作者：
Ulas BagciLi BaiCMIAG
School of Computer Science and IT University of Nottingham UK
A novel method for classification of magnetic resonance brain images is presented in this paper. We construct a computational framework for discriminative image feature subspaces. Magnetic resonance images of patients...
详细信息
A novel method for classification of magnetic resonance brain images is presented in this paper. We construct a computational framework for discriminative image feature subspaces. Magnetic resonance images of patients in Alzheimer's disease and normal brain MR images are classified with support vector machines. The framework for the novel method bases on the extraction of gabor features from 2D-magnetic resonance images in different scales and orientations. Experiments show that Gabor wavelets can significantly improve classification performance with respect to other popular approaches reported recently in the literature. Combination of gabor features in 3 scales and 8 orientations give 100% classification performance. Experimental results with promising improvements and comparison to related studies are provided.
A camera or display usually has a smaller dynamic range than the human eye. For this reason, objects that call be detected by the naked eye may not be visible in recorded images. Lighting is here an important factor;i...
详细信息
ISBN:
(纸本)9780819466976
A camera or display usually has a smaller dynamic range than the human eye. For this reason, objects that call be detected by the naked eye may not be visible in recorded images. Lighting is here an important factor;improper local lighting impairs visibility of details or even entire objects. When a human is observing a scene with different kinds of lighting, such as shadows, he will need to see details in both the dark and light parts of the scene. For grey value images such as IR imagery, algorithms have been developed in which the local contrast of the image is enhanced using local adaptive techniques. In this paper, we present how such algorithms can be adapted so that details in color images are enhanced while color information is retained. We propose to apply the contrast enhancement on color images by applying a grey value contrast enhancement algorithm to the luminance channel of the color signal. The color coordinates of the signal will remain the same. Care is taken that the saturation change is not too high. Gamut mapping is performed so that the output can be displayed on a monitor. The proposed technique can for instance be used by operators monitoring movements of people in order to detect suspicious behavior. To do this effectively, specific individuals should both be easy to recognize and track. This requires optimal local contrast, and is sometimes much helped by color when tracking a person with colored clothes. In such applications, enhanced local contrast in color images leads to more effective monitoring.
The proceedings contain 18 papers. The topics discussed include: model based compression of the calibration matrix for hyperspectral imaging systems;optimization of a lossless object-based compression embedded on GAIA...
详细信息
ISBN:
(纸本)9780819468482
The proceedings contain 18 papers. The topics discussed include: model based compression of the calibration matrix for hyperspectral imaging systems;optimization of a lossless object-based compression embedded on GAIA a next-generation space telescope;design of multichannel filter banks for subband coding of audio signals using multirate signalprocessing techniques;the optimum running-type approximation for time-limited worst-case measures of error based on Fredholm integral equation using Pincherle-Goursat kernel;adaptive model and neural network based watermark identification;compressed versus uncompressed domain video watermarking;generation of lattice independent vector sets for pattern recognition applications;and the validity of pyramid k-means clustering.
With hyperspectral pushbroom imaging spectrometers on Earth observation satellites it is possible to detect and identify dedicated ground pixels by their spectral signature. Conventional time consuming on-ground proce...
详细信息
ISBN:
(纸本)9780819467133
With hyperspectral pushbroom imaging spectrometers on Earth observation satellites it is possible to detect and identify dedicated ground pixels by their spectral signature. Conventional time consuming on-ground processing performs this selection by processing the measured hyperspectral data cube of the image. The Imaging Spectral Signature Instrument (ISSI) concept combines an optical on-board processing of the hyperspectral data cube with a thresholding algorithm, to identify pixels with a pre-defined and programmable spectral signature, such as water, forest and minerals, in the ground swath. The Imaging Spectral Signature Instrument consists of an imaging telescope, which images an object line on the entrance slit of a first imaging spectrometer, which disperses each pixel of the object line into its spectral content and images the hyperspectral image on the spatial light modulator. This spatial light modulator will be programmed with a spatial transmission or reflection behavior, which is constant along the spatial pixels and along the spectral pixels identical to a filter vector that corresponds to the spectral signature of the searched specific feature. A second inverted spectrometer reimages the by the first spectrometer dispersed and by the spatial light modulator transmitted or reflected flux into a line of pixels. In case the spectral content of the ground scene is identical to the searched signature, the flux traversing or reflecting the spatial light modulator will be maximum. The related pixel can be identified in the final image as a high signal by a threshold discriminator. A component test setup consists of an imaging lens, two Imspector(TM) spectrographs, a spatial light modulator, which is a programmable transmissible liquid crystal display and a CCD sensor as a detector. A mathematical model was developed for the instrument and its performance was evaluated in order to compare different concept variations. All components were measured and charact
Distributed video coding is a new paradigm for video compression. Practical distributed video coding are promising solutions for emerging applications. Nevertheless, more study and exploration is needed. This paper pr...
详细信息
During operation of present fusion devices, the Plasma Facing Components (PFCs) are submitted to large heat fluxes within a range of 10-20 MW/m2. Understanding and preventing overheating of these components during lon...
详细信息
In order to study the SAR image of the ocean wave and the wave modulation of the RCS (radar cross section), the numerical simulation has been done by using the velocity bunching (VB) model with various parameters. The...
详细信息
ISBN:
(纸本)9780819469502
In order to study the SAR image of the ocean wave and the wave modulation of the RCS (radar cross section), the numerical simulation has been done by using the velocity bunching (VB) model with various parameters. The SAR image has a migration in the azimuthal direction for the wave velocity and the process of the nonlinear imaging. The way is an available method of studying the ocean wave image by SAR.
In this paper, we propose a method of improving imperceptibility and robustness of a wavelet-based watermark by finding the optimal wavelet transform used for image decomposition required for watermark embedding. Our ...
详细信息
ISBN:
(纸本)9781424407781;1424407796
In this paper, we propose a method of improving imperceptibility and robustness of a wavelet-based watermark by finding the optimal wavelet transform used for image decomposition required for watermark embedding. Our approach can be easily generalized for enhancing watermarking performance of any wavelet-based technique as they usually use predefined (not necessarily optimal) wavelets. We measured imperceptibility by PSNR and considered robustness to filtering or JPEG compression. To find the optimal wavelet, we used both local and global (genetic algorithm) optimizers. We applied our method to a recent wavelet-based watermarking scheme and achieved better watermarking properties both in terms of imperceptibility and robustness.
Widely used in imageprocessing, wavelets seem to be a promising versatile tool for the high frequency surface wave radar (HFSWR). HFSWR is based on the ability of HF waves (3 MHz to 30 MHz) to propagate along the ear...
详细信息
Widely used in imageprocessing, wavelets seem to be a promising versatile tool for the high frequency surface wave radar (HFSWR). HFSWR is based on the ability of HF waves (3 MHz to 30 MHz) to propagate along the earth curvature. HFSWR can detect targets up to few hundred kilometers beyond the horizon. The two main applications of the HFSWR are the maritime surveillance of the exclusive economic zone (EEZ) and the remote sensing of the sea. Beside the classical noise which affects all radar signals, the detection capabilities of HFSWR suffer from two limitations: the sea clutter and the ionospheric clutter which are target masks. However sea clutter can be used to perform remote sensing of the sea. In this paper we are studying how wavelets may contribute to the improvement of radar signalprocessing. We consider general de-noising feature for radar signals, we carry out a wavelet-based improvement of remote sensing of oceanographic parameters and we show the first results of a wavelet-based processing for ionospheric clutter mitigation.
Emerging multi-core processors are able to accelerate medical imaging applications by exploiting the parallelism available in their algorithms. We have implemented a mutual-information-based 3D linear registration alg...
详细信息
ISBN:
(纸本)9781424410163
Emerging multi-core processors are able to accelerate medical imaging applications by exploiting the parallelism available in their algorithms. We have implemented a mutual-information-based 3D linear registration algorithm on the Cell Broadband Engine (TM) processor. By exploiting the highly parallel architecture and its high memory bandwidth, our implementation with two CBE processors can register a pair of 256x256x30 3D images in one second. This implementation is significantly faster than a conventional one on a traditional microprocessor or even faster than a previously reported custom-hardware implementation. In addition to parallelizing the code for multiple cores and organizing the data structure for reducing the amount of the memory traffic, it is also critical to optimize the code for the SIMD pipeline structure. We note that code optimization for the SIMD pipeline alone results in a 4.2x-8.7x acceleration for the computation of small kernels. Further, SIMD optimization alone results in a 4.5x end-end application speedup.
暂无评论