propose an operational classifier directed at thematic mapping based on the most efficient combination of reflectance inputs — which will probably change across geographical regions and with different land cover nomenclatures — we intentionally restrict our experimental framework to continental Portugal. Because our observation data stream contains highly correlated components, we need to rank the temporal and the spectral features according not only to their individual ability at separating the land cover classes, but also to their differential contribution to the existing information. To proceed, we resort to the median Mahalanobis distance as a statistical separability criterion. Once achieved this arrangement, we strive to evaluate, in a classification perspective, the gain obtained when the dimensionality of the input feature space grows. We then successively embedded the prior ranked measures into the multitemporal and multispectral training data set of a Support Vector Machines (SVM) classifier. In this way, we show that, only the inclusion of the approximately first three dates substantially increases the classification accuracy. Moreover, this multitemporal factor has a significant effect when coupled with combinations of few spectral bands, but it turns negligible as soon as the full spectral information is exploited. Regarding the multispectral factor, its beneficence on classification accuracy remains more constant, regardless of the number of dates being used.     

A novel unsupervised Levy flight particle swarm optimization (ULPSO) method for multispectral remote-sensing image classification

The rapid development of earth observation technology has produced large quantities of remote-sensing data. Unsupervised classification (i.e. clustering) of remote-sensing images, an important means to acquire land-use/cover information, has become increasingly in demand due to its simplicity and ease of application. Traditional methods, such as k-means, struggle to solve this NP-hard (Non-deterministic Polynomial hard) image classification problem. Particle swarm optimization (PSO), always achieving better result than k-means, has recently been applied to unsupervised image classification. However, PSO was also found to be easily trapped on local optima. This article proposes a novel unsupervised Levy flight particle swarm optimization (ULPSO) method for image classification with balanced exploitation and exploration capabilities. It benefits from a new searching strategy: the worst particle in the swarm is targeted and its position is updated with Levy flight at each iteration. The effectiveness of the proposed method was tested with three types of remote-sensing imagery (Landsat Thematic Mapper (TM), Flightline C1 (FLC), and QuickBird) that are distinct in terms of spatial and spectral resolution and landscape. Our results showed that ULPSO is able to achieve significantly better and more stable classification results than k-means and the other two intelligent methods based on genetic algorithm (GA) and particle swarm optimization (PSO) over all of the experiments. ULPSO is, therefore, recommended as an effective alternative for unsupervised remote-sensing image classification.     

Finger vein segmentation in infrared images using supervised and unsupervised clustering algorithms

In this paper, two new methods to segment infrared images of finger in order to perform the finger vein pattern extraction task are presented. In the first, the widespread known and used K nearest neighbor (KNN) classifier, which is a very effective supervised method for clustering data sets, is used. In the second, a novel clustering algorithm named nearest neighbor clustering algorithm (NNCA), which is unsupervised and has been recently proposed for retinal vessel segmentation, is used. As feature vectors for the classification process in both cases two features are used: the multidirectional response of a matched filter and the minimum eigenvalue of the Hessian matrix. The response of the multidirectional filter is essential for robust classification because offers a distinction between vein-like and edge-like structures while Hessian based approaches cannot offer this. The two algorithms, as the experimental results show, perform well with the NNCA has the advantage that is unsupervised and thus can be used for full automatic finger vein pattern extraction. It is also worth to note that the proposed vector, composed only of two features, is the simplest feature set which has proposed in the literature until now and results in a performance comparable with others that use a vector with much larger size (31 features). NNCA evaluated also quantitatively on a database which contains artificial images of finger and achieved the segmentation rates: 0.88 sensitivity, 0.80 specificity and 0.82 accuracy.     

Combining algorithms for automatic detection of optic disc and macula in fundus images

This paper proposes an efficient combination of algorithms for the automated localization of the optic disc and macula in retinal fundus images. There is in fact no reason to assume that a single algorithm would be optimal. An ensemble of algorithms based on different principles can be more accurate than any of its individual members if the individual algorithms are doing better than random guessing. We aim to obtain an improved optic disc and macula detector by combining the prediction of multiple algorithms, benefiting from their strength and compensating their weaknesses. The location with maximum number of detectors’ outputs is formally the hotspot and is used to find the optic disc or macula center. An assessment of the performance of integrated system and detectors working separately is also presented. Our proposed combination of detectors achieved overall highest performance in detecting optic disc and fovea closest to the manually center chosen by the retinal specialist.     

A novel unsupervised bee colony optimization (UBCO) method for remote-sensing image classification: a case study in a heterogeneous marsh area

Unsupervised image classification is an important means to obtain land-use/cover information in the field of remote sensing, since it does not require initial knowledge (training samples) for classification. Traditional methods such as k-means and Iterative self-organizing data analysis technique (ISODATA) have limitations in solving this NP-hard unsupervised classification problem, mainly due to their strict assumptions about the data distribution. The bee colony optimization (BCO) is a new type of swarm intelligence, based upon which a simple and novel unsupervised bee colony optimization (UBCO) method is proposed for remote-sensing image classification. UBCO possesses powerful exploitation and exploration capacities that are carried out by employed bees, onlookers, and scouts. This allows the promising regions to be globally searched quickly and thoroughly, without becoming trapped on local optima. In addition, it has no restrictions on data distribution, and thus is especially suitable for handling complex remote-sensing data. We tested the method on the Zhalong National Nature Reserve (ZNNR) – a typical inland wetland ecosystem in China, whose landscape is heterogeneous. The preliminary results showed that UBCO (overall accuracy = 80.81%) achieved statistically significant better classification result (McNemar test) in comparison with traditional k-means (63.11%) and other intelligent clustering methods built on genetic algorithm (unsupervised genetic algorithm (UGA), 71.49%), differential evolution (unsupervised differential evolution (UDE), 77.57%), and particle swarm optimization (unsupervised particle swarm optimization (UPSO), 69.86%). The robustness and superiority of UBCO were also demonstrated from the two other study sites next to the ZNNR with distinct landscapes (urban and natural landscapes). Enabling one to consistently find the optimal or nearly optimal global solution in image clustering, the UBCO is thus suggested as a robust method for unsupervised remote-sensing image classification, especially in the case of heterogeneous areas.     

结合非监督分类和几何—纹理—光谱特征的高分影像道路提取

目的 目前针对复杂场景高分辨率遥感影像道路提取多采用监督分类方法,但需要人工选择样本,自动化程度低且具有不稳定性。基于像元级的方法,提取完整度低且易产生椒盐噪声;面向对象的方法易产生粘连问题。为了提高道路提取的完整度、准确度和自动化程度,提出一种基于非监督分类和几何—纹理—光谱特征的道路提取方法。方法 首先考虑光谱特征利用非监督分类进行初步分割,结合基于纹理特征分类的结果得到初始道路区域。然后根据道路特征建立一套完整的非道路区域滤除体系：边缘滤波断开道路和非道路的连接、纹理滤波滤除大面积非道路区域、形状滤波去除剩余小面积非道路区域。最后利用张量投票算法得到连贯、平滑的道路中心线。结果 选择复杂场景下的高分辨率IKONOS影像和QuickBird影像进行实验,与国内外基于像素和面向对象的两种有代表性的道路提取方法进行对比,采用完整率、正确率、检测质量3个评价指标进行定量评价。实验结果表明该方法相比于其他算法在完整率、正确率和检测质量上平均提高26.61%、5.57%和26.77%。定性分析结果表明,本文方法可以有效改善椒盐噪声和粘连现象。此外本文方法的自动化程度更高。结论 提出了一种基于非监督分类和几何—纹理—光谱特征的高分辨遥感影像道路提取方法,非监督相对于监督分类的方法有更高的自动化程度,复杂场景下的道路提取融合几何—纹理—光谱特征有效避免了基于像元级道路提取易产生的椒盐噪声现象和面向对象道路提取易产生的粘连现象。该方法适用于高分辨率遥感影像城市道路提取,能够得到较高的完整度、准确度以及自动化程度。非监督分类和多特征结合的道路提取方法有广阔的应用前景。     

Combining supervised and unsupervised learning for data clustering

Clustering aims to partition a data set into homogenous groups which gather similar objects. Object similarity, or more often object dissimilarity, is usually expressed in terms of some distance function. This approach, however, is not viable when dissimilarity is conceptual rather than metric. In this paper, we propose to extract the dissimilarity relation directly from the available data. To this aim, we train a feedforward neural network with some pairs of points with known dissimilarity. Then, we use the dissimilarity measure generated by the network to guide a new unsupervised fuzzy relational clustering algorithm. An artificial data set and a real data set are used to show how the clustering algorithm based on the neural dissimilarity outperforms some widely used (possibly partially supervised) clustering algorithms based on spatial dissimilarity.     

遥感图像光照一致性定量评价

高分辨率图像比对法是图像质量评价中简单而又行之有效的方法,其前提是两幅用于比较的高低分辨率图像具有良好的一致性,但实际情况往往很难满足这些一致性要求。为了使不能满足光照一致性的图像也能用于卫星在轨参数监测,需要进行光照一致性校正。针对如何定量评价多幅遥感图像的光照一致性问题,提出了一种定量评价方法。该方法根据Retinex原理,将图像分解为光照分量和反射分量,然后比较光照分量直方图的相似度,将这一相似度约束在0～1之间,称为光照一致性系数。实验结果表明,这种方法评价的结果与主观感受相一致,能够量化图像的光照一致性。     

Applying tree-based ensemble algorithms to the classification of ecological zones using multi-temporal multi-source remote-sensing data

The decision tree method has grown fast in the past two decades and its performance in classification is promising. The tree-based ensemble algorithms have been used to improve the performance of an individual tree. In this study, we compared four basic ensemble methods, that is, bagging tree, random forest, AdaBoost tree and AdaBoost random tree in terms of the tree size, ensemble size, band selection (BS), random feature selection, classification accuracy and efficiency in ecological zone classification in Clark County, Nevada, through multi-temporal multi-source remote-sensing data. Furthermore, two BS schemes based on feature importance of the bagging tree and AdaBoost tree were also considered and compared. We conclude that random forest or AdaBoost random tree can achieve accuracies at least as high as bagging tree or AdaBoost tree with higher efficiency; and although bagging tree and random forest can be more efficient, AdaBoost tree and AdaBoost random tree can provide a significantly higher accuracy. All ensemble methods provided significantly higher accuracies than the single decision tree. Finally, our results showed that the classification accuracy could increase dramatically by combining multi-temporal and multi-source data set.