Scene classification based on a hierarchical convolutional sparse auto-encoder for high spatial resolution imagery

Efficiently representing and recognizing the semantic classes of the subregions of large-scale high spatial resolution (HSR) remote-sensing images are challenging and critical problems. Most of the existing scene classification methods concentrate on the feature coding approach with handcrafted low-level features or the low-level unsupervised feature learning approaches, which essentially prevent them from better recognizing the semantic categories of the scene due to their limited mid-level feature representation ability. In this article, to overcome the inadequate mid-level representation, a patch-based spatial-spectral hierarchical convolutional sparse auto-encoder (HCSAE) algorithm, based on deep learning, is proposed for HSR remote-sensing imagery scene classification. The HCSAE framework uses an unsupervised hierarchical network based on a sparse auto-encoder (SAE) model. In contrast to the single-level SAE, the HCSAE framework utilizes the significant features from the single-level algorithm in a feedforward and full connection approach to the maximum extent, which adequately represents the scene semantics in the high level of the HCSAE. To ensure robust feature learning and extraction during the SAE feature extraction procedure, a ‘dropout’ strategy is also introduced. The experimental results using the UC Merced data set with 21 classes and a Google Earth data set with 12 classes demonstrate that the proposed HCSAE framework can provide better accuracy than the traditional scene classification methods and the single-level convolutional sparse auto-encoder (CSAE) algorithm.     

Revisiting linear discriminant techniques in gender recognition

Emerging applications of computer vision and pattern recognition in mobile devices and networked computing require the development of resource-limited algorithms. Linear classification techniques have an important role to play in this context, given their simplicity and low computational requirements. The paper reviews the state-of-the-art in gender classification, giving special attention to linear techniques and their relations. It discusses why linear techniques are not achieving competitive results and shows how to obtain state-of-the-art performances. Our work confirms previous results reporting very close classification accuracies for Support Vector Machines (SVMs) and boosting algorithms on single-database experiments. We have proven that Linear Discriminant Analysis on a linearly selected set of features also achieves similar accuracies. We perform cross-database experiments and prove that single database experiments were optimistically biased. If enough training data and computational resources are available, SVM's gender classifiers are superior to the rest. When computational resources are scarce but there is enough data, boosting or linear approaches are adequate. Finally, if training data and computational resources are very scarce, then the linear approach is the best choice.     

Pattern selection approaches for the logical analysis of data considering the outliers and the coverage of a pattern

The logical analysis of data (LAD) is one of the most promising data mining methods developed to date for extracting knowledge from data. The key feature of the LAD is the capability of detecting hidden patterns in the data. Because patterns are basically combinations of certain attributes, they can be used to build a decision boundary for classification in the LAD by providing important information to distinguish observations in one class from those in the other. The use of patterns may result in a more stable performance in terms of being able to classify both positive and negative classes due to their robustness to measurement errors.The LAD technique, however, tends to choose too many patterns by solving a set covering problem to build a classifier; this is especially the case when outliers exist in the data set. In the set covering problem of the LAD, each observation should be covered by at least one pattern, even though the observation is an outlier. Thus, existing approaches tend to select too many patterns to cover these outliers, resulting in the problem of overfitting. Here, we propose new pattern selection approaches for LAD that take both outliers and the coverage of a pattern into account. The proposed approaches can avoid the problem of overfitting by building a sparse classifier. The performances of the proposed pattern selection approaches are compared with existing LAD approaches using several public data sets. The computational results show that the sparse classifiers built on the patterns selected by the proposed new approaches yield an improved classification performance compared to the existing approaches, especially when outliers exist in the data set.     

Local normalized linear summation kernel for fast and robust recognition

Kernel-based methods are effective for object detection and recognition. However, the computational cost when using kernel functions is high, except when using linear kernels. To realize fast and robust recognition, we apply normalized linear kernels to local regions of a recognition target, and the kernel outputs are integrated by summation. This kernel is referred to as a local normalized linear summation kernel. Here, we show that kernel-based methods that employ local normalized linear summation kernels can be computed by a linear kernel of local normalized features. Thus, the computational cost of the kernel is nearly the same as that of a linear kernel and much lower than that of radial basis function (RBF) and polynomial kernels. The effectiveness of the proposed method is evaluated in face detection and recognition problems, and we confirm that our kernel provides higher accuracy with lower computational cost than RBF and polynomial kernels. In addition, our kernel is also robust to partial occlusion and shadows on faces since it is based on the summation of local kernels.     

Patch-based active learning (PTAL) for spectral-spatial classification on hyperspectral data

Active learning (AL) has been shown to be a useful approach to improving the efficiency of the classification process for remote-sensing imagery. Current AL methods are essentially based on pixel-wise classification. In this paper, a new patch-based active learning (PTAL) framework is proposed for spectral-spatial classification on hyperspectral remote-sensing data. The method consists of two major steps. In the initialization stage, the original hyperspectral images are partitioned into overlapping patches. Then, for each patch, the spectral and spatial information as well as the label are extracted. A small set of patches is randomly selected from the data set for annotation, then a patch-based support vector machine (PTSVM) classifier is initially trained with these patches. In the second stage (close-loop stage of query and retraining), the trained PTSVM classifier is combined with one of three query methods, which are margin sampling (MS), entropy query-by-bagging (EQB), and multi-class level uncertainty (MCLU), and is subsequently employed to query the most informative samples from the candidate pool comprising the rest of the patches from the data set. The query selection cycle enables the PTSVM model to select the most informative queries for human annotation. Then, these informative queries are added to the training set. This process runs iteratively until a stopping criterion is met. Finally, the trained PTSVM is employed to patch classification. In order to compare this to pixel-based active learning (PXAL) models, the prediction label of a patch by PTSVM is transformed into a pixel-wise label of a pixel predictor to get the classification maps. Experimental results show better performance of the proposed PTAL methods on classification accuracy and computational time on three different hyperspectral data sets as compared with PXAL methods.     

Multiple kernel representation and classification of multivariate satellite-image time-series for crop mapping

Multivariate satellite-image time-series (MSITS) are a valuable source of information for a wide range of agricultural applications. Image classification, one of the main applications of this type of data, is a challenging task. It is mainly because MSITS are generated by a complex interaction among several sources of information, which are known as the factors of variation. These factors contain different information with different levels of relevance to a classification task. Thus, a proper representation of MSITS data is required in order to extract and model the most useful information from these factors for classification purpose. To this end, this article proposes three multiple kernel representations of MSITS data. These representations extract the most classification-related information from these data through combining the basis kernels constructed from different factors of variation of the MSITS data. In the proposed representations, the combination of the basis kernels was achieved by using the multiple kernel learning algorithms. The efficiency of the proposed multiple kernel representations was evaluated based both on analysing the relevance of their kernels to the classification task and their classification performances. Two different MSITS data sets composed of 10 RapidEye imageries of an agricultural area were used to evaluate the performances of the proposed methods. In addition, the classification results of both MSITS using a single kernel were considered as the baseline for comparison. The results showed an increase of up to 14% in overall accuracy of the classification maps by using the multiple kernel representations. Moreover, these particular representations for classification of time-series observations were able to handle the undesirable effects in image data such as the presence of clouds and their shadows.     

Distorted spatial warping to compress large,high-resolution rasters for remote-sensing classification

Decisions made early in the data preparation phases of remote-sensing classification projects set fundamental limits on the value to society of the final products. The often-used approach of degrading/down-sampling high-resolution (e.g. 1 m pixel size) imagery to match lower-resolution data (e.g. Landsat 30 m) through averaging or majority-rule solves the problem of aligning pixels across bands of differing resolution, but does so by forgoing all ability to detect features smaller than 30 m in addition to potentially discarding up to 99% of the information content of the high-resolution data. The alternative of up-sampling coarser-resolution data into smaller-sized synthetic pixels creates its own set of problems, including potentially enormous file sizes, likely absence of meaningful variation over small spatial scales (which may generate matrix singularities fatal to the maximum likelihood classifier), and no assurance of meaningful improvement in classification accuracy despite guaranteed increases in computational time and resource requirements. We propose a new ‘warped space compression technique’ as a variation of vector quantization that analyses local variability in the finest-resolution data available to define acceptable pixel-based neighbourhood (N × N) sizes over which data can be averaged while minimizing overall information loss. Alternative neighbourhoods are aligned so that nine smaller ones nest within each progressively larger one as 3 × 3 squares, resulting in local data compression options of 3 × 3 (ninefold), 9 × 9 (81-fold), 27 × 27 (729-fold), and 81 × 81 (6561-fold). Our transformation process to ‘warped space’ created spatially distorted images with jagged east edges and little visually discernible relationship to the original data. We achieved compressions of 48- to 138-fold in disc storage and 292- to 785-fold in actual numbers of non-null pixels through our choice of cut-off values for accepting 3 × 3, 9 × 9, 27 × 27, or 81 × 81 neighbourhoods of tolerable variability, while otherwise retaining full (1 m) resolution data in regions three cells wide by three cells high. Medium-resolution data (e.g. Landsat 30 m) can be translated into the warped space defined by high-resolution data and composited with it for conducting remote-sensing classifications. When applied to a 71-band, 55-class remote-sensing classification of a 25,500 km² region centred on the Willamette Valley of Oregon, USA, classification accuracy increased from 64.4% in normal space to 71.3% in warped space. Unsupervised classification in warped space identified several additional categories that could be appended to the 55 existing ground-truth classes, leading to further increases in accuracy. Warped-space compression may be particularly beneficial for ecological studies where it could maintain high resolution in features of interest such as riparian buffers without creating exorbitantly large data files.     

Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model image

We present a novel method of nonlinear discriminant analysis involving a set of locally linear transformations called "Locally Linear Discriminant Analysis" (LLDA). The underlying idea is that global nonlinear data structures are locally linear and local structures can be linearly aligned. Input vectors are projected into each local feature space by linear transformations found to yield locally linearly transformed classes that maximize the between-class covariance while minimizing the within-class covariance. In face recognition, linear discriminant analysis (LIDA) has been widely adopted owing to its efficiency, but it does not capture nonlinear manifolds of faces which exhibit pose variations. Conventional nonlinear classification methods based on kernels such as generalized discriminant analysis (GDA) and support vector machine (SVM) have been developed to overcome the shortcomings of the linear method, but they have the drawback of high computational cost of classification and overfitting. Our method is for multiclass nonlinear discrimination and it is computationally highly efficient as compared to GDA. The method does not suffer from overfitting by virtue of the linear base structure of the solution. A novel gradient-based learning algorithm is proposed for finding the optimal set of local linear bases. The optimization does not exhibit a local-maxima problem. The transformation functions facilitate robust face recognition in a low-dimensional subspace, under pose variations, using a single model image. The classification results are given for both synthetic and real face data.     

Stacked Autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping

Land-cover mapping is an important research topic with broad applicability in the remote-sensing domain. Machine learning algorithms such as Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest (RF) have been playing an important role in this field for many years, although deep neural networks are experiencing a resurgence of interest. In this article, we demonstrate early efforts to apply deep learning-based classification methods to large-scale land-cover mapping. Based on the Stacked Autoencoder (SAE), one of the deep learning models, we built a classification framework for large-scale remote-sensing image processing. We adjusted and optimized the model parameters based on our test samples. We compared the performance of the SAE-based approach with traditional classification algorithms including RF, SVM, and ANN with multiple performance analytics. Results show that the SAE classifier trained with an entire set of African training samples achieves an overall classification accuracy of 78.99% when assessed by test samples collected independently of training samples, which is higher than the accuracies achieved by the other three classifiers (76.03%, 77.74%, and 77.86% of RF, SVM, and ANN, respectively) based on the same set of test samples. We also demonstrated the advantages of SAE in prediction time and land-cover mapping results in this study.     

Latent linkage semantic kernels for collective classification of link data

Generally, links among objects demonstrate certain patterns and contain rich semantic clues. These important clues can be used to improve classification accuracy. However, many real-world link data may exhibit more complex regularity. For example, there may be some noisy links that carry no human editorial endorsement about semantic relationships. To effectively capture such regularity, this paper proposes latent linkage semantic kernels (LLSKs) by first introducing the linkage kernels to model the local and global dependency structure of a link graph and then applying the singular value decomposition (SVD) in the kernel-induced space. For the computational efficiency on large datasets, we also develop a block-based algorithm for LLSKs. A kernel-based contextual dependency network (KCDN) model is then presented to exploit the dependencies in a network of objects for collective classification. We provide experimental results demonstrating that the KCDN model, together with LLSKs, demonstrates relatively high robustness on the datasets with the complex link regularity, and the block-based computation method can scale well with varying sizes of the problem.     

A new difference image creation method based on deep neural networks for change detection in remote-sensing images

In this article, we propose a novel difference image (DI) creation method for unsupervised change detection in multi-temporal multi-spectral remote-sensing images based on deep learning theory. First, we apply deep belief network to learn local and high-level features from the local neighbour of a given pixel in an unsupervised manner. Second, a back propagation algorithm is improved to build a DI based on selected training samples, which can highlight the difference on changed regions and suppress the false changes on unchanged regions. Finally, we get the change trajectory map using simple clustering analysis. The proposed scheme is tested on three remote-sensing data sets. Qualitative and quantitative evaluations show its superior performance compared to the traditional pixel-level and texture-level-based approaches.     

Weighted mahalanobis distance kernels for support vector machines.

The support vector machine (SVM) has been demonstrated to be a very effective classifier in many applications, but its performance is still limited as the data distribution information is underutilized in determining the decision hyperplane. Most of the existing kernels employed in nonlinear SVMs measure the similarity between a pair of pattern images based on the Euclidean inner product or the Euclidean distance of corresponding input patterns, which ignores data distribution tendency and makes the SVM essentially a "local" classifier. In this paper, we provide a step toward a paradigm of kernels by incorporating data specific knowledge into existing kernels. We first find the data structure for each class adaptively in the input space via agglomerative hierarchical clustering (AHC), and then construct the weighted Mahalanobis distance (WMD) kernels using the detected data distribution information. In WMD kernels, the similarity between two pattern images is determined not only by the Mahalanobis distance (MD) between their corresponding input patterns but also by the sizes of the clusters they reside in. Although WMD kernels are not guaranteed to be positive definite (pd) or conditionally positive definite (cpd), satisfactory classification results can still be achieved because regularizers in SVMs with WMD kernels are empirically positive in pseudo-Euclidean (pE) spaces. Experimental results on both synthetic and real-world data sets show the effectiveness of "plugging" data structure into existing kernels.     

Low-Rank Bilinear Classification: Efficient Convex Optimization and Extensions

In pattern classification, it is needed to efficiently treat not only feature vectors but also feature matrices defined as two-way data, while preserving the two-way structure such as spatio-temporal relationships. The classifier for the feature matrix is generally formulated in a bilinear form composed of row and column weights which jointly result in a matrix weight. The rank of the matrix should be low from the viewpoint of generalization performance and computational cost. For that purpose, we propose a low-rank bilinear classifier based on the efficient convex optimization. In the proposed method, the classifier is optimized by minimizing the trace norm of the classifier (matrix) to reduce the rank without any hard constraint on it. We formulate the optimization problem in a tractable convex form and provide the procedure to solve it efficiently with the global optimum. In addition, we propose two novel extensions of the bilinear classifier in terms of multiple kernel learning and cross-modal learning. Through kernelizing the bilinear method, we naturally induce a novel multiple kernel learning. The method integrates both the inter kernels between heterogeneous reproducing kernel Hilbert spaces (RKHSs) and the ordinary kernels within respective RKHSs into a new discriminative kernel in a unified manner using the bilinear model. Besides, for cross-modal learning, we consider to map into the common space the multi-modal features which are subsequently classified in that space. We show that the projection and the classification are jointly represented by the bilinear model, and then propose the method to optimize both of them simultaneously in the bilinear framework. In the experiments on various visual classification tasks, the proposed methods exhibit favorable performances compared to the other methods.     

Deterministic multikernel extreme learning machine with fuzzy feature extraction for pattern classification

In this paper a novel multikernel deterministic extreme learning machine (ELM) and its variants are developed for classification of non-linear problems. Over a decade ELM is proved to be efficacious learning algorithms, but due to the non-deterministic and single kernel dependent feature mapping proprietary, it cannot be efficiently applied to real time classification problems that require invariant output solution. We address this problem by analytically calculation of input and hidden layer parameters for achieving the deterministic solution and exploiting the data fusion proficiency of multiple kernel learning. This investigation originates a novel deterministic ELM with single layer architecture in which kernel function is aggregation of linear combination of disparate base kernels. The weight of kernels depends upon perspicacity of problem and is empirically calculated. To further enhance the performance we utilize the capabilities of fuzzy set to find the pixel-wise coalition of face images with different classes. This handles the uncertainty involved in face recognition under varying environment condition. The pixel-wise membership value extracts the unseen information from images up to significant extent. The validity of the proposed approach is tested extensively on diverse set of face databases: databases with and without illumination variations and discrete types of kernels. The proposed algorithms achieve 100% recognition rate for Yale database, when seven and eight images per identity are considered for training. Also, the superior recognition rate is achieved for AT & T, Georgia Tech and AR databases, when compared with contemporary methods that prove the efficacy of proposed approaches in uncontrolled conditions significantly.

     

遥感图像飞机目标分类的卷积神经网络方法

目的 遥感图像飞机目标分类,利用可见光遥感图像对飞机类型进行有效区分,对提供军事作战信息有重要意义。针对该问题,目前存在一些传统机器学习方法,但这些方法需人工提取特征,且难以适应真实遥感图像的复杂背景。近年来,深度卷积神经网络方法兴起,网络能自动学习图像特征且泛化能力强,在计算机视觉各领域应用广泛。但深度卷积神经网络在遥感图像飞机分类问题上应用少见。本文旨在将深度卷积神经网络应用于遥感图像飞机目标分类问题。方法 在缺乏公开数据集的情况下,收集了真实可见光遥感图像中的8种飞机数据,按大致4∶1的比例分为训练集和测试集,并对训练集进行合理扩充。然后针对遥感图像与飞机分类的特殊性,结合深度学习卷积神经网络相关理论,有的放矢地设计了一个5层卷积神经网络。结果 首先,在逐步扩充的训练集上分别训练该卷积神经网络,并分别用同一测试集进行测试,实验表明训练集扩充有利于网络训练,测试准确率从72.4%提升至97.2%。在扩充后训练集上,分别对经典传统机器学习方法、经典卷积神经网络LeNet-5和本文设计的卷积神经网络进行训练,并在同一测试集上测试,实验表明该卷积神经网络的分类准确率高于其他两种方法,最终能在测试集上达到97.2%的准确率,其余两者准确率分别为82.3%、88.7%。结论 在少见使用深度卷积神经网络的遥感图像飞机目标分类问题上,本文设计了一个5层卷积神经网络加以应用。实验结果表明,该网络能适应图像场景,自动学习特征,分类效果良好。     

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.     

Evaluating and comparing performances of topographic correction methods based on multi-source DEMs and Landsat-8 OLI data

Topographic correction is a crucial and challenging step in interpreting optical remote-sensing images of extremely complex terrain environments due to the lack of universally suitable correction algorithms and digital elevation models (DEMs) of adequate resolution and quality. The free availability of open source global DEMs provides an unprecedented opportunity to remove topographic effects associated with remote-sensing data in remote and rugged mountain terrains. This study evaluated the performances of seven topographic correction methods including C-correction (C), Cosine C-correction (CC), Minnaert correction (M), Sun–canopy–sensor (SCS) correction (S), SCS+C-correction (SC), Teillet regression correction (TR), and the Terrain illumination correction model (TI) based on multi-source DEMs (local topographic map, Shuttle Radar Topography Mission (SRTM) DEM filled-finished A/B and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) global digital elevation model (GDEM) data sets) and Landsat-8 Operational Land Imager (OLI) data using visual and statistical evaluation strategies. Overall, these investigated topographic correction methods removed topographic effects associated with Landsat-8 OLI data to varying degrees. However, the performances of these methods generally depend on the use of different DEMs and evaluation strategies. Among these correction methods, the SCS+C-correction performed best and was less sensitive to the use of different DEMs. The performances of topographic corrections based on free and open-access DEMs were generally better than or comparable to those based on local topographic maps. In particular, the topographic correction performance was greatly improved using the SRTM filled-finished B (FFB) data set with a resampling scheme based on the average value within a 3 × 3 pixel window. Nevertheless, further quantitative investigation is needed to determine the relative importance of DEMs and evaluation strategies used to select topographic correction methods.     

COG: local decomposition for rare class analysis

Given its importance, the problem of predicting rare classes in large-scale multi-labeled data sets has attracted great attention in the literature. However, rare class analysis remains a critical challenge, because there is no natural way developed for handling imbalanced class distributions. This paper thus fills this crucial void by developing a method for classification using local clustering (COG). Specifically, for a data set with an imbalanced class distribution, we perform clustering within each large class and produce sub-classes with relatively balanced sizes. Then, we apply traditional supervised learning algorithms, such as support vector machines (SVMs), for classification. Along this line, we explore key properties of local clustering for a better understanding of the effect of COG on rare class analysis. Also, we provide a systematic analysis of time and space complexity of the COG method. Indeed, the experimental results on various real-world data sets show that COG produces significantly higher prediction accuracies on rare classes than state-of-the-art methods and the COG scheme can greatly improve the computational performance of SVMs. Furthermore, we show that COG can also improve the performances of traditional supervised learning algorithms on data sets with balanced class distributions. Finally, as two case studies, we have applied COG for two real-world applications: credit card fraud detection and network intrusion detection.     

Land-cover classification using multi-temporal GF-1 wide field view data

ABSTRACT

Vegetation is an important land-cover type and its growth characteristics have potential for improving land-cover classification accuracy using remote-sensing data. However, due to lack of suitable remote-sensing data, temporal features are difficult to acquire for high spatial resolution land-cover classification. Several studies have extracted temporal features by fusing time-series Moderate Resolution Imaging Spectroradiometer data and Landsat data. Nevertheless, this method needs assumption of no land-cover change occurring during the period of blended data and the fusion results also present certain errors influencing temporal features extraction. Therefore, time-series high spatial resolution data from a single sensor are ideal for land-cover classification using temporal features. The Chinese GF-1 satellite wide field view (WFV) sensor has realized the ability of acquiring multispectral data with decametric spatial resolution, high temporal resolution and wide coverage, which contain abundant temporal information for improving land-cover classification accuracy. Therefore, it is of important significance to investigate the performance of GF-1 WFV data on land-cover classification. Time-series GF-1 WFV data covering the vegetation growth period were collected and temporal features reflecting the dynamic change characteristics of ground-objects were extracted. Then, Support Vector Machine classifier was used to land-cover classification based on the spectral features and their combination with temporal features. The validation results indicated that temporal features could effectively reflect the growth characteristics of different vegetation and finally improved classification accuracy of approximately 7%, reaching 92.89% with vegetation type identification accuracy greatly improved. The study confirmed that GF-1 WFV data had good performances on land-cover classification, which could provide reliable high spatial resolution land-cover data for related applications.     

A fast algorithm for the nearest-neighbor classifier

A fast algorithm that finds the nearest neighbor (NN) of an unknown sample from a design set of labeled samples is proposed. This algorithm requires a quite moderate preprocessing effort and a rather excessive storage, but it accomplishes substantial computational savings during classification. The performance of the algorithm is described and compared to the performance of the conventional one. Results on simulated data are provided to illustrate the computational savings that may be achieved using this fast algorithm