Showing papers in "International Journal of Imaging Systems and Technology in 2008"
TL;DR: A FreeSurfer-based image-processing analysis “pipeline” or methodology that inputs an MRI volume, corrects possible contrast defects, creates surface reconstructions, and outputs various curvature-based function analyses, which demonstrates that curvature measures and functions peaked at term, with a gradual decline through early childhood and further decline continuing through to adults.
Abstract: The character and timing of gyral development is one manifestation of the complex orchestration of human brain development. The ability to quantify these changes would not only allow for deeper understanding of cortical development but also conceivably allow for improved detection of pathologies. This article describes a FreeSurfer-based image-processing analysis “pipeline” or methodology that inputs an MRI volume, corrects possible contrast defects, creates surface reconstructions, and outputs various curvature-based function analyses. A technique of performing neonate reconstructions using FreeSurfer, which has not been possible previously because of inverted image contrast in premyelinated brains, is described. Once surfaces are reconstructed, the analysis component of the pipeline incorporates several surface-based curvature functions found in literature (principle curvatures, Gaussian, mean curvature, “curvedness,” and Willmore Bending Energy). We consider the problem of analyzing curvatures from different sized brains by introducing a Gaussian-curvature based variable-radius filter. Segmented volume data are also analyzed for folding measures: a gyral folding index (gyrification-white index GWI) and a gray-white matter junction folding index (WMF). A very simple curvature-based classifier is proposed that has the potential to discriminate between certain classes of subjects. We also present preliminary results of this curvature analysis pipeline on nine neonate subjects (30.4 weeks through 40.3 weeks Corrected Gestational Age), three children (2, 3, and 7 years), and three adults (33, 37, and 39 years). Initial results demonstrate that curvature measures and functions across our subjects peaked at term, with a gradual decline through early childhood and further decline continuing through to adults. We can also discriminate older neonates, children, and adults based on curvature analysis. Using a variable radius Gaussian-curvature filter, we also observed that the per-unit bending energy of neonate brain surfaces was also much higher than the children and adults. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 42–68, 2008
133 citations
TL;DR: The results suggest that rtfMRI helped individuals learn how to increase region-specific cortical activity associated with a motor imagery task, and the level of increased activation in motor areas was consolidated after the 2-week self-practice period, with the involvement of neural circuitries implicated in motor skill learning.
Abstract: We report the long-term effect of real-time functional MRI (rtfMRI) training on voluntary regulation of the level of activation from a hand motor area. During the performance of a motor imagery task of a right hand, blood-oxygenation-level-dependent (BOLD) signal originating from a primary motor area was presented back to the subject in real-time. Demographically-matched individuals also received the same procedure without valid feedback information. Followed by the initial rtfMRI sessions, both groups underwent 2-week long, daily-practice of the task. Off-line data analysis revealed that the individuals in the experimental group were able to increase the level of BOLD signal from the regulatory target to a greater degree compared with the control group. Furthermore, the learned level of activation was maintained after the 2-week period, with the recruitment of additional neural circuitries such as the hippocampus and the limbo-thalamo-cortical pathway. The activation obtained from the control group, in the absence of proper feedback, was indifferent across the training conditions. The level of BOLD activity from the target regulatory region was positively correlated with a self evaluative score within the experimental group, while the majority of control subjects had difficulty adopting a strategy to attain the desired level of functional regulation. Our results suggest that rtfMRI helped individuals learn how to increase region-specific cortical activity associated with a motor imagery task, and the level of increased activation in motor areas was consolidated after the 2-week self-practice period, with the involvement of neural circuitries implicated in motor skill learning. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 69–78, 2008
102 citations
TL;DR: This paper demonstrates a pulse sequence with a specialized radiofrequency coil that achieves an uniformity and resolution not shown in previous studies at 7.0T.
Abstract: Human brain imaging with magnetic resonance at 7.0 Tesla (T) can reveal the brain's architecture with resolution equivalent to that obtained from thin slices in vitro. In vivo images can provide tissue type identification with a greater clarity than that available in vitro without special stains. The coil design is an 8 or 12 channel phased array antenna tuned for 7.0T. The individual coils are arranged 8 or 12 loops in a “crown” configuration. Image acquisition is 6 minutes for 15 slices of 2 mm thickness with in-plane resolution of 0.25 mm using a gradient echo pulse sequence. While others have achieved good resolution in human brain imaging, this paper demonstrates a pulse sequence with a specialized radiofrequency coil that achieves an uniformity and resolution not shown in previous studies at 7.0T. Our new images demonstrate very fine details of the midbrain, brainstem, and hippocampal area that have not been previously achieved in living human subjects. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 2–8, 2008
47 citations
TL;DR: A novel tone mapping operator (TMO) for high dynamic range (HDR) images is presented, starting from an algorithm for low dynamic range image enhancement and color correction called ACE (automatic color enhancement), and introducing new features to correctly handle the high variation of HDR images.
Abstract: In this article we present a novel tone mapping operator (TMO) for high dynamic range (HDR) images. Starting from an algorithm for low dynamic range image enhancement and color correction called ACE (automatic color enhancement), we keep its differential and local behavior, introducing new features to correctly handle the high variation of HDR images. In particular, we add a nonlinear local regulator able to automatically tune the algorithm parameters on image variations. In this way, the algorithm behavior changes according to local variations. Moreover, a key setting feature has been added to control the output appearance; it automatically proposes an appropriate key value for the final spatial invariant display mapping. The proposed method performs the spatial variant filtering using only one parameter, that tunes output detail visibility versus overall contrast. We propose a default setting, that guarantees a good solution in most cases. Test, results, and comparison are presented. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 285–294, 2007
17 citations
TL;DR: A selective neural network ensemble is applied to gait recognition and selects some neural network based on the minimization of generalization error to obtain adequate component networks to constitute an ensemble.
Abstract: The neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. Generally, the ensemble shows better generalization performance than a single neural network. In this article, a selective neural network ensemble is applied to gait recognition. The proposed method selects some neural network based on the minimization of generalization error. Since the selection rule is directly incorporated into the cost function, we can obtain adequate component networks to constitute an ensemble. Experiments are performed with the NLPR database to show the performance of the proposed algorithm. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 237–241, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
17 citations
TL;DR: The rotation-invariant texture feature, directionality, and regularity are the main features used in the proposed approach for similarity assessment and the proposed schemes for feature extraction and image retrieval significantly outperform previous works, including methods based on the MPEG-7 texture descriptors.
Abstract: In this article, we present an efficient approach for image retrieval based on the textural information of an image, such as orientation, directionality, and regularity. For this purpose, we apply the nonlinear modified discrete Radon transform to estimate these visual contents. We then utilize texture orientation to construct the rotated Gabor transform for extraction of the rotation-invariant texture feature. The rotation-invariant texture feature, directionality, and regularity are the main features used in the proposed approach for similarity assessment. Experimental results on a large number of texture and aerial images from standard databases show that the proposed schemes for feature extraction and image retrieval significantly outperform previous works, including methods based on the MPEG-7 texture descriptors. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 295–302, 2007
16 citations
TL;DR: This work empirically demonstrates time-course correlation as a function of voxel separation for a human brain in resting state and for a water-filled sphere (called a “phantom”) that served as a test object known not to contain any interacting neuronal systems.
Abstract: Brain function is widely investigated with functional magnetic resonance imaging (fMRI) in humans and animals. In fMRI, the time courses of voxels typically reflect the local blood-oxygen level, which is taken as an indicator of neuronal activity. Voxel time-course correlations are often explicitly modeled and interpreted in terms of neuronal interactions. They also affect standard analyses that do not explicitly target neuronal interactions. As a consequence, time-course correlations between voxels influence conclusions about cognitive and physiological brain processes in many studies. However, voxel correlations are known to arise not only from cognitive and physiological processes, but also as artifacts of fMRI techniques such as the commonly used echoplanar imaging. We empirically demonstrate this phenomenon by plotting time-course correlation as a function of voxel separation for a human brain in resting state and for a water-filled sphere (called a “phantom”). The phantom served as a test object known not to contain any interacting neuronal systems. The plots for brain and phantom are surprisingly similar. The correlational structure found in the phantom must be artifactual. Artifactual correlations spanning many centimeters occur within and between different imaging slices. Correlations between voxel time courses do not necessarily reflect brain processes. Instead, fMRI is affected by artifactual correlations, which are very strong for neighboring voxels and clearly present even at large distances. This needs to be taken into account in the neuroscientific interpretation of voxel correlations. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 345–349, 2008
16 citations
TL;DR: By rigorously searching the optimum toggled pixels with the proposed human visual LMS-trained filter, the proposed method is proven to be superior to the Data Hiding Smart Pair Toggling, proposed by Fu and Au, in image quality under a number of tested halftone images.
Abstract: An improved data hiding in halftone images with cooperating pair toggling human visual system is presented in this paper. An objective halftone image quality evaluation method based on the human visual system obtained by Least-Mean-Square (LMS) is also introduced. By rigorously searching the optimum toggled pixels with the proposed human visual LMS-trained filter, the proposed method is proven to be superior to the Data Hiding Smart Pair Toggling, proposed by Fu and Au [Fu and Au, IEEE Trans Image Process 11 (2002), 477–484], in image quality under a number of tested halftone images. The tested halftone images include ordered dithering [Ulichney, Digital Halftoning (1987)], Floyd error diffusion [Floyd and Steinberg, An adaptive algorithm for spatial gray scale (1975) 36–37], Jarvis error diffusion [Jarvis et al., Comp Graph Image Proc 5 (1976), 13–40], and Stucki error diffusion images. Moreover, the proposed method offers high embedded capacity, and it is flexible to deal with different capacity applications. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 328–332, 2007
13 citations
TL;DR: The overall procedure is challenging due to gross structural deformations in the postmortem brain during extraction and subsequent distortions in the histological preparations, so Hemispheres of the brain were co-registered separately to mitigate these effects.
Abstract: Certain features such as small vascular lesions seen in human MRI (Magnetic Resonance Imaging) are detected reliably only in postmortem histological samples by microscopic imaging. Co-registration of these microscopically detected features to their corresponding locations in the in vivo images would be of great benefit to understanding the MRI signatures of specific diseases. Using nonlinear Polynomial transformation, we report a method to co-register in vivo MRIs to microscopic images of histological samples drawn off the postmortem brain. The approach utilizes digital photographs of postmortem slices as an intermediate reference to co-register the MRIs to microscopy. The overall procedure is challenging due to gross structural deformations in the postmortem brain during extraction and subsequent distortions in the histological preparations. Hemispheres of the brain were co-registered separately to mitigate these effects. Approaches relying on matching single-slices, multiple-slices and entire volumes in conjunction with different similarity measures suggested that using four slices at a time in combination with two sequential measures, Pearson correlation coefficient followed by mutual information, produced the best MRI-postmortem co-registration according to a voxel mismatch count. The accuracy of the overall registration was evaluated by measuring the 3D Euclidean distance between the locations of microscopically identified lesions on postmortem slices and their MRI-postmortem co-registered locations. The results show a mean 3D displacement of 5.1 ± 2.0 mm between the in vivo MRI and microscopically determined locations for 21 vascular lesions in 11 subjects. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 325–335, 2008
13 citations
TL;DR: It is demonstrated the efficacy of such a distributed fuzzy segmentation algorithm by testing it with large datasets and finding a speed-up factor of ∼5 over the sequential implementation seems to be the norm.
Abstract: The usefulness of fuzzy segmentation algorithms based on fuzzy connectedness principles has been established in numerous publications. New technologies are capable of producing larger-and-larger datasets and this causes the sequential implementations of fuzzy segmentation algorithms to be time-consuming. We have adapted a sequential fuzzy segmentation algorithm to multiprocessor machines. We demonstrate the efficacy of such a distributed fuzzy segmentation algorithm by testing it with large datasets (of the order of 50 million points-voxels-items): a speed-up factor of ∼5 over the sequential implementation seems to be the norm. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 336–344, 2008
9 citations
TL;DR: The results suggest that the fMRI BOLD nonlinearity seen with short duration stimuli is not solely due to transient neuronal activity, and predictions of fMRI responses from MEG signals show a weaker non linearity than observed in the actual fMRI data.
Abstract: While recent analysis of functional magnetic resonance imaging (fMRI) data utilize a generalized nonlinear convolution model (e.g., dynamic causal modeling), most conventional analyses of local responses utilize a linear convolution model (e.g., the general linear model). These models assume a linear relationship between the blood oxygenated level dependent (BOLD) signal and the underlying neuronal response. While previous studies have shown that this “neurovascular coupling” process is approximately linear, short stimulus durations are known to produce a larger fMRI response than expected from a linear system. This divergence from linearity between the stimulus time-course and BOLD signal could be caused by neuronal onset and offset transients, rather than a nonlinearity in the hemodynamics related to BOLD contrast. We tested this hypothesis by measuring MEG and fMRI responses to stimuli with ramped contrast onsets and offsets in place of abrupt transitions. MEG results show that the ramp successfully reduced the transient onset of neural activity. However, the nonlinearity in the fMRI response, while also reduced, remained. Predictions of fMRI responses from MEG signals show a weaker nonlinearity than observed in the actual fMRI data. These results suggest that the fMRI BOLD nonlinearity seen with short duration stimuli is not solely due to transient neuronal activity. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 17–28, 2008
TL;DR: A simple and effective improvement in Tsai's method is proposed such that suitable thresholds can be found even when the peaks of a histogram has peaks with a great size variation.
Abstract: Thresholding is frequently used for image segmentation One of the most popular approach to thresholding is the moment-preserving thresholding method proposed by Tsai in 1985 However, it does not work well when the peaks of a histogram have a great size variation Hence, in this study we propose a simple and effective improvement in Tsai's method such that suitable thresholds can be found even when the histogram has peaks with a great size variation Experimental results show the effectiveness of the proposed improvement © 2008 Wiley Periodicals, Inc Int J Imaging Syst Technol, 18, 365–370, 2008
TL;DR: In this article, a method of iterative grid refinement for MD-EIT, which produces images significantly better than unconstrained solutions, is described, and the ill-conditioned nature of the MD EIT inverse problem is improved by limiting the number of unknowns to be solved.
Abstract: Magnetic detection electrical impedance tomography (MD-EIT) produces images of conductivity from magnetic field measurements taken around the body. The ill-conditioned nature of the MD-EIT inverse problem is improved by limiting the number of unknowns to be solved. In this article, a method of iterative grid refinement for MD-EIT, which produces images significantly better than unconstrained solutions, is described. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 379–382, 2007
TL;DR: An independent vector analysis (IVA) is presented to overcome limitations of the ICA method by offering an analysis of additional dependent components that are assigned for use in the automated grouping of dependent (i.e., similar) activation patterns across subjects.
Abstract: During functional MRI (fMRI) studies, blood oxygenation-level dependent (BOLD) signal associated with neuronal activity acquired from multiple individuals are subject to the derivation of group-averaged brain activation patterns. Unlike other cortical areas, subcortical areas such as the thalamus and basal ganglia often manifest smaller, biphasic BOLD signal that are aberrant from signals originating from cortices. Independent component analysis (ICA) can offer session-individual specific brain activation maps without a priori assumptions regarding the timing or pattern of the signal responses. The small activation loci within the subcortical areas are sparsely distributed among the subjects, and a conventional group processing method based on the general linear model (GLM) or ICA may fail to characterize the activation loci. In this article, we present an independent vector analysis (IVA) to overcome these limitations by offering an analysis of additional dependent components (compared to the ICA-based method) that are assigned for use in the automated grouping of dependent (i.e., similar) activation patterns across subjects. The proposed IVA algorithm was applied to simulated data, and its utility was confirmed from real fMRI data employing a trial-based hand motor task. A GLM and the group ICA of the fMRI toolbox (GIFT) were also applied for comparison. From the analysis of activation patterns within subcortical areas, in which the hemodynamic responses (HRs) often deviate from a canonical, model-driven HR, IVA detected task-related activation loci that were not detected through GLM and GIFT. IVA may offer a unique advantage for inferring group activation originating from subcortical areas. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 29–41, 2008
TL;DR: A probabilistic approach to superresolution to address the problem of varying uncertainty is developed based on Kalman filter-like recursion relations and applied to a video sequence acquired by a forward looking sonar system.
Abstract: Superresolution is a procedure that produces a high-resolution image from a set of low-resolution images. Many of superresolution techniques are designed for optical cameras, which produce pixel values of well-defined uncertainty, while there are still various imaging modalities for which the uncertainty of the images is difficult to control. To construct a superresolution image from low-resolution images with varying uncertainty, one needs to keep track of the uncertainty values in addition to the pixel values. In this paper, we develop a probabilistic approach to superresolution to address the problem of varying uncertainty. As direct computation of the analytic solution for the superresolution problem is difficult, we suggest a novel algorithm for computing the approximate solution. As this algorithm is a noniterative method based on Kalman filter-like recursion relations, there is a potential for real-time implementation of the algorithm. To show the efficiency of our method, we apply this algorithm to a video sequence acquired by a forward looking sonar system. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 242–250, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
TL;DR: Some pretreatment techniques used for the object extraction in color debris image were introduced, which was an important basic work in ferrographic technology to identify precisely wear debris produced by friction and wear from the relative motions between machine parts.
Abstract: In this article, some pretreatment techniques used for the object extraction in color debris image were introduced, which was an important basic work in ferrographic technology to identify precisely wear debris produced by friction and wear from the relative motions between machine parts. These pretreatment techniques included image enhancement, image segmentation, filling pore, image erosion, and recognition of wear debris. The results showed that these methods were feasible and effective, which could be applied to extract object of color wear debris image successfully and precisely. It provided an important basis for the recognition technique of wear debris which was related to monitoring machine operation state and fault diagnosis. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 277–284, 2007
TL;DR: It is shown that the combination of SPIO and Gd-DTPA in an aqueous solution exhibits unique and predictable relaxivity properties that are unattainable via the individual use of either agent.
Abstract: Gadolinium-chelates (Gd-DTPA) and superparamagnetic particles of iron oxide (SPIO) are two commonly used MR contrast agents that exhibit inherently different relaxation properties. These two agents have been used to label cells ex-vivo to generate signal contrast with respect to background tissue when introduced to a tissue-of-interest. Assuming minimal mutual interaction between these two agents, we were motivated to investigate the creation of composite relaxation properties by mixing the two in aqueous solutions for conditioning cell labeling. Concentration-dependent relaxivity coefficients were first obtained from each contrast agent, independently, in saline solution at 3 Tesla. These coefficients were then used to predict both the R1 and R2 relaxation rates of a composite contrast agent using a linear model combining the effects of both contrast media. The predicted relaxation rates were experimentally confirmed from 25 composite solutions (combinations of SPIO-concentration ranging from 0 to 1 μg-mL and Gd-DTPA-concentration ranging from 0 to 0.20 mM). We show that the combination of SPIO and Gd-DTPA in an aqueous solution exhibits unique and predictable relaxivity properties that are unattainable via the individual use of either agent. The method may be applied to create “user-tunable” contrast conditions for the visualization of magnetically labeled cells in the context of cell replacement therapy. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 79–84, 2008
TL;DR: A novel method based on statistical facial feature control models for generating realistic controllable face models by forming scattered data interpolation functions that are devoted to the generation of desired shape by taking the anthropometric parameters as input.
Abstract: This article presents a novel method based on statistical facial feature control models for generating realistic controllable face models. The local feature control models are constructed based on the exemplar 3D face scans. We use a three-step model fitting approach for the 3D registration problem. Once we have a common surface representation for examples, we form feature shape spaces by applying a principal component analysis (PCA) to the data sets of facial feature shapes. We compute a set of anthropometric measurements to parameterize the exemplar shapes of each facial feature in a measurement space. Using PCA coefficients as a compact shape representation, we approach the shape synthesis problem by forming scattered data interpolation functions that are devoted to the generation of desired shape by taking the anthropometric parameters as input. The correspondence among all exemplar face textures is obtained by parameterizing a 3D generic mesh over a 2D image domain. The new feature texture with desired attributes is synthesized by interpolating the exemplar textures. With the exception of an initial tuning of feature point positions and assignment of texture attribute values, our method is fully automated. In the resulting system, users are assisted in automatically generating or editing a face model by controlling the high-level parameters. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 341–358, 2007
TL;DR: An attempt has been made to analyze various skin (textured) images caused because of hot water, chemical, electrical, thermal, cigarette, etc using the texture primitive spectrum and a trend is obtained.
Abstract: In this article, an attempt has been made to analyze various skin (textured) images. They are caused because of hot water, chemical, electrical, thermal, cigarette, etc. These images are analyzed using our texture representation scheme. Our approach uses a set of 92 texture primitives. They are tested for the presence of texture by a statistical design of experiments based approach [Ganesan and Bhattacharyya, Pattern Recogn 28 (1995), 99–105]. These texture primitives are concluded as the local descriptor and their distribution over the entire image is the global representation called texture primitive spectrum. The set of texture primitives and the texture primitive spectrums are successful for a number of Bench mark images (Brodatz, Texture—A photographic album for artists and designers, Reinbold, New York, 1968; Vistex, Available at http:--www.white.media.mit.edubvismodbimgerybVision Texture, MIT Media Lab, 1995). Using the texture primitive spectrum, several texture images have been categorized as micro, macro, fine, and coarse and a trend is obtained. Similarly, a set of skin images affected by severe burn with many causes are analyzed. The severity has been quantified and concluded based on simple and weighted mean computed for the texture primitive spectrums. The extent of burn and hence the curing duration can be approximated from the results. The outcome of our experimentation with ground truth and the opinion from the experts are closely matching. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 359–366, 2007
TL;DR: An image processing system that can work in hard real-time and takes advantage on recent technological advances and it is designed to work with a single processor PC under RTLinux.
Abstract: This article presents an image processing system that can work in hard real-time. Compared with systems that use the traditional multiprocessor architecture approach, this computer system takes advantage on recent technological advances and it is designed to work with a single processor PC under RTLinux. Its programming environment is similar to C programming language and it offers a friendly graphical user interface. The performance of the system is illustrated by means of experiments applied to visual guidance of mobile robots via velocity fields using a fixed high-speed camera. The experiments were carried out with a strict sampling frequency of 100 Hz. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 251–256, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
TL;DR: A method of mapping the three-dimensional (3D) cortical surface represented in a simplex mesh to a sphere surface, which does not have any overlap between the polygons and minimizes the geometric distortions as well as the computation time is proposed.
Abstract: The convoluted shape of the cerebral cortex makes it difficult to analyze and visualize the neuronal activation area. One way of overcoming this problem is to use a spherical inflation method to draw a cerebral cortex on a spherical surface. The task of mapping the cortical surface on a sphere has several obstacles, namely, the overlap between the polygons of the surface, the heavy computation demand, and the geometric distortions inherent in the process. This article proposes a method of mapping the three-dimensional (3D) cortical surface represented in a simplex mesh to a sphere surface, which does not have any overlap between the polygons and minimizes the geometric distortions as well as the computation time. The proposed method consists of the two steps of preprocessing and refinement. In the preprocessing step, the 3D cortical surface is mapped onto a sphere without any overlap between the polygons by iterative deformation. In the refinement step, the mapped surface is adjusted to minimize its linear distortion. The experimental results show the efficiency and performance of the proposed mapping method. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 9–16, 2008
TL;DR: A watermarking that adopts the ordered dithering to produce the referenced halftone image, then applying the noise-balanced error diffusion to embed the watermark is proposed, achieving a low computational complexity, low memory demand, and good embedded image quality.
Abstract: Ordered dithering and error diffusion are the two most popular processes to produce halftone results for printing industry. Ordered dithering inherently has the benefit of efficiency. On the other hand, error diffusion has high quality and reasonable complexity. In this article, we propose a watermarking that adopts the ordered dithering to produce the referenced halftone image, then applying the noise-balanced error diffusion to embed the watermark. A low computational complexity, low memory demand, and good embedded image quality are achieved with the proposed technique. From the experimental results, this technique can guard against the cropping and print-and-scan two major degradation processes in halftone images. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 303–314, 2007
TL;DR: In this article, an inverse scattering problem for recovering the shapes of multiple conducting cylinders with the immersed targets in a half-space by genetic algorithm was presented, and the improved steady state GA algorithm was used to find out the global extreme solution.
Abstract: This paper presents an inverse scattering problem for recovering the shapes of multiple conducting cylinders with the immersed targets in a half-space by genetic algorithm. Two separate perfectly conducting cylinders of unknown shapes are buried in one half-space and illuminated by transverse magnetic (TM) plane wave from the other half-space. Based on the boundary condition and the measured scattered field, a set of nonlinear integral equations are derived, and the electromagnetic imaging problem is reformulated into an optimization problem. The improved steady state genetic algorithm is used to find out the global extreme solution. Numerical results are given to demonstrate the performance of the inverse algorithm. Good reconstruction can be obtained even when the initial guesses are far different from the exact shapes, and then the multiple scattered fields between two conductors are serious. In addition, the effect of Gaussian noise on the reconstruction is investigated. We can find that the effect of noise is negligible for the normalized standard deviations below 0.01. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 276–281, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
TL;DR: A novel adaptation framework is proposed that can improve on this current lighting adaptation using a simple road context, feature arbiter, and a proper feature fusion scheme, and can robustly track by selecting or removing the distinctive visual attributes.
Abstract: Despite recent active research on vision-based vehicle detection and tracking, its lack of flexibility hindered practical use in real environments. To be practical, adaptation to various illumination conditions is an essential ingredient. We propose a novel adaptation framework that can improve on this current lighting adaptation using a simple road context, feature arbiter, and a proper feature fusion scheme. In real driving environments, self-supervised online learning can efficiently segment the road and nonroad regions in front of the host vehicle. Classification into these regions is very important to generate regions of interest (ROIs) for potential vehicle position, that is, road context. It improves on system efficiency by reducing noise and processing time. In our global and local lighting models, the feature arbiter selects an appropriate daytime or nighttime detector for each ROI. And finally, an adaptive fusion framework method can robustly track by selecting or removing the distinctive visual attributes. This system was successfully tested on real road data obtained with various ambient lighting conditions. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 283–295, 2008
TL;DR: This system is composed of the following stages: image acquisition, foreground segmentation, depth field estimation, 3D modeling from depth and shape information, and arbitrary view rendering, and a real-time system that demonstrates the use of the aforementioned algorithms.
Abstract: We propose a 3D video system that uses environmental stereo cameras to display a target object from an arbitrary viewpoint. This system is composed of the following stages: image acquisition, foreground segmentation, depth field estimation, 3D modeling from depth and shape information, and arbitrary view rendering. To create 3D models from captured 2D image pairs, a real-time segmentation algorithm, a fast depth reconstruction algorithm, and a simple and efficient shape reconstruction method were developed. For viewpoint generation, the 3D surface model is rotated toward the desired place and orientation, and the texture data extracted from the original camera is projected onto this surface. Finally, a real-time system that demonstrates the use of the aforementioned algorithms was implemented. The generated 3D object can easily be manipulated, e.g., rotated or translated, to render images from different viewpoints. This provides stable scenes of a minimal area that made it possible to understand the target space, and also made it easier for viewers to understand in near real-time. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 367–378, 2007
TL;DR: In this article, a recursive vector selection scheme and an adaptive weighting parameter are proposed to find the robust motion vectors in the region, previous frame vectors are recursively averaged to be utilized for motion error region.
Abstract: True motion estimation is necessary for deinterlacing, frame-rate conversion, and film judder compensation. There have been several block-based approaches to find true motion vectors by tracing minimum sum-of-absolute-difference values by considering spatial and temporal consistency. However, the algorithms cannot find robust motion vectors when the texture of objects is changed. To find the robust motion vectors in the region, a recursive vector selection scheme and an adaptive weighting parameter are proposed. Previous frame vectors are recursively averaged to be utilized for motion error region. The weighting parameter controls fidelity to input vectors and the recursively averaged ones, where the input vectors come from the conventional estimators. If the input vectors are not reliable, then the mean vectors of the previous frame are used for temporal consistency. Experimental results show more robust motion vectors than those of the conventional methods in time-varying texture objects. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 265–275, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
TL;DR: In this paper, the inverse scattering of buried inhomogeneous biaxial dielectric cylinders coated on a conductor with known cross-section is investigated, and the algorithm is based on the moment method and the unrelated illumination method.
Abstract: The inverse scattering of buried inhomogeneous biaxial dielectric cylinders coated on a conductor with known cross section is investigated. Dielectric cylinders with known cross section coated on a conductor of unknown permittivities are buried in one half space and scatter a group of unrelated waves incident from another half space where the scattered field is recorded. By proper arrangement of the various unrelated incident fields, the difficulties of ill-posedness and nonlinearity are circumvented, and the permittivity distribution can be reconstructed through simple matrix operations. The algorithm is based on the moment method and the unrelated illumination method. Numerical results are given to demonstrate the capability of the inverse algorithm. Good reconstruction is obtained both with and without Gaussian noise in measured data. In addition, the effect of noise on the reconstruction result is also investigated. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 228–236, 2008; Published online in Wiley InterScience (www.interscience.wiley.com).
TL;DR: The experimental results demonstrate that the proposed tracking method improves the performance of the real-time face tracking process in terms of success rates and with robustness against interruptions from face-like blobs.
Abstract: We propose a novel face tracking framework, the three-stage model, for robust face tracking against interruptions from face-like blobs. For robust face tracking in real-time, we considered two critical factors in the construction of the proposed model. One factor is the exclusion of background information in the initialization of the target model, the extraction of the target candidate region, and the updating of the target model. The other factor is the robust estimation of face movement under various environmental conditions. The proposed three-stage model consists of a preattentive stage, an assignment stage, and a postattentive stage with a prerecognition phase. The model is constructed by means of effective integration of optimum cues that are selected in consideration of the trade-off between true positives and false positives of face classification based on a context-dependant type of categorization. The experimental results demonstrate that the proposed tracking method improves the performance of the real-time face tracking process in terms of success rates and with robustness against interruptions from face-like blobs. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 321–327, 2007
TL;DR: A robust multiscales algorithm of hierarchical estimation for gradient-based motion estimation is proposed in this article using a combination of robust statistical method and multiscale technique.
Abstract: Gradient-based techniques represent a very popular class of approaches to estimate motions. A robust multiscale algorithm of hierarchical estimation for gradient-based motion estimation is proposed in this article using a combination of robust statistical method and multiscale technique. In such a multiscale approach of hierarchical estimation, motion at each level of the pyramid is estimated using different gradient filters. The iterative multiscale estimation begins by using five-tap central filter, and it is switched to nine-tap Timoner filter after a few iterations. In addition, robust M-estimators are applied at each level of the pyramid to overcome the problem of the outliers caused by illumination variations and motion discontinuities in motion estimation. Experimental simulations show that the new algorithm not only provides an improvement in estimator accuracy, but also achieves computational speedups. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 333–340, 2007
TL;DR: Improved up-sampling filter design for spatially scalable video coding makes use of a basic characteristic of human vision system and intends to assign different filters for different components.
Abstract: Scalable video coding is an ongoing standard, and the current working draft (WD) is to be finalized as an extension of H.264-AVC. It provides scalability at the bit stream level with good compression efficiency and allowing free combinations of spatial, temporal and quality scalability. In the WD, a uniform up-sampling filter is employed to interpolate the base layer frames. This technique achieves high interpolated precision for both luma component and chroma components, but it results in extremely large encoding time which obstructs it from practical use. This paper proposes an improved up-sampling filter design for spatially scalable video coding. It makes use of a basic characteristic of human vision system and intends to assign different filters for different components. Specifically, current usage of the 6-tap up-sampling filter is only for luma component, but for chroma components, much more simplified filter such as 4-tap filter or 2-tap filter should be used instead. Experimental results show that improved up-sampling filter design reduces the computational complexity significantly with negligible coding loss and bit-rate increases. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 315–319, 2007