Although FPGA technology offers the potential of designing high performance systems at low cost for a wide range of applications, its programming model is prohibitively low level requiring either a dedicated FPGA-expe...
详细信息
ISBN:
(纸本)0780367251
Although FPGA technology offers the potential of designing high performance systems at low cost for a wide range of applications, its programming model is prohibitively low level requiring either a dedicated FPGA-experienced programmer or basics digital design knowledge. To allow a signal/imageprocessing end-user to benefit from this kind of devices, the level of design abstraction needs to be raised, even beyond a Hardware Description Language level (eg VHDL). This approach will help the application developer to focus on signal/imageprocessing algorithms rather than on low-level designs and implementations. This paper arms to present a framework for an FPGA-based coprocessor dedicated to Discrete wavelet Transforms (DWT). The proposed approach will help the end-user to generate FPGA configurations for DWT at a highest level without any knowledge of the low-level design styles and architectures.
An algorithm for multidimensional nonlinear registration is proposed. The deformation field between two elastic bodies is represented by a multi-resolution separable wavelet. Using a progressive approach that reduces ...
详细信息
ISBN:
(纸本)0819450804
An algorithm for multidimensional nonlinear registration is proposed. The deformation field between two elastic bodies is represented by a multi-resolution separable wavelet. Using a progressive approach that reduces algorithm complexity the registration parameters are recovered in a coarse to fine order. A custom wavelet that approximates threefold orthogonality is developed. The performance of the algorithm is evaluated by the alignment of sections from mouse brains. The wavelet registration algorithm demonstrated on average fourfold improvement in section alignment over linear alignment.
In tomographic medical devices such as SPELT or PET cameras, image reconstruction is an unstable inverse problem, due to the presence of additive noise. A new family of regularization methods for reconstruction, based...
详细信息
ISBN:
(纸本)0819441929
In tomographic medical devices such as SPELT or PET cameras, image reconstruction is an unstable inverse problem, due to the presence of additive noise. A new family of regularization methods for reconstruction, based on a thresholding procedure in wavelet and wavelet packet decompositions, is studied. This approach is based on the fact that the decompositions provide a near-diagonalization of the inverse Radon transform and of the prior information on medical images. An optimal wavelet packet decomposition is adaptively chosen for the specific image to be restored. Corresponding algorithms have been developed for both 2-D and full 3-D reconstruction. These procedures are fast, non-iterative, flexible, and their performance outperforms Filtered Back-Projection and iterative procedures such as OS-EM.
In this paper a three dimensional discrete wavelet transform (3D-DWT) based feature extraction for the classification of facial hyperspectral imagery is proposed. Most of the relevant work processes 2-D slices of hype...
详细信息
ISBN:
(纸本)9781467389105
In this paper a three dimensional discrete wavelet transform (3D-DWT) based feature extraction for the classification of facial hyperspectral imagery is proposed. Most of the relevant work processes 2-D slices of hyperspectral images separately;3D-DWT has the advantage of extracting the spatial and spectral information simultaneously. Decomposing an image into a set of spatial-spectral components is an important characteristic of 3D-DWT. We propose two methods for 3D-DWT feature extraction, namely, 3D subband energy (3D-SE) and 3D subband overlapping cube (3D-SOC). Extracted feature vector datasets are processed through k-NN classifier and their performance is evaluated under three different testing scenarios. The experimental results revealed that hyperspectral face recognition with proposed 3D-DWT methods substantially outperforms the methods used in spatial-spectral classification reported in the literature.
A novel method for simultaneous registration and segmentation is developed. The method is designed to register two similar images while a region with significant difference is adaptively segmented. This is achieved by...
详细信息
ISBN:
(纸本)0819432997
A novel method for simultaneous registration and segmentation is developed. The method is designed to register two similar images while a region with significant difference is adaptively segmented. This is achieved by minimization of a non-linear functional that models the statistical properties of the subtraction of the two images. Minimization is performed in the wavelet domain by a coarse-to-fine approach to yield a mapping that yields the registration and the boundary that yields the segmentation. The new method was applied to the registration of the left and the right lung regions in chest radiographs for extraction of lung nodules while the normal anatomic structures such as ribs are removed. A preliminary result shows that our method is very effective in reducing the number of false detections obtained with our computer-aided diagnosis scheme for detection of lung nodules in chest radiographs.
It is apparent that there is no future for telemedicine without signal compression. In fact the very idea of sending X-rays and other medical images and information electronically could not have brought up without adv...
详细信息
ISBN:
(纸本)0780376129
It is apparent that there is no future for telemedicine without signal compression. In fact the very idea of sending X-rays and other medical images and information electronically could not have brought up without advances in compression technology over the past two decades. Leading compression standards, such as JPEG/MPEG [1] and those based on Hadamard matrix [2], have been successfully implemented in numerous signal/image coding/decoding applications ranging from satellites to medical imaging. On the other hand, ever-increasing requirements in signal recognition and transmission, particularly related to telemedicine, have challenged the researchers to develop new compression techniques better suited for each practical situation. The wavelet technology emerged as one of the most promising tools in that direction. Both wavelet and Hadamard transform based algorithms provide excellent quality biomedical signal reconstruction at high compression ratios and can be implemented in real-time on existing microprocessors. The objective. of this study is to construct hybrid Hadamard-wavelet transforms and to develop corresponding optimal zonal sampling methods with the use of such transforms. The designed hybrid transforms can be useful in various specific signalprocessingapplications where combining properties of Hadamard and wavelet transforms may be of particular benefit.
The paper presents further research on neural engineering that focuses on the classification of emotional, mental, physical and no stress through the use of Electroencephalography (EEG) signal analysis. Stress is one ...
详细信息
ISBN:
(纸本)9781509055593
The paper presents further research on neural engineering that focuses on the classification of emotional, mental, physical and no stress through the use of Electroencephalography (EEG) signal analysis. Stress is one of the leading causes of several health-related problems and diseases. Therefore, it becomes necessary for people to monitor their stress. The human body acquires and responds to stress in different ways resulting to two classifications of stress namely, mental and emotional stress. Traditional methods in classifying stress such as through questionnaires and self-assessment tests are said to be subjective since they rely on personal judgment. Thus, in this study, stress is classified through an objective measure which is EEG signal analysis. The features of the EEG recordings are then pre-processed, extracted, and selected using Discrete wavelet Transform (DWT). These features are then ussed as inputs to classify stress using Artificial Neural Network (ANN) and validated using K-fold Cross Validation Method. Lastly, the results from the software assisted method is compared to the results of the traditional method.
This paper presents the results of the development of an adaptive method for reducing signal-dependent noise, such as speckle noise, in a coherent imaging system signal, such as in medical ultrasound imaging. Speckle ...
详细信息
ISBN:
(纸本)0819425915
This paper presents the results of the development of an adaptive method for reducing signal-dependent noise, such as speckle noise, in a coherent imaging system signal, such as in medical ultrasound imaging. Speckle noise is filtered using nonlinear adaptive thresholding of received echo wavelet transform coefficients. Filtering speckle noise in ultrasound imaging enhances the resultant image by improving the signal-to-noise ratio. This method includes the steps of transforming the imaging system signal using discrete wavelet transformation to provide wavelet transform coefficients for each of the wavelet scales having different levels of resolution ranging from a finest wavelet scale to a coarsest wavelet scale;deleting the wavelet transform coefficients representing the finest wavelet scale;identifying, for each wavelet scale other than the finest wavelet scale, which of the wavelet transform coefficients are related to noise and which are related to a true signal through the use of adaptive non-linear thresholding;selecting those wavelet transform coefficients which are identified as being related to a true signal;and inverse transforming the selected wavelet transform coefficients using an inverse discrete wavelet transformation to provide an enhanced true signal with reduced noise. This method is shown to improve the signal-to-noise ratio by 2-5 dB in digital ultrasound images of real and phantom objects for a range of thresholding levels while preserving the contrast differences between regions and maintaining feature edges. The filtered images have an enhanced apparent contrast resulting from the reduction in the speckle noise and the preservation of the contrast differences.
In a multimedia framework, digital image sequences (videos) are by far the most demanding as far as storage, search, browsing and retrieval requirements are concerned. In order to reduce the computational burden assoc...
详细信息
ISBN:
(纸本)0819432997
In a multimedia framework, digital image sequences (videos) are by far the most demanding as far as storage, search, browsing and retrieval requirements are concerned. In order to reduce the computational burden associated to video browsing and retrieval, a video sequence is usually decomposed into several scenes (shots) and each of them is characterized by means of some key frames. The proper selection of these key frames, i.e. the most representative frames in the scene, is of paramount importance for computational efficiency. In this contribution a novel key frame extraction technique based on the wavelet analysis is presented. Experimental results show the capability of the proposed algorithm to select key frames properly summarizing the shot.
image mosaic combines two or more images. It has found many applications in computer vision, imageprocessing, and computer graphics. A common goal of the problem is to join two or more images such that there is an in...
详细信息
ISBN:
(纸本)0780367251
image mosaic combines two or more images. It has found many applications in computer vision, imageprocessing, and computer graphics. A common goal of the problem is to join two or more images such that there is an invisible boundary around the seam line and the mosaic image is as little distortion from the original images as possible. We propose a new image mosaic method by wavelet multiresolution analysis and variational calculus. We first project the images into wavelet spaces. The projected images at each wavelet space are then blended. In our approach, variational calculus techniques are applied to balance the quality between the smoothness around the seam line and the fidelity of the combined image relative to the original images in image blending. A mosaic image is finally obtained by summing the blended images at the wavelet spaces. Experimental results based on our method are demonstrated.
暂无评论