Spectral Angle Mapper (SAM) model has got wide applications in hyperspectral remotesensing (RS) information processing. But Spectral Angle couldn't achieve satisfied performance in some cases because of its sensi...
详细信息
Spectral Angle Mapper (SAM) model has got wide applications in hyperspectral remotesensing (RS) information processing. But Spectral Angle couldn't achieve satisfied performance in some cases because of its sensitivity to noises and uncertainty. Based on the analysis to traditional SAM algorithm, four types of errors and their impacts to spectral angle are investigated. In order to reduce the impacts of above errors, some improved algorithms are proposed and experimented. The first improved algorithm is grouping spectral angle algorithm. In this new algorithm all bands are divided into two sets by odd and even bands, that means two additional sub-vectors are created in addition to the original spectral vector. So three spectral angles will be computed and the minimum of three indexes is used as final index. The second improved algorithm is normalized spectral angle. In this way spectral angle is computed to the normalized vectors of two original vectors. Two approaches are used to normalize the spectral vector, and spectral angle is computed to the normalized vectors. This algorithm is able to decrease the impacts of random errors. The third algorithm is intersected spectral angle. Spectral angle is calculated by a spectral displacement strategy in this approach. That means a given displacement to change the corresponding bands of two spectral vectors is used and a spectral angle to the displaced vectors will be got. By this displacement strategy the impacts of band offset is reduced. Finally some experiments are used to test those improved algorithms. It proves that those new approaches can reduce and control the errors and improve the precision and reliability of similarity measure.
We present a textural kernel for "support vector machines" classification applied to remotesensing problems. SVMs constitute a method of supervised classification well adapted to deal with data of high dime...
详细信息
We present a textural kernel for "support vector machines" classification applied to remotesensing problems. SVMs constitute a method of supervised classification well adapted to deal with data of high dimension, such as images. We introduce kernel functions in order to favor the distinction between our class of interest and the other classes: it gives information of similarity. In our case this similarity is based on radiometric and textural characteristics. One of the main difficulties is to elaborate textural parameters which are relevant and characterize as well as possible the joint distribution of a set of connected pixels. We apply this method to remotesensing problems: the detection of forest fires and the extraction of urban areas in high resolution images.
This paper revises the theoretical background for upcoming dual-channel Radar satellite missions to monitor traffic from space. As it is well-known, an object moving with a velocity deviating from the assumptions inco...
详细信息
Automating the process of postmortem identification of individuals using dental records is receiving increased attention. In developing a research prototype of an Automated Dental Identification System (ADIS), researc...
详细信息
ISBN:
(纸本)0975339346
Automating the process of postmortem identification of individuals using dental records is receiving increased attention. In developing a research prototype of an Automated Dental Identification System (ADIS), research teams from multiple institutes collaborated with forensic experts from the US Federal Bureau of Investigation (FBI) to identify the functional requirements of ADIS. A multitude of digital imageprocessing and patternrecognition techniques were developed to meet the requirements of the constituent components of ADIS. In this paper we present a web-based environment that integrates ADIS components and provides a unified web interface to ADIS (webADIS), thus facilitating remote access to ADIS and also allowing for the choice among multiple possible realizations of some components as well as alternative identification strategies.
The performance of a statistical imageprocessing system depends in large part on the accuracy of the probabilistic model used. This paper presents a robust probabilistic mixture model based on the Dirichlet distribut...
详细信息
The performance of a statistical imageprocessing system depends in large part on the accuracy of the probabilistic model used. This paper presents a robust probabilistic mixture model based on the Dirichlet distribution. An unsupervised algorithm based on MML for learning this mixture is given, too. Experimental results involve shadows modeling and its application to shadows detection in images.
The growing neural gas (GNG) patternrecognition algorithm is an unsupervised algorithm which inserts nodes into the state space of the training data. Observations of the behavior of the algorithm lead to the hypothes...
详细信息
The growing neural gas (GNG) patternrecognition algorithm is an unsupervised algorithm which inserts nodes into the state space of the training data. Observations of the behavior of the algorithm lead to the hypothesis that this method may be an efficient pre-classification clustering algorithm for data in highly discrete state spaces, as in satellite remotesensingimages. The GNG algorithm was used to train a network using a Landsat image from Wyoming. The initial results of this investigation were extremely positive. The image derived from the trained GNG network is difficult to distinguish from the source image. Preliminary statistical results also indicate a high degree of correlation between the source and resultant images.
Fuzzy Models and Algorithms for patternrecognition and imageprocessing presents a comprehensive introduction of the use of fuzzy models in patternrecognition and selected topics in imageprocessing and computer vis...
详细信息
ISBN:
(纸本)9780387245157
Fuzzy Models and Algorithms for patternrecognition and imageprocessing presents a comprehensive introduction of the use of fuzzy models in patternrecognition and selected topics in imageprocessing and computer vision. Unique to this volume in the Kluwer Handbooks of Fuzzy Sets Series is the fact that this book was written in its entirety by its four authors. A single notation, presentation style, and purpose are used throughout. The result is an extensive unified treatment of many fuzzy models for patternrecognition. The main topics are clustering and classifier design, with extensive material on feature analysis relational clustering, imageprocessing and computer vision. Also included are numerous figures, images and numerical examples that illustrate the use of various models involving applications in medicine, character and word recognition, remotesensing, military image analysis, and industrial engineering.
This paper imported wavelet analysis and wavelet descriptor into the building recognition of high resolution satellite remotesensingimage, and brought forward the building recognition method based on wavelet descrip...
详细信息
This paper imported wavelet analysis and wavelet descriptor into the building recognition of high resolution satellite remotesensingimage, and brought forward the building recognition method based on wavelet descriptor in theory: firstly used wavelet analysis to do image segmentation in order to wipe off the large blocks of vegetation area in the image, then used dyadic wavelet to extract the edge, and used coordinate wavelet descriptor to describe the detected building contour, after that, computed the affine invariants to recognize the buildings, at last employed shadow validating to ascertain if the detected edge was the real building edge. This paper also constructed the building recognitionpattern database, and used a QuickBird RS image of Peking University to do the experiment and the experimental result proved the feasibility of the method.
The vast majority of the published skew estimation methods for scanned document images are for textual documents. These methods are based on the principle that the skew angles can be derived from the presence of the o...
详细信息
We present a new approach based on discriminant analysis to map a high dimensional image feature space onto a subspace which has the following advantages: 1) each dimension corresponds to a semantic likelihood, 2) an ...
详细信息
We present a new approach based on discriminant analysis to map a high dimensional image feature space onto a subspace which has the following advantages: 1) each dimension corresponds to a semantic likelihood, 2) an efficient and simple multiclass classifier is proposed and 3) it is low dimensional. This mapping is learnt from a given set of labeled images with a class groundtruth. In the new space a classifier is naturally derived which performs as well as a linear SVM. We show that projecting images in this new space provides a database browsing tool which is meaningful to the user. Results are presented on a remotesensing database with eight classes, made available online. The output semantic space is a low dimensional feature space which opens perspectives for other recognition tasks.
暂无评论