Search

In this paper, we present a new approach to geometrical modeling which allows the user to easily characterize and control the shape defined to a closed surface. We will focus on dealing with the shape's topological, morphological and geometrical properties separately. To do this, we have based our work on the following observations concerning surfaces defined by control-points, and implicit surfaces with skeleton. They both provide complementary approaches to the surface's deformation, and both have specific advantages and limits. We thus attempted to conceive a model which integrates the local and geometrical characterization induced by the control points, as well as the representation of the morphology given by the skeleton. Knowing that the lattice of control points is close to the surface and that the skeleton is centered in the related shape, we thought of a 3-layer model. The transition layer separates the local geometrical considerations from those linked to the global morphology. We apply our model to shape design in order to modify an object in an interactive and ergonomic way, as well as to reconstruction which allows better shape understanding. To do so, we present the algorithms related to these processes. [ABSTRACT FROM AUTHOR]

The parallel implementation of image processing algorithms implies an important choice of data distribution strategy. In order to handle the specific constraints associated with images, data distribution must take into account not only the locality of the data and its geometrical regularity but also the possible irregular computation costs associated with different image elements. A widely studied field to tackle this problem is the family of methods related to rectilinear partitioning. We introduce two fully parallel heuristics that compute suboptimal partitions, with a better complexity than the best known algorithms that compute optimal partitions. In this paper, we compare our heuristics to an optimal partitioning, both in terms of execution time and accuracy of the partition. We give some theoretical bounds on the quality of these heuristics that are corroborated by results of random numerical experiments and real applications. [ABSTRACT FROM AUTHOR]

The continuous image sequence recognition is more difficult than the single image recognition because the classification of continuous image sequences and the image edge recognition must be very accurate. Hence, a method based on sequence alignment for action segmentation and classification is proposed to reconstruct a template sequence by estimating the mean action of a class category, which calculates the distance between a single image and a template sequence by sparse coding in Dynamic Time Warping. The proposed method, the methods of Kulkarni et al. [Continuous action recognition based on sequence alignment, Int. J. Comput. Vis. pp. 1-26.] and Hoai et al. [Joint segmentation and classification of human actions in video, IEEE Conf. Computer Vision and Pattern Recognition, 2008, pp. 108-119.] are compared on the recognition accuracy of the continuous recognition and isolated recognition, which clearly shows that the proposed method outperforms the other methods. When applied to continuous gesture classification, it not only can recognize the gesture categories more quickly and accurately, but is more realistic in solving continuous action recognition problems in a video than the other existing methods. [ABSTRACT FROM AUTHOR]

Region of interest (ROI) is the most important part of an image that expresses the effective content of the image. Extracting regions of interest from images accurately and efficiently can reduce computational complexity and is essential for image analysis and understanding. In order to achieve the automatic extraction of regions of interest and obtain more accurate regions of interest, this paper proposes Optimized Automatic Seeded Region Growing (OASRG) algorithm. The algorithm uses the affinity propagation (AP) clustering algorithm to extract the seeds automatically, and optimizes the traditional region growing algorithm by regrowing strategy to obtain the regions of interest where target objects are contained. Experimental results show that our algorithm can automatically locate seeds and produce results as good as traditional region growing with seeds selected manually. Furthermore, the precision is improved and the extraction effect is better after the optimization with regrowing strategy. [ABSTRACT FROM AUTHOR]

Compression of logo as an image is addressed in logo watermarking, in which a framework of joint Human Vision System (HVS) model and rate allocation theory in the wavelet domain is applied. Under this framework, a novel logo watermarking algorithm using reversible discrete wavelet transform is proposed. Based on multi-level wavelet decomposition of both host and logo images, a well-known HVS model is applied to locate the visually insensitive area in the host for embedding, while the rate allocation theory determines how the logo is compressed and embedded by using the statistical characteristics of the logo. For a given overall embedding distortion, quantization step-sizes of different logo subbands are analytically determined to maximize the fidelity of the extracted logo under the imperceptibility constraint. The adaptive system is thus applicable to different hosts and logos without tuning the parameters manually. It is proved to be robust against various types of attacks and is quite suitable for hardware implementations. Since logo is considered as an image in this new algorithm, the watermarking approach developed can be extended in general to image-in-image embedding. [ABSTRACT FROM AUTHOR]

This paper presents a new topological structure for use in the context of hierarchical radiosity combined with discontinuity meshing. This is most useful for a new strategy adopted for subdividing the elements of a scene consisting of convex polygons. The subdivision is done in a local optimization manner keeping the aspect ratios of produced polygons low. The generated meshes give high visual accuracy. [ABSTRACT FROM AUTHOR]

Accurate motion estimation algorithms are based on a number of invariant properties that can be inferred from the motion. A large number of calibration algorithms have been proposed over the last two decades mainly based on analytic, perspective, or epipolar geometries. Extending Chasles' screw motion concept to the estimation of motion parameters in computer vision, we have presented an analysis of geometric properties of image correspondence vectors synthesized into a single coordinate frame and developed calibration algorithms using both simulated and real range image data.[sup 15,16] In this paper, we extend that work by defining the relevant geometric properties of image correspondence vectors from the point of view of invariants and by developing two calibration algorithms using the Monte Carlo method and median filtering. The algorithms are applied to real and synthetic image data corrupted by noise and outliers. Experimental results demonstrate that the median filter based algorithm is generally more robust and accurate than the Monte Carlo based algorithm and that the geometric analysis of invariant properties of correspondence vectors is a useful framework to motion parameter estimation. [ABSTRACT FROM AUTHOR]

This paper introduces and compares three parallel algorithms to compute general geometric image transformations on MIMD machines. We propose three variants of a parallel general scheme. We focus on the load balancing and the data redistributions. Experimental results are reported and compared. The implementation has been done using PPCM library allowing us to run the program over different parallel machines. We compare logical communication schemes for message-passing machines. Since our parallel algorithm needs global communications such as multiscatters, we study the efficiency of two different logical topologies usable with PPCM. These studies allow us to find the best combination of algorithm and virtual topology to use on a given parallel machine. [ABSTRACT FROM AUTHOR]

This paper presents a gray-scale skeletonization algorithm based on the gray weighted distance transformation (GWDT). The proposed algorithm is conceptually simple and could be used to process nonuniformly distributed gray-scale images. The algorithm can detect the hollows on the gray-scale image, a feature that is often ignored in other skeletonization algorithms, and improves the quality of the skeleton. [ABSTRACT FROM AUTHOR]

One can prove that a specified parallel thinning algorithm always preserves the topology of the input binary image by verifying that no iteration of that algorithm can ever delete a minimal non-simple (“MNS”) set of 1's of an image. For binary images on a 3D face-centered cubic (“FCC”) grid, we determine which sets of voxels can be MNS, and also determine which of those sets can be MNS without being a component of the 1's. These two problems are complicated by the fact that there are (at least) three reasonable ways of defining connectedness for sets of 1's and 0's in a binary image on an FCC grid, since one can: (a) use 18-connectedness for sets of 1's and 12-connectedness for sets of 0's; (b) use 12-connectedness both for sets of 1's and for sets of 0's; (c) use 12-connectedness for sets of 1's and 18-connectedness for sets of 0's. We solve the two problems in all three cases. The analogous problems for binary images on Cartesian grids were first solved by Ronse (in the 2D case) and Ma (in the 3D case). However, our treatment of simple 1's and MNS sets is rather different from theirs, in that it is based on the attachment sets of 1's in binary images. This concept was introduced in an earlier paper [T. Y. Kong, “On topology preservation in 2-D and 3-D thinning,” Int. J. Pattern Recognition and Artificial Intelligence9 (1995) 813–844] and we use the same general approach to MNS sets as was used there. The voxels of an FCC grid are rhombic dodecahedra, which are rather more difficult to visualize and draw than the cubical voxels of a 3D Cartesian grid. An advantage of working with attachment sets is that such sets can be shown in a planar Schlegel diagram of a voxel, which is easy to draw. [ABSTRACT FROM AUTHOR]

In this paper a new thinning algorithm is presented. It is simple yet robust, and can maintain the same advantages of other key skeletonization algorithms. In this new algorithm, only a very small set of rules of criteria for deleting pixels is used. It is faster and easier to implement. Its advantages and limitations are discussed and compared with others. Several examples are illustrated. [ABSTRACT FROM AUTHOR]

Securing the confidentiality of patient information using the image steganography process has gained more attention in the research community. However, embedding the patient information is a major task in the steganography process due to the complexity in identifying the pixel features. Thus, an effective Crow Search Algorithm-based deep belief network (CSA-DBN) is proposed for embedding the information in the medical image. Initially, the appropriate pixels and the features, like pixel coverage, wavelet energy, edge information, and texture features, such as local binary pattern (LBP) and local directional pattern (LDP), are extracted from each pixel. The proposed CSA-DBN utilizes the feature vector and identifies the suitable pixels used for embedding. The patient information is embedded into the image by using the embedding strength and the DWT coefficient. Finally, the embedded information is extracted using the DWT coefficient. The analysis of the proposed CSA-DBN approach is done based on the performance metrics, such as correlation coefficient, peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) that acquired the average values as 0.9471, 24.836 dB, and 0.4916 in the presence of salt and pepper noise and 0.9741, 57.832 dB, and 0.9766 in the absence of noise. [ABSTRACT FROM AUTHOR]

Sport type classification and posture identification based on visual meaning of posture semantic in still images are challenging tasks. The difficulty of these tasks comes from the complex image content consisting of a player's posture, the color and texture of a player's clothes as well as complexity of the background. Player detection is one of the most important tasks in posture identification. For sport type classification without object segmentation, the new set of features, based on 64-bins color histogram, DCT coefficients, and Cb and Cr components, is introduced. To achieve high accuracy, an appropriate feature extraction technique should be also realized. For posture identification, three algorithms, concerning player region detection and suitable features for posture identification, are proposed namely blurred background elimination, irrelevant region elimination, and trimming players region. The DFT coefficients, based on image resizing and slicing techniques, are used as significant features in posture identification. Our proposed features were compared with Edge Histogram and Region-based Shape (EH and RS), two of MPEG-7 descriptors. The experimental results showed that our proposed features yielded better performance with 85.76% of accuracy in sport classification and 86.66% of accuracy in posture identification. [ABSTRACT FROM AUTHOR]

The chronic hyperglycemia of diabetes is associated with long-term damage, dysfunction, and failure of different organs, especially the eyes, kidneys, nerves, heart and blood vessels. The regular examination of diabetic patients can potentially reduce the risk of vision impairment and in the last instance blindness. Early diabetic retinopathy detection enables application of laser therapy treatment in order to prevent or delay loss of vision. The diagnostics and detection of diabetic retinopathy is performed by specialized ophthalmologists manually and represents expensive procedure. Automatic exudates detection and retina images classification would be helpful for reducing diabetic retinopathy screening costs and encouraging regular examinations. We proposed the automated algorithm that applies mathematical modeling which enables light intensity levels emphasis, easier exudates detection, efficient and correct classification of retina images. The proposed algorithm is robust to various appearance changes of retinal fundus images which are usually processed in clinical environments. [ABSTRACT FROM AUTHOR]

Face recognition, a kind of biometric identification, researched in several fields such as computer vision, image processing, and pattern recognition is a natural and direct biometric method. Face Recognition Technology has diverse potential over applications in the fields of information security, law enforcement and surveillance, smart cards, access control and more. Face recognition is one of the diverse techniques used for identifying an individual. Generally the image variations because of the change in face identity are less than the variations among the images of the same face under different illumination and viewing angle. Illumination and pose are the two major challenges, among the several factors that influence face recognition. After pose and illumination, the main factors that affect the face recognition performance are occlusion and expression. So in order to overcome these issues, we proposed an efficient face recognition system based on partial occlusion and expression. The similar blocks in the face image are identified and occlusion can be recovered using the block matching technique. This is combined with expression normalized by calculating the Empherical Mode Decomposition feature. Finally, the face can be recognized by using the PCA. From the implementation result, it is evident that our proposed method based on the PCA technique recognizes the face images effectively. [ABSTRACT FROM AUTHOR]

This article introduces a partial matching framework, based on set theory criteria, for the measurement of shape similarity. The matching framework is described in an abstract way because the proposed scheme is independent of the selection of a segmentation method and feature space. This paradigm ensures the high adaptability of the algorithm and brings the implementer a wide control over the robustness, the ability to balance between selectivity and sensitivity, and the freedom to deal with more general and arbitrary image transformations required for some particular problem. A strategy to establish a descriptor set obtained from components segmented from the main shape is expounded, and two exclusion measure functions are formulated. Proofs are given to show that it is not required to match the entire descriptor sets to determine that two shapes are similar. The methodology provides a dissimilarity score that may be used for shape-based retrieval and object recognition; this is demonstrated applying the proposed approach in a cattle brand identification system. [ABSTRACT FROM AUTHOR]

A new Bregman iterative regularization method is introduced for wavelet-based image deblurring. By using a suitable sequence of penalty parameters, we solve the issue of solvability of minimization problems arising in each step of the iterative procedure. Moreover, we give a projection-based algorithm to compute the solution. The convergence of the algorithm is also stated. The procedure is very fast and easy to implement. We also show numerical results of image deblurring using the algorithm. [ABSTRACT FROM AUTHOR]

We describe a wayfinding system for blind and visually impaired persons that uses a camera phone to determine the user's location with respect to color markers, posted at locations of interest (such as offices), which are automatically detected by the phone. The color marker signs are specially designed to be detected in real time in cluttered environments using computer vision software running on the phone; a novel segmentation algorithm quickly locates the borders of the color marker in each image, which allows the system to calculate how far the marker is from the phone. We present a model of how the user's scanning strategy (i.e. how he/she pans the phone left and right to find color markers) affects the system's ability to detect color markers given the limitations imposed by motion blur, which is always a possibility whenever a camera is in motion. Finally, we describe experiments with our system tested by blind and visually impaired volunteers, demonstrating their ability to reliably use the system to find locations designated by color markers in a variety of indoor and outdoor environments, and elucidating which search strategies were most effective for users. [ABSTRACT FROM AUTHOR]

Digital inpainting provides a means for reconstruction of damaged portions of an image. Although the inpainting basics are straightforward, most inpainting techniques published in the literature are only suitable for remarkable small portion or smooth color image. In order to avoid such shortcomings, we present a new algorithm for digital reconstruction based on combination of wavelet decomposition, surface-based/PDE-based inpainting and texture synthesis. In this algorithm, wavelet transform firstly decomposes the image into high frequency and low frequency level parts. Subsequently, CSRBF which is generally used for surface interpolation or PDE-based inpainting is employed for low frequency level and texture synthesis is used for high frequency level. It results in that not only slight portion but also the common blotched image can be reconstructed with high quality. Especially, our algorithm makes large-size blotched image possible and becomes more efficient as compared to individual PDE-based and CSRBF approaches. [ABSTRACT FROM AUTHOR]

Representing the image to be inpainted in an appropriate sparse dictionary, we introduce a novel method for the filling-in of structure and texture in regions of missing image information. In the morphological component analysis (MCA) inpainting approach, a TV penalty is added to better reduce ringing artifacts. However, the incorporation of TV penalty terms leads to PDE schemes that are numerically intensive. Inspired by the works of Daubechies–Teschke and Borup–Nielsen, we replace the TV term by a $G_{1,1}^{1/2}$ term. It results in an iterative curvelet thresholding scheme for the structure image inpainting. In the whole inpainting process, an alternative approach is presented to layer inpainting. Experimental results show the performance of the algorithm. [ABSTRACT FROM AUTHOR]

We have developed a hyperspectral deconvolution algorithm that sharpens the spectral dimension in addition to the more usual across-track and along-track dimensions. Using an individual three-dimensional model for each pixel's point spread function, the algorithm iteratively applies maximum likelihood criteria to reveal previously hidden features in the spatial and spectral dimensions. Of necessity, our solution is adaptive to unreported across-track and along-track vibrations with amplitudes smaller than the ground sampling distance. We sense and correct these vibrations using a combination of maximum likelihood deconvolution and gradient descent registration that maximizes statistical correlations over many bands. Test panels in real hyperspectral imagery show significant improvement when locations are corrected. Tests on simulated imagery show that the precision of relative corrected positions improves by about a factor of two. [ABSTRACT FROM AUTHOR]

Several studies in neuroscience have shown that nonlinear oscillatory networks represent bio-inspired models for information and image processing. Recent studies on the thalamo-cortical system have shown that weakly connected oscillatory networks (WCONs) exhibit associative properties and can be exploited for dynamic pattern recognition. In this manuscript we focus on WCONs, composed of oscillators that adhere to a Lur'e like description and are organized in such a way that they communicate one another, through a common medium. The main dynamic features are investigated by exploiting the phase deviation equation (i.e. the equation that describes the phase variation of each oscillator, due to weak coupling). Firstly a very accurate analytic expression of the phase deviation equation is derived, by jointly describing the function technique and the Malkin's Theorem. Furthermore, by using a simple learning algorithm, the phase-deviation equation is designed in such a way that given sets of patterns can be stored and recalled. In particular, two models of WCONs are presented as examples of associative and dynamic memories. [ABSTRACT FROM AUTHOR]

This work presents an inversion algorithm for the exponential Radon transform (ERT) over 180° range of view angles. The algorithm can be applied to two-dimensional parallel beam geometry in single photon emission computed tomography. First the differentiation of the ERT over π is backprojected. A convolutional relation between this backprojected differentiation and the original image is then established. In order to invert the convolution relation, the least-squares method is utilized to obtain a numerically generated filtering kernel, which readily restores the original image. The advantages of the proposed algorithm are, first, it only requires half the view angles of the conventional inversion algorithm, second, it deals with truncation in ERT data in certain situations, and third, the numerically generated filtering kernel can be pre-calculated and stored for later applications. The algorithm is an analytical approach except for the pre-calculated inverse kernel. [ABSTRACT FROM AUTHOR]

In a research context in which multiple and well-behaved Surface Reconstruction algorithms already exist, the main goal is not to implement a visualization toolkit able render complex object, but the implementation of methods which can improve our knowledge on the observed world. This work presents a general Surface Reconstruction framework which encapsulates the uncertainty of the sampled data, making no assumption on the shape of the surface to be reconstructed. Starting from the input points (either points clouds or multiple range images), an Estimated Existence Function (EEF) is built which models the space in which the desired surface could exist and, by the extraction of EEF critical points, the surface is reconstructed. The final goal is the development of a generic framework that is able to adapt the result to different kinds of additional information coming that is from multiple sensors. [ABSTRACT FROM AUTHOR]

Having performed discrete stationary wavelet transform (DSWT) to an infrared image and employing generalized cross validation (GCV), noise is reduced in high frequency sub-bands. These sub-bands are at finer resolution levels and the local contrast is enhanced by combining the de-noising method with non-linear operator in these sub-bands which are at coarser resolutionn levels. In order to enhance global contrast for an infrared image, the low frequency sub-band image is also enhanced employing non-incomplete Beta transform (IBT), simulated annealing algorithm (SA) and wavelet neural network (WNN). IBT is used to obtain non-linear gray transform curve. Transform parameters are determined by SA so as to obtain optimal non-linear gray transform parameters. Contrast type of an original image is determined by a new criterion. Gray transform parameters space is determined respectively according to different contrast types. A kind of WNN is proposed to approximate the IBT in the whole low frequency sub-band image. The quality of enhanced image is evaluated by an overall cost criterion. Experimental results show that the new algorithm can greatly improve the global and local contrast for an infrared image while efficiently reducing the correlative noise (CN), gauss white noise (GWN) and multiplicative noise (MN) in the infrared image. [ABSTRACT FROM AUTHOR]

Thresholding algorithms are being increasingly used in a wide variety of disciplines to objectively discern patterns and objects in micrographs, still pictures or remotely-sensed images. Our experience has shown that three common thresholding algorithms exhibit indeterminacy, in that different operator inputs may lead to very different pattern characterizations. A grayscale image of a soil profile is used to illustrate this phenomemon in the case of the intermeans (IM), minimum error (ME), and Besag's iterated conditional modes (ICM) algorithms. For the illustrative example, the IM algorithm depends only weakly on the starting point of the iterative process — it converges to only two adjacent threshold values. In contrast, the ME algorithm converges to 14 different threshold values plus a segmentation that identifies the entire image as dye, and one that identifies none of it as dye. The ICM algorithm converges to an even wider variety of final segmentations, depending on its starting point. A noniterative modification of the IM and ME algorithms is proposed, providing a consistent method for choosing from among a set of apparently equally-valid segmentations. [ABSTRACT FROM AUTHOR]

This article presents a semi-automatic procedure to restore the visual appearance of aged paintings converted to a digital form. The innovative implementation of an image-processing algorithm based on the Retinex theory of human vision alleviates layers of yellowed varnish and dust, restores chromatic balance and contrast, and recovers some of the original painted details. This virtual cleaning of artwork is totally non-intrusive and can be applied automatically to color images of paintings or ancient illustrations. Cleaned virtual reproductions help art historians and restorers in their research and classification work, and also show the artwork in good condition to a wide audience while avoiding an always costly and dangerous manual restoration. [ABSTRACT FROM AUTHOR]

In this article, the new concept of diffusion fields based on partial differential equations is applied to character image processing. Specific diffusion fields are developed according to character image structures and features, depending, on the scope of application. Doing so allows the application of a straightforward one-dimensional numerical scheme to image enhancement, erosion, dilation and thinning. The strength of this approach is the flexibility brought by the diffusion field, which can be defined taking into account specific difficulties of grayscale character images with a minimum of prior information. Thus, the application of the algorithm is shown to be robust to singularity points, the creation of spurious branches, variations in stroke thickness and intensity, multimodality, noise and image background patterns. The resulting enhanced images are noise free with sharp edges and the local typical intensity levels preserved. Thinned characters are connected skeletons located on the ridge of the initial character. Again, the typical intensity of the character and background are preserved. [ABSTRACT FROM AUTHOR]

This article presents an automatic system that takes in grayscale scanned images, which could be mixed text/graphic documents, and performs thresholding and skew detection on the document images. The system consists of two major components; multistage thresholding and skew detection. The proposed skew detection algorithm has no restriction on detectable angle range and does not rely on large blocks of text. It works well on textual document images, graphical images and mixed text and graphic images. The performance of the systems was evaluated using over 60 images that consist of real life documents like envelopes and artificial mixed text/graphic icons. The superior performance of thresholding is clear compared to other techniques from the evaluation. The skew detection algorithm is robust when compared with other methods when very few text lines are present in the document image. [ABSTRACT FROM AUTHOR]

A new unified environment to analyze hardware implementations of video processing and noise reduction algorithms is proposed and analyzed. Based on an automatic word-length determination tool, it evaluates the implementation costs required to reach a given quality target by performing several tests with noisy images at different noise levels. The unified environment uses a universal image quality index to compute the effect of finite precision on image quality. Also, this unified environment has the capacity to distribute the analysis task over a computer network in order to reduce the required processing latency. This unified environment helps to determine which algorithm requires the lowest implementation cost. Furthermore, the unified environment is useful to explore multiple hardware architectures that can be used to implement a given noise reduction algorithm. [ABSTRACT FROM AUTHOR]

An assessment of the performance of a hybrid network with different model selection criteria is considered. These criteria are used in an automatic model selection algorithm for constructing a hybrid network of radial and perceptron hidden units for regression. A forward step builds the full hybrid network; a model selection criterion is used for controlling the network-size and another criterion is used for choosing the appropriate hidden unit for different regions of input space. This is followed by a conservative pruning step using Likelihood Ratio Test, Bayesian or Minimum Description Length, which leads to robust estimators with low variance. The result is a small architecture that performs well on difficult, realistic, benchmark data-sets of high dimensionality and small training size. Best results are obtained by using the Bayesian approach for the model selection. [ABSTRACT FROM AUTHOR]

We propose a method of description and modeling of complex symmetrical images, which can be used for the synthesis of ornamental patterns. Our approach allows considerable memory reduction for storing symmetrical images and considerable time reduction for their synthesis. Our algorithms for ornamental patterns synthesis suggest the design of a special purpose ornamental patterns editor which can store and synthesize symmetrical images. [ABSTRACT FROM AUTHOR]

This work gives an algorithm that makes up for the many iterations and the loss of some main features encountered in the usual methods of wavelet transform filtering. The wavelet transform technique is merged with the window low-pass method. The results are acceptable. [ABSTRACT FROM AUTHOR]

Given an n × n binary image of white and black pixels, we present two optimal algorithms for computing the distance transform and the nearest feature transform using the Euclidean metric. The first algorithm is a fast sequential algorithm that runs in linear time in the input size. The second is a parallel algorithm that runs in O(n²/p) time on a linear array of p processors, p, 1 ≤ p ≤ n. [ABSTRACT FROM AUTHOR]