Integrating high spatial resolution of functional magnetic resonance imaging (fMRI) and high temporal resolution of electroencephalogram (EEG) is promising in simultaneous EEG and fMRI analysis, especially for epilept...
详细信息
Integrating high spatial resolution of functional magnetic resonance imaging (fMRI) and high temporal resolution of electroencephalogram (EEG) is promising in simultaneous EEG and fMRI analysis, especially for epileptic patients. The EEG recorded inside an MR scanner is interfered with MR artifacts. In this article, we propose new artifact reduction approaches and compare them with the conventional artifact reduction methods. Our proposed approaches are based on generalized eigenvalue decomposition (GEVD) and median filtering. The proposed methods are applied on experimental simultaneous EEG and fMRI recordings of an epileptic patient. The results show significant improvement over conventional MR artifact reduction methods. copyright by EURASIP.
The extraction of features for automated assessment for breast cancer detection and diagnosis requires identification of the breast tissue. The pectoral muscle in medio-lateral oblique (MLO) mammogram images is one of...
详细信息
ISBN:
(纸本)9780863419348
The extraction of features for automated assessment for breast cancer detection and diagnosis requires identification of the breast tissue. The pectoral muscle in medio-lateral oblique (MLO) mammogram images is one of the few landmarks in the breast. Yet, it can bias and affect the results of any mammogram processing method. To avoid such effects it is often necessary to automatically identify and segment the pectoral muscle prior to breast tissue imageanalysis. We propose the use of Independent Component analysis (ICA) for identification and subsequent removal of the pectoral muscle. The identification is posed as classification of image subsections corresponding to pectoral muscle and breast tissue as represented by a set of ICA basis functions. Average classification rates 97.3% and 83.3% for pectoral muscle and breast tissue respectively have been obtained.
The aim of this study was to analyze the brain structures in temporal lobe epilepsy (TLE) using 3D T1-weighed magnetic resonance images (MRI). We used a method of voxel-based morphometry (VBM) with the unified segment...
详细信息
ISBN:
(纸本)9781424422968;1424422965
The aim of this study was to analyze the brain structures in temporal lobe epilepsy (TLE) using 3D T1-weighed magnetic resonance images (MRI). We used a method of voxel-based morphometry (VBM) with the unified segmentation framework to examine the effects of TLE on specific brain structures in 22 patients. Also, 18 healthy control subjects were included in this study for group comparison. We accomplished GM segmentation, spatial normalization, and intensity non-uniformity correction in the same model. Besides, removal of nonbrain voxels and compensation of spatial normalization effects were performed in this study. Student's t-test statistical models of differences between gray matter concentration (GMC) of patients and controls were obtained using a general linear model (GLM). Compared to controls, TLE presented GMC reduction in hippocampus, amygdala, and entorhinal cortex. Comparison of abnormal areas detected by VBM method and manual delineation of these structures confirms the obtained results.
A non-ideal iris segmentation approach using graph cuts is presented. Unlike many existing algorithms for iris localization which extensively utilize eye geometry, the proposed approach is predominantly based on image...
详细信息
A non-ideal iris segmentation approach using graph cuts is presented. Unlike many existing algorithms for iris localization which extensively utilize eye geometry, the proposed approach is predominantly based on image intensities. In a step-wise procedure, first eyelashes are segmented from the input images using image texture, then the iris is segmented using grayscale information, followed by a post-processing step that utilizes eye geometry to refine the results. A preprocessing step removes specular reflections in the iris, and image gradients in a pixel neighborhood are used to compute texture. The image is modeled as a Markov random field, and a graph cut based energy minimization algorithm [2] is used to separate textured and untextured regions for eyelash segmentation, as well as to segment the pupil, iris, and background using pixel intensity values. The algorithm is automatic, unsupervised, and efficient at producing smooth segmentation regions on many non-ideal iris images. A comparison of the estimated iris region parameters with the ground truth data is provided.
Object removal in image and video sequences has attracted many researchers in video processing. In this paper, a novel method is proposed to separate moving objects from background based on combination of Kalman filte...
详细信息
Object removal in image and video sequences has attracted many researchers in video processing. In this paper, a novel method is proposed to separate moving objects from background based on combination of Kalman filtering and background subtraction. Also, a video completion algorithm is proposed to remove the extracted objects. This algorithm uses the temporal information of frames to complete the holes appeared after object removal. The holes associated to the fixed objects in background model are removed and filled by image completion algorithm based on exemplar texture synthesis. Experimental results demonstrate the privilege performance of the proposed method in object removing and background restoration of real captured video sequences.
Robust detection of buildings is an important part of the automated aerial image interpretation problem. Automatic detection of buildings enables creation of maps, detecting changes, and monitoring urbanization. Due t...
详细信息
Robust detection of buildings is an important part of the automated aerial image interpretation problem. Automatic detection of buildings enables creation of maps, detecting changes, and monitoring urbanization. Due to the complexity and uncontrolled appearance of the scene, an intelligent fusion of different methods gives better results. In this study, we present a novel approach for building detection using multiple cues. We benefit from segmentation of aerial images using invariant color features. Besides, we use the edge and shadow information for building detection. We also determine the shape of the building by a novel method.
This paper proposes a method to obtain fronto-parallel (side-view) body part trajectories for a walk observed from an arbitrary view. The method is based on homography transformations computed for each gait half-cycle...
详细信息
ISBN:
(纸本)9781424421749
This paper proposes a method to obtain fronto-parallel (side-view) body part trajectories for a walk observed from an arbitrary view. The method is based on homography transformations computed for each gait half-cycle detected in the walk. Each homography maps the body part trajectories to a simulated side view of the walk. The proposed method is stable as the resulting normalized trajectories are not influenced by missing or omitted parts of the raw trajectories. Experiments confirm that normalized trajectories are in agreement with the ones that would be obtained from a side view.
A common problem in video surveys in very shallow waters is the presence of strong light fluctuations, due to sun light refraction. Refracted sunlight casts fast moving patterns, which can significantly degrade the qu...
详细信息
ISBN:
(纸本)9781424426195
A common problem in video surveys in very shallow waters is the presence of strong light fluctuations, due to sun light refraction. Refracted sunlight casts fast moving patterns, which can significantly degrade the quality of the acquired data. Motivated by the growing need to improve the quality of shallow water imagery, we propose a method to remove sunlight patterns in video sequences. The method exploits the fact that video sequences allow several observations of the same area of the sea floor, over time. It is based on computing the image difference between a given reference frame and the temporal median of a registered set of neighboring images. A key observation is that this difference will have two components with separable spectral content. One is related to the illumination field (lower spatial frequencies) and the other to the registration error (higher frequencies). The illumination field, recovered by lowpass filtering, is used to correct the reference image. In addition to removing the sunflickering patterns, an important advantage of the approach is the ability to preserve the sharpness in corrected image, even in the presence of registration inaccuracies. The effectiveness of the method is illustrated in image sets acquired under strong camera motion containing non-rigid benthic structures. The results testify the good performance and generality of the approach.
We propose a novel technique to detect feature points from portrait and range representations of the face. In this technique, the appearance of each feature point is encoded using a set of Gabor wavelet responses extr...
详细信息
ISBN:
(纸本)9781424422968;1424422965
We propose a novel technique to detect feature points from portrait and range representations of the face. In this technique, the appearance of each feature point is encoded using a set of Gabor wavelet responses extracted at multiple orientations and spatial frequencies. A vector of Gabor coefficients, called a jet, is computed at each pixel in the search window on a fiducial and compared with a set of jets, called a bunch, collected from a set of training data on the same type of fiducial. The desired feature point is located at the pixel whose jet is the most similar to the training bunch. This is the first time that Gabor wavelet responses were used to detect facial landmarks from range images. This method was tested on 1146 pairs of range and portrait images and high detection accuracies are achieved using a small number of training images. It is shown that co-localization using Gabor jets on range and portrait images resulted in better accuracy than using any single image modality. The obtained accuracies are competitive to that of other techniques in the literature.
Acute rejection is the most common reason of graft failure after kidney transplantation, and early detection is crucial to survive the transplanted kidney function. Automatic classification of normal and acute rejecti...
详细信息
Acute rejection is the most common reason of graft failure after kidney transplantation, and early detection is crucial to survive the transplanted kidney function. Automatic classification of normal and acute rejection transplants from dynamic contrast enhanced magnetic resonance imaging (DCEMRI), is of great importance. Kidney segmentation is the first step for such classification. The image intensity inside the kidney is used as an indication of failure/success. Differentiating between different cases cases is implemented by comparing subsequential kidney scans signals. So, this process is mainly dependent on segmentation. This paper introduces a new shape-based segmentation approach based on level sets. Training shapes are collected from different real data sets to represent the shape variations. Signed distance functions are used to represent these shapes. The methodology incorporates image and shape prior information in a variational framework. The shape registration is considered the backbone of the approach where more general transformations can be used to handle the process. We introduce a novel shape dissimilarity measure that enables the use of different (inhomogeneous) scales. The approach gives successful results compared with other techniques restricted to transformations with homogeneous scales. Results for segmenting kidney images will be illustrated and compared with other approaches to show the efficiency of the proposed technique.
暂无评论