For more accurate classification of earthquake-induced damaged regions, a high-resolution satellite image is required to extract textural and spatial features of the damage. In addition to using textural features, spectral features may improve the identification of the damaged regions. Earthquake-induced damage that occurred in the city of Bam in Iran was identified by a nonparametric and nonlinear classifier called support vector selection and adaptation (SVSA) using both the textural and the spectral features. SVSA can achieve the performance of nonlinear support vector machines (NSVM) without the need for a kernel function. Our aim is to show the effectiveness of the SVSA algorithm compared with the linear support vector machines, NSVM, and K-nearest neighbor (KNN) methods in terms of classification accuracy when using the textural features. A nonparametric weighted feature extraction was also implemented before the classification in order to increase the classification accuracy further by assigning a different weight to the textural feature. The results indicate that SVSA is significantly better than the linear SVM (LSVM) and KNN classifiers, and it is quite competitive with NSVM in terms of damage detection accuracy.
The main objective of classification is to partition the surface materials into non-overlapping regions by using some decision rules. For supervised classification, the hyperspectral imagery (HSI) is compared with the reflectance spectra of the material containing similar spectral characteristic. As being a spectral similarity based classification method, prediction of different level of upper and lower spectral boundaries of all classes spectral signatures across spectral bands constitutes the basic principles of the Multi-Scale Vector Tunnel Algorithm (MS-VTA) classification algorithm. The vector tunnel (VT) scaling parameters obtained from means and standard deviations of the class references are used. In this study, MS-VT method is improved and a spectral similarity based technique referred to as Weighted Chebyshev Distance (WCD) method for the supervised classification of HSI is introduced. This is also shown to be equivalent to the use of the WCD in which the weights are chosen as an inverse power of the standard deviation per spectral band. The use of WCD measures in terms of the inverse power of standard deviations and optimization of power parameter constitute the most important side of the study. The algorithms are trained with the same kinds of training sets, and their performances are calculated for the power of the standard deviation. During these studies, various levels of the power parameters are evaluated based on the efficiency of the algorithms for choosing the best values of the weights.
In this study, targets and nontargets in a hyperspectral image are characterized in terms of their spectral features. Target detection problem is considered as a two-class classification problem. For this purpose, a vector tunnel algorithm (VTA) is proposed. The vector tunnel is characterized only by the target class information. Then, this method is compared with Euclidean Distance (ED), Spectral Angle Map (SAM) and Support Vector Machine (SVM) algorithms. To obtain the training data belonging to target class, the training regions are selected randomly. After determination of the parameters of the algorithms with the training set, detection procedures are accomplished at each pixel as target or background. Consequently, detection results are displayed as thematic maps. The algorithms are trained with the same training sets, and their comparative performances are tested under various cases. During these studies, various levels of thresholds are evaluated based on the efficiency of the algorithms by means of Receiver Operating Characteristic Curves (ROC) as well as visually.
We describe a method of using femtosecond laser for direct writing of volume Fresnel zone plates with high diffraction
efficiency. A volume zone plate consists of a number of Fresnel zone plate layers designed to focus light coherently to a
single spot. We fabricated both low numerical aperture (NA) and high NA volume zone plates, resulting in a significant
increase in overall diffraction efficiency. The performance of the volume zone plate is also simulated using the Hankel
transform beam propagation method (Hankel BPM). The results show an excellent agreement with the scalar diffraction
theory and the experimental results. The numerical method allows more comprehensive studies of the VFZP parameters
to achieve higher diffraction efficiency.
In this paper, we present a new fusion algorithm based on a multidecomposition approach with the DFT based symmetric, zero-phase, nonoverlapping digital filter bank representation. The DFT of the signal is separated into two parts leading to the low and high −pass components then decimated by two to obtain subband signals. The original signal may be recovered by interpolating the subband signals, computing their inverse DFT and summing the results. In the proposed image fusion algorithm, two or more source images are decomposed into subbands by DFT based digital filters. The detail and approximation subband coefficients are modified according to their magnitudes and mean values, respectively. Then, the modified subbands are combined in the subband domain. Finally, the fused image is obtained by the inverse transform.
The experimental investigation of a novel technical approach for formation of security diffraction structures with high degree of protection based on a combined optical and electron-beam lithography techniques are presented.
In this study, we investigate an unsupervised learning algorithm for the segmentation of remote sensing images in which the optimum number of clusters is automatically estimated, and the clustering quality is checked. The computational load is also reduced as compared to a single stage algorithm. The algorithm has two stages. At the first stage of the algorithm, the self-organizing map was used to obtain a large number of prototype clusters. At the second stage, these prototype clusters were further clustered with the K-means clustering algorithm to obtain the final clusters. A clustering validity checking method, Davies-Bouldin validity checking index, was used in the second stage of the algorithm to estimate the optimal number of clusters in the data set.
Electron-beam and holographic recording of diffraction gratings was processed in the layers of poly-N-poxypropylcarbazole (PEPC) and co-polymers of carbazolylalkylmethacrylate with octylmethacrylate (CAM:OMA) containing additions of CHI3. The dependence of the diffraction efficiency of planar gratings on the recording current was studied. The influence of post-effect and storage in the dark on the diffraction efficiency is considered. By chemical development technique the reflecting relief diffraction gratings are obtained with the diffraction efficiency of 25-30%.
A rotation invariant binary circular filter has been developed for optical pattern recognition. The filter is generated using an iterative numerical optimization method. The optimization is based on the genetic algorithm, which fits very well in optical systems due to its parallel nature. The features of the genetic algorithm provide a highly efficient and rapid learning process. During training, the parameters of a binary circular filter are selected to maximize the distinction between the target and other expected objects in the image. The genetic algorithm is searching through the complete filter space for the global solution, this is the filter with the best performance. These iteratively designed filters are good discriminators because they utilize all the spatial visual information about the target. The design of the rotation invariant filter does not require any a priori information about the target image. The rotation invariant filters are designed as binary circular filters to be suitable for real- time applications, when combined with spatial light modulators.
An adaptive approach to edge detection using the transform domain and bandpass filtering is discussed. The method is also extended to 3-D and shown to yield better edge maps. The discrete symmetric cosine transform (DSCT) is shown to be the best transform for accurate edge detection. The theory is first discussed in 1-D. Then, the adaptive algorithm utilizing both the gradient and the Laplacian information is developed in 2-D and 3-D. Computer simulations with regular scenes and magnetic resonance imaging images are provided. The extension of the method to 3-D leads to improved noise immunity and better edge contours.
Artificial neural net models have been studied for many years in the hope of achieving human- like performance in the fields of speech, image recognition and pattern recognition. For high performance and for controlling the size of the network, the input information must be preprocessed before being fed into the neural network. In this paper, a probabilistic spectral feature extraction technique (PSFET) with multiview spectral representations and its applications are described. During training and testing, the PSFET allows efficient extraction of useful information in addition to generating an input vector size for best classification performance by the following neural network. Experimental results indicate that the performance of the neural network increases in classification accuracy when PSFET is used at the input. The network also generalizes better.
The blockwise transform edge detection method consists of segmenting the image into a number of small blocks, with neighboring blocks overlapping slightly; transforming each block by a fast transform; multiplying the transform coefficients of each block by a bandpass mask; inverse transforming the modified transform coefficients; detecting zero crossings and deciding an edge according to a thresholding scheme. Simulation results with the blockwise transform edge detection method in comparison to other bandpass filtering techniques indicate that higher performance is achieved with the new technique on the average. This is believed to result from the use of blockwise generalized filtering with appropriate transforms rather than linear convolutional filtering, as in other bandpass filtering techniques. The new method also has less computational complexity, and is well-suited to parallel processing.
Blockwise transform image enhancement techniques are discussed. It is shown that the best transforms for transform image coding, namely, the scrambled real discrete Fourier transform, the discrete cosine transform, and the discrete cosine-III transform, are also the best for image enhancement. Three techniques of enhancement discussed in detail are alpha- rooting, modified unsharp masking, and filtering motivated by the human visual system response (HVS). With proper modifications, it is observed that unsharp masking and HVS- motivated filtering without nonlinearities are basically equivalent. Block effects are completely removed by using an overlap-save technique in addition to the best transform.
Blockwise transform image enhancement techniques are discussed. Previously, transform image enhancement has usually been based on the discrete Fourier transform (DFT) applied to the whole image. Two major drawbacks with the DFT are high complexity of implementation involving complex multiplications and additions, with intermediate results being complex numbers, and the creation of severe block effects if image enhancement is done blockwise. In addition, the quality of enhancement is not very satisfactory. It is shown that the best transforms for transform image coding, namely, the scrambled real discrete Fourier transform, the discrete cosine transform, and the discrete cosine-III transform, are also the best for image enhancement. Three techniques of enhancement discussed in detail are alpha-rooting, modified unsharp masking, and filtering motivated by the human visual system response (HVS). With proper modifications, it is observed that unsharp masking and HVS-motivated filtering without nonlinearities are basically equivalent. Block effects are completely removed by using an overlap-save technique in addition to the best transform.
Symmetric nonlinear matched filters (SNMFs) involve the transformation of the signal spectrum and the filter transfer function through pointwise nonlinearities before they are multiplied in the transform domain. The resulting system is analogous to a multistage neural network. The experimental and theoretical results discussed indicate that SNMFs
hold considerable potential to achieve a high power of discrimination and resolution and large SNR. The statistical analysis of a particular SNMF in the two-class problem indicates that the performance coefficient of the SNMF is about four times larger than the performance coefficient of the classical matched filter. In terms of resolving closeby signals, there seems to be no limit to the achievable resolution. However, artifacts should be carefully monitored.
A new fast approach to computer-generated holography for 3-D objects points in arbitrary positions in 3-D space is presented. The approach is based on fast computation of weighted zero-crossings their accumulation and thresholding to achieve a coded hologram to be physically generated. 1.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.