Search

This paper presents way of generation color documents from elements extracted from an original document image. This scheme yields synthetic documents of similar visual information to the original one. This method has several advantages as it allows a far more efficient way of storing and transmitting the information. Its rationale is to decompose a color document into paper and ink texture parameters and textual information. The textual information may be either typed or handwritten and is stored as a compressed monochromatic image. [ABSTRACT FROM AUTHOR]

Automatic evaluation of visual print quality is addressed in this study. Due to many complex factors of perceived visual quality its evaluation is divided to separate parts which can be individually evaluated using standardized assessments. Most of the assessments however require active evaluation by trained experts. In this paper one quality assessment, missing dot detection from printed dot patterns, is addressed by defining sufficient hardware for image acquisition and method for detecting and counting missing dots from a test strip. The experimental results are evidence how the human assessment can be automated with the help of machine vision, thus making the test more repeatable and accurate. [ABSTRACT FROM AUTHOR]

Graphics recognition for raster-based input discovers primitives such as lines, arrowheads, and circles. This paper focuses on graphics recognition of figures in vector-based PDF documents. The first stage consists of extracting the graphic and text primitives corresponding to figures. An interpreter was constructed to translate PDF content into a set of self-contained graphics and text objects (in Java), freed from the intricacies of the PDF file. The second stage consists of discovering simple graphics entities which we call graphemes, e.g., a pair of primitive graphic objects satisfying certain geometric constraints. The third stage uses machine learning to classify figures using grapheme statistics as attributes. A boosting-based learner (LogitBoost in the Weka toolkit) was able to achieve 100% classification accuracy in hold-out-one training/testing using 16 grapheme types extracted from 36 figures from BioMed Central journal research papers. The approach can readily be adapted to raster graphics recognition. Keywords: Graphics Recognition, PDF, Graphemes, Vector Graphics, Machine Learning, Boosting. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach for facial expression analysis and recognition. The proposed approach relies on the distance vectors retrieved from 3D distribution of facial feature points to classify universal facial expressions. Neural network architecture is employed as a classifier to recognize the facial expressions from a distance vector obtained from 3D facial feature locations. Facial expressions such as anger, sadness, surprise, joy, disgust, fear and neutral are successfully recognized with an average recognition rate of 91.3%. The highest recognition rate reaches to 98.3% in the recognition of surprise. [ABSTRACT FROM AUTHOR]

With the development of computer science, there is an increasing demand on the object recognition in stereo images. As a binocular image pair contains larger and more complicated information than a monocular image, the stereo vision analysis has been a difficult task. Therefore how to extract the region of user's interest is a vital step to reduce the data redundancy and improve the robustness and reliability of the analysis. The original stereo sequences used in the paper are obtained from two parallel video cameras mounted on a vehicle driving in a residential area. This paper targets the problem of data segmentation of those stereo images. It proposes a set of algorithms to separate the foreground from the complicated changing background. Experiments show that the whole process is fast and efficient in reducing the data redundancy, and improves the overall performance for the further obstacle extraction. [ABSTRACT FROM AUTHOR]

Recent solutions to object classification have focused on the decomposition of objects into representative parts. However, the vast majority of these methods are based on single visual cue measurements. Psychophysical evidence suggests that humans use multiple visual cues to accomplish recognition. In this paper, we address the problem of integrating multiple visual information for object recognition. Our contribution in this paper is twofold. First, we describe a new probabilistic integration model of multiple visual cues at different spatial locations across the image. Secondly, we use the cue integration framework to classify images of objects by combining two-dimensional and three-dimensional visual cues. Classification results obtained using the method are promising. [ABSTRACT FROM AUTHOR]

In this paper, we present the results of the Acoustic Event Detection (AED) and Classification (AEC) evaluations carried out in February 2006 by the three participant partners from the CHIL project. The primary evaluation task was AED of the testing portions of the isolated sound databases and seminar recordings produced in CHIL. Additionally, a secondary AEC evaluation task was designed using only the isolated sound databases. The set of meeting-room acoustic event classes and the metrics were agreed by the three partners and ELDA was in charge of the scoring task. In this paper, the various systems for the tasks of AED and AEC and their results are presented. [ABSTRACT FROM AUTHOR]

This paper presents a novel shape recovery technique that combines photometric stereo with polarization information. First, a set of ambiguous surface normals are estimated from polarization data. This is achieved using Fresnel theory to interpret the polarization patterns of light reflected from dielectric surfaces. The process is repeated using three different known light source positions. Photometric stereo is then used to disambiguate the surface normals. The relative pixel brightnesses for the different light source positions reveal the correct surface orientations. Finally, the resulting unambiguous surface normal estimates are integrated to recover a depth map. The technique is tested on various objects of different materials. The paper also demonstrates how the depth estimates can be enhanced by applying methods suggested in earlier work. [ABSTRACT FROM AUTHOR]

In this paper, a method for automatically indexing the contents to reduce the effort that used to be required for input paper information and constructing index is sought. Various contents formats for journals, which have different features from those for general documents, are described. The principal elements that we want to represent are titles, authors, and pages for each paper. Thus, the three principal elements are modeled according to the order of their arrangement, and then their features are generalized. The content analysis system is then implemented based on the suggested modeling method. The content analysis system, implemented for verifying the suggested method, gets its input in the form containing more than 300 dpi gray scale image and analyze structural features of the contents. It classifies titles, authors and pages using efficient projection method. The definition of each item is classified according to regions, and then is extracted automatically as index information. It also helps to recognize characters region by region. The experimental result is obtained by applying to some of the suggested 6 models, and the system shows 97.3% success rate for various journals. [ABSTRACT FROM AUTHOR]

In this paper, we present a scheme that segments triangular meshes into several meaningful patches using multi-scale normal variation. In differential geometry, there is a traditional scheme that segments smooth surfaces into several patches such as elliptic, hyperbolic, or parabolic regions, with several curves such as ridge, valley, and parabolic curve between these regions, by means of the principal curvatures of the surface. We present a similar segmentation scheme for triangular meshes. For this purpose, we develop a simple and robust scheme that approximates the principal curvatures on triangular meshes by multi-scale normal variation scheme. Using these approximated principal curvatures and modifying the classical segmentation scheme for triangular meshes, we design a scheme that segments triangular meshes into several meaningful regions. This segmentation scheme is implemented by evaluating a feature weight at each vertex, which quantifies the likelihood that each vertex belongs to one of the regions. We test our scheme on several face models and demonstrate its capability by segmenting them into several meaningful regions. [ABSTRACT FROM AUTHOR]

Ring artifacts can occur in reconstructed images from X-ray microtomography as full or partial circles centred on the rotation axis. In this paper, a 2D method is proposed that reduces these ring artifacts in the reconstructed images. The method consists of two main parts. First, the artifacts are localised in the image using local orientation estimation of the image structures and filtering to find ring patterns in the orientation information. Second, the map of the located artifacts is used to calculate a correction image using normalised convolution. The method is evaluated on 2D images from volume data of paper fibre imaged at the European Synchrotron Radiation Facility (ESRF) with high resolution X-ray microtomography. The results show that the proposed method reduces the artifacts and restores the pixel values for all types of partial and complete ring artifacts where the signal is not completely saturated. [ABSTRACT FROM AUTHOR]

Gastric cancer is a great part of the cancer occurrence and the mortality from cancer in Korea, and the early detection of gastric cancer is very important in the treatment and convalescence. This paper, for the early detection of gastric cancer, proposes the analysis system of an endoscopic image of the stomach, which detects the abnormal region by using the change of color in the image and by providing the surface tissue information to the detector. While advanced inflammation and cancer may be easily detected, early inflammation and cancer are difficult to detect and requires more attention to be detected. This paper, at first, converts the endoscopic image to the image of the IHb(Index of Hemoglobin) model and removes noises incurred by illumination and, automatically detects the regions suspected as cancer and provides the related information to the detector, or provides the surface tissue information for the regions appointed by the detector. This paper does not intend to provide the final diagnosis of the detected abnormal regions as gastric cancer, but it intends to provide a supplementary mean to reduce the load and mistaken diagnosis of the detector, by automatically detecting the abnormal regions not easily detected by the human eye and this provides additional information for the diagnosis. The experiments using practical endoscopic images for performance evaluation showed that the proposed system is effective in the analysis of endoscopic image of the stomach. [ABSTRACT FROM AUTHOR]

Automatic classification of objects based on their visual appearance is often performed based on clustering algorithms, which can be based on soft computing techniques. One of the most used methods is fuzzy clustering. However, this method can converge to local minima. This problem has been addressed very recently by applying ant colony optimization to tackle this problem. This paper proposed the use of this fuzzy-ant clustering approach to derive fuzzy models. These models are used to classify marbles based on their visual appearance; color and vein classification is performed. The proposed fuzzy modeling approach is compared to other soft computing classification algorithms, namely: fuzzy, neural, simulated annealing, genetic and combinations of these approaches. Fuzzy-ant models presented higher classification rates than the other soft computing techniques. [ABSTRACT FROM AUTHOR]

Visualization is a technique used to facilitate the understanding of scientific results such as large data sets and maps. Provenance techniques can also aid in increasing the understanding and acceptance of scientific results by providing access to information about the sources and methods which were used to derive them. Visualization and provenance techniques, although rarely used in combination, may further increase scientists' understanding of results since the scientists may be able to use a single tool to see and evaluate result derivation processes including any final or partial result. In this paper we introduce Probe-It!: a visualization tool for scientific provenance information that enables scientists to move the visualization focus from intermediate and final results to provenance back and forth. To evaluate the benefits of Probe-It!, in the context of maps, this paper presents a quantitative user study on how the tool was used by scientists to discriminate between quality results and results with known imperfections. The study demonstrates that only a very small percentage of the scientists tested can identify imperfections using maps without the help of knowledge provenance and that most scientists, whether GIS experts, subject matter experts (i.e., experts on gravity data maps) or not, can identify and explain several kinds of map imperfections when using maps together with knowledge provenance visualization. [ABSTRACT FROM AUTHOR]

In this paper, a hierarchical shape decomposition algorithm is proposed, which integrates the advantages of skeleton-based and minima-rule-based meaningful segmentation algorithms. The method makes use of new geometrical and topological functions of skeleton to define initial cutting critical points, and then employs salient contours with negative minimal principal curvature values to determine natural final boundary curves among parts. And sufficient experiments have been carried out on many meshes, and shown that our framework can provide more reasonable perceptual results than single skeleton-based [8] or minima-rule-based [15] algorithm. In addition, our algorithm not only can divide a mesh of any genus into a collection of genus zero, but also partition level-of-detail meshes into similar parts. [ABSTRACT FROM AUTHOR]

Academia and search engine industry followers consider personalization as the future of search engines, and this fact is well supported by the tremendous amount of research in this field. However the impact of technological advancement seems to be focused towards bringing more relevant results to the users - not the way it is usually presented to the users. User archives are useful resources which can be exploited more efficiently if reusability is promoted appropriately. In this paper, we present a theoretical framework which can sit on top of existing search technologies and deliver visually enhanced user experience and archival reusability. Contribution of this paper is two fold; first - visual interface for personal search engine setup, self-updating user interests, and session mapping based on modified spider graph; and secondly - enabling better archival reusability through user archival maps, session maps, interest specific maps and visual bookmarking. [ABSTRACT FROM AUTHOR]

Face recognition is one of the most successful applications in biometric authentication. However, methods reported in the literature still suffer from some problems which prevent the further development in face recognition. This paper presents a novel robust method for face recognition under near infrared (NIR) lighting condition based on Extended Local Binary Pattern (ELBP), which solves the problems produced by variations of illumination rightly, since the NIR images are insensitive to variations of ambient lighting, and ELBP can extract adequate texture features form the NIR images. By combining the local feature vectors, a global feature vector is formed and as the global feature vectors extracted by ELBP operator often have very high dimensions, a classifier has been trained using the AdaBoost algorithm to select the most representative features for better performance and dimensionality reduction. Compared with the huge number of features produced by ELBP operator, only a small part of the features are selected in this paper, which saves much computation and time cost. The comparison with the results of classic algorithms proves the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Content based image retrieval (CBIR), a technique which uses visual contents to search images from the large scale image databases, is an active area of research for the past decade. It is increasingly evident that an image retrieval system has to be domain specific. In this paper, we present an algorithm for retrieving images with respect to a database consisting of engineering/computer-aided design (CAD) models. The algorithm uses the shape information in an image along with its 3D information. A linear approximation procedure that can capture the depth information using the idea of shape from shading has been used. Retrieval of objects is then done using a similarity measure that combines shape and the depth information. Plotted precision/recall curves show that this method is very effective for an engineering database. [ABSTRACT FROM AUTHOR]

Schlick's approximation of the term xp is used primarily to reduce the complexity of specular lighting calculations in graphics applications. Since moment functions have a kernel defined using a monomial xpyp, the same approximation could be effectively used in the computation of normalized geometric moments and invariants. This paper outlines a framework for computing moments of various orders of an image using a simplified kernel, and shows the advantages provided by the approximating function through a series of experimental results. [ABSTRACT FROM AUTHOR]

Floating mines are a significant threat to the safety of ships in theatres of military or terrorist conflict. Automating mine detection is difficult, due to the unpredictable environment and high requirements for robustness and accuracy. In this paper, a floating mine detection algorithm using motion analysis methods is proposed. The algorithm aims to locate suspicious regions in the scene using contrast and motion information, specifically regions that exhibit certain predefined motion patterns. Throughput of the algorithm is improved with a parallel pipelined data flow. Moreover, this data flow enables further computational performance improvements though special hardware such as field programmable gate arrays (FPGA) or Graphics Processing Units (GPUs). Experimental results show that this algorithm is able to detect mine regions in the video with reasonable false positive and minimum false negative rates. [ABSTRACT FROM AUTHOR]

A tensor-based optical flow algorithm is presented in this paper. This algorithm uses a cost function that is an indication of tensor certainty to adaptively adjust weights for tensor computation. By incorporating a good initial value and an efficient search strategy, this algorithm is able to determine optimal weights in a small number of iterations. The weighting mask for the tensor computation is decomposed into rings to simplify a 2D weighting into 1D. The devised algorithm is well-suited for real-time implementation using a pipelined hardware structure and can thus be used to achieve real-time optical flow computation. This paper presents simulation results of the algorithm in software, and the results are compared with our previous work to show its effectiveness. It is shown that the proposed new algorithm automatically achieves equivalent accuracy to that previously achieved via manual tuning of the weights. [ABSTRACT FROM AUTHOR]

In the two-view case, point matching constraints are represented by the fundamental matrix. In the three-view case, the point matching constraints are indirectly represented by three trifocal tensors corresponding to the three camera matrices. A direct representation of the point matching constraints can be obtained by applying suitable transformations on the trifocal tensors. This paper discusses some issues related to point matching constraints. First, it presents a novel approach for deriving the constraints in terms of a generator space. Second, it shows that the resulting set of linearly independent constraints is 10-dimensional for the three-view case, a result which deviates from the literature on this subject. Third, in the case that the cameras have non-co-linear focal points, 9 of these 10 constraints can be obtained in a straight-forward way from the three fundamental matrices which we have in the three-view case. The last constraint can be obtained from the fundamental matrices but in a non-trivial way. The main result of the paper is a better understanding of the properties related to point matching constraints in three dimensions and how they are related to the corresponding two-view constraints. [ABSTRACT FROM AUTHOR]

This paper presents real-time fabric defect detection based in intelligent techniques. Neural networks (NN), fuzzy modeling (FM) based on product-space fuzzy clustering and adaptive network based fuzzy inference system (ANFIS) were used to obtain a clearly classification for defect detection. Their implementation requires thresholding its output, and based in previous studies a confusion matrix based optimization is used to obtain the threshold. Experimental results for real fabric defect detection were obtained from the experimental apparatus presented in the paper, that showed the usefulness of the three intelligent techniques, although the NN has a faster performance. Online implementation of the algorithms showed they can be easily implemented with commonly available resources and may be adapted to industrial applications without great effort. [ABSTRACT FROM AUTHOR]

Degradation in old documents has been a matter of concern for a long time. With the easy access to information provided by technologies such as the Internet, new ways have arisen for consulting those documents without exposing them to yet more dangers of degradation. While restoration methods are present in the literature in relation to text documents and artworks, little attention has been given to the restoration of ancient music. This paper describes and compares different methods to restore images of ancient music documents degraded over time. Six different methods were tested, including global and adaptive thresholding, color clustering and edge detection. In this paper we conclude that those based on the Sauvola's thresholding algorithm are the better suited for our proposed goal of ancient music restoration. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for face recognition based on a multiresolution analysis tool called Digital Curvelet Transform. Multiresolution ideas notably the wavelet transform have been profusely employed for addressing the problem of face recognition. However, theoretical studies indicate, digital curvelet transform to be an even better method than wavelets. In this paper, the feature extraction has been done by taking the curvelet transforms of each of the original image and its quantized 4 bit and 2 bit representations. The curvelet coefficients thus obtained act as the feature set for classification. These three sets of coefficients from the three different versions of images are then used to train three Support Vector Machines. During testing, the results of the three SVMs are fused to determine the final classification. The experiments were carried out on three well known databases, viz., the Georgia Tech Face Database, AT&T "The Database of Faces" and the Essex Grimace Face Database. [ABSTRACT FROM AUTHOR]

Shape-based image retrieval is one of the most challenging aspects in Content-Based Image Retrieval (CBIR). A variety of techniques are reported in the literature that aim to retrieve objects based on their shapes; each of these techniques has its advantages and disadvantages. In this paper, we propose a novel scheme that exploits complementary benefits of several shape-based image retrieval techniques and integrates their assessments based on a pair-wise co-ranking process. The proposed scheme can handle any number of CBIR techniques; however, three common techniques are used in this study: Invariant Zernike Moments (IZM), Multi-Triangular Area Representation (MTAR), and Fourier Descriptor (FD). The performance of the proposed scheme is compared with that of each of the selected techniques. As will be demonstrated in this paper, the proposed co-ranking scheme exhibits superior performance. [ABSTRACT FROM AUTHOR]

The problem of 3D reconstruction of nonrigid objects from uncalibrated image sequences is addressed in the paper. Our method assumes that the nonrigid object is composed of rigid part and deformation part. We first recover the affine structure of the object and separate the rigid features from the deformation ones. Then stratify the structure from affine to Euclidean space by virtue of the rigid features. The novelty of the paper lies in two aspects. First, we propose a deformation weight constraint to the problem and prove that the recovered shape bases and shapes are transformation invariant under this constraint. Second, we propose a constrained power factorization (CPF) algorithm to recover the deformation structure in affine space. The algorithm overcomes the limitations of previous SVD-based methods and can work with missing data in the tracking matrix. Extensive experiments on synthetic data and real sequences validate the proposed method and show improvements over existing solutions. [ABSTRACT FROM AUTHOR]

This paper presents a scheme for image decomposition and reconstruction, using complex Gabor wavelets. Gabor functions have been used extensively in areas related to the human visual system due to their localization in space and bandlimited properties. However, since the standard two-sided Gabor functions are not orthogonal and lead to nearly singular Gabor matrices, they have been used in the decomposition and feature extraction of images rather than in image reconstruction. In an attempt to reduce the singularity of the Gabor matrix and produce reliable image reconstruction, in this paper, we show that a single-sided Gabor function can accomplish both, with the reconstruction residual error being very small (PSNR of at least 300 dB). [ABSTRACT FROM AUTHOR]

In this paper, we approach the problem of determining the basic components from repetitive textured surfaces undergoing free-form deformations. Traditional methods for texture modeling are usually based on measurements performed on fronto-parallel planar surfaces. Recently, affine invariant descriptors have been proposed as an effective way to extract local information from non-planar texture surfaces. However, affine transformations are unable to model local image distortions caused by changes in surface curvature. Here, we propose a method for selecting the most representative candidates for the basic texture elements of a texture field while preserving the descriptors' affine invariance requirement. Our contribution in this paper is twofold. First, we investigate the distribution of extracted affine invariant descriptors on a nonlinear manifold embedding. Secondly, we describe a learning procedure that allows us to group repetitive texture elements while removing candidates presenting high levels of curvature-induced distortion. We demonstrate the effectiveness of our method on a set of images obtained from man-made texture surfaces undergoing a range of non-rigid deformations. [ABSTRACT FROM AUTHOR]

Automatic segmentation of sub-cortical structures has great use in studying various neurodegentative diseases. In this paper, we propose a fully automatic solution to this problem through the utilization of a distribution atlas built from a set of training MR images. Our model consists of two major components: a local likelihood based active contour (LLAC) model and a guiding probabilistic atlas. The former has a very strong ability in standing out the structures that are in low contrast with the surrounding tissues. The latter has the functionality of defining and leading the segmentation procedure to capture the structure of interest. Formulated under the maximum a posterior framework, probabilistic atlas for the structure of interest, e.g. caudate, putamen, can be seamlessly integrated into the level set evolution procedure, and no thresholding step is needed for capturing the target. [ABSTRACT FROM AUTHOR]

The ability to recognize the strokes drawn by the user, is central to most sketch-based interfaces. However, very few solutions that rely on recognition are robust enough to make sketching a definitive alternative to traditional WIMP user interfaces. In this paper, we propose an approach based on classification that given an unconstrained sketch, can robustly assign a label to each stroke that comprises the sketch. A key contribution of our approach is a technique for grouping strokes that eliminates outliers and enhances the robustness of the classification. We also propose a set of features that capture important attributes of the shape and mutual relationship of strokes. These features are statistically well-behaved and enable robust classification with Support Vector Machines (SVM). We conclude by presenting a concrete implementation of these techniques in an interface for driving facial expressions. [ABSTRACT FROM AUTHOR]

Multidimensional databases are commonly used for decision making in the context of data warehouses. Considering the multidimensional model, data are presented as hypercubes organized according to several dimensions. However, in general, hypercubes have more than three dimensions and contain a huge amount of data, and so cannot be easily visualized. In this paper, we show that data cubes can be visualized as images by building blocks that contain mostly the same value. Blocks are built up using an APriori-like algorithm and each block is considered as a set of pixels which colors depend on the corresponding value. The key point of our approach is to set how to display a given block according to its corresponding value while taking into account that blocks may overlap. In this paper, we address this issue based on the Pixelization paradigm. [ABSTRACT FROM AUTHOR]

Head pose estimation in low resolution is a challenge problem. Traditional pose estimation algorithms, which assume faces have been well aligned before pose estimation, would face much difficulty in this situation, since face alignment itself does not work well in this low resolution scenario. In this paper, we propose to estimate head pose using view-based multi-view face detectors directly. Naive Bayesian classifier is then applied to fuse the information of head pose from multiple camera views. To model the temporal changing of head pose, Hidden Markov Model is used to obtain the optimal sequence of head pose with greatest likelihood. [ABSTRACT FROM AUTHOR]

In this paper, we present KNIGHT, a Windows-based stand-alone object detection, tracking and classification software, which is built upon Microsoft Windows technologies. The object detection component assumes stationary background settings and models background pixel values using Mixture of Gaussians. Gradient-based background subtraction is used to handle scenarios of sudden illumination change. Connected- component algorithm is applied to detected foreground pixels for finding object-level moving blobs. The foreground objects are further tracked based on a pixel-voting technique with the occlusion and entry/exit reasonings. Motion correspondences are established using the color, size, spatial and motion information of objects. We have proposed a texture-based descriptor to classify moving objects into two groups: vehicles and persons. In this component, feature descriptors are computed from image patches, which are partitioned by concentric squares. SVM is used to build the object classifier. The system has been used in the VACE-CLEAR evaluation forum for the vehicle tracking task. Corresponding system performance is presented in this paper. [ABSTRACT FROM AUTHOR]

This paper illustrates and extends an efficient framework, called the square-root-elastic (SRE) framework, for studying shapes of closed curves, that was first introduced in [2]. This framework combines the strengths of two important ideas - elastic shape metric and path-straightening methods - for finding geodesics in shape spaces of curves. The elastic metric allows for optimal matching of features between curves while path-straightening ensures that the algorithm results in geodesic paths. This paper extends this framework by removing two important shape preserving transformations: rotations and re-parameterizations, by forming quotient spaces and constructing geodesics on these quotient spaces. These ideas are demonstrated using experiments involving 2D and 3D curves. [ABSTRACT FROM AUTHOR]

The pupil localization algorithm is very important for a face recognition system. Traditional pupil localization algorithms are easy to be affected by uneven illuminations and accessories. Aiming at those limitations, a novel pupil localization algorithm is proposed in this paper. The algorithm firstly implements face image tilt adjustment and extracts eye region through the horizontal intensity gradient integral projection and Gabor filtering. Then in order to increase the eye detection accuracy, PCA is applied to select Gabor filter, and the projection enhancement algorithm is presented. At last the Negative Radial Symmetry is presented to locate the pupil position precisely in eye windows. Experimental results show that the method can locate the pupil position accurately, and demonstrate robustness to uneven lighting, noise, accessories and pose variations. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach to graph regularisation based on energy minimisation. Our method hinges in the use of a Ginzburg-Landau functional whose extremum is achieved efficiently by a gradient descend optimisation process. As a result of the treatment given in this paper to the regularisation problem, constraints can be enforced in a straightforward manner. This provides a means to solve a number of problems in computer vision and pattern recognition. To illustrate the general nature of our graph regularisation algorithm, we show results on two application vehicles, photometric stereo and image segmentation. Our experimental results demonstrate the efficacy of our method for both applications under study. [ABSTRACT FROM AUTHOR]

The lower the resolution of a given text is, the more difficult it becomes to segment and to recognize it. The resolution of screen-rendered text can be very low. With a typical x-height of 4 to 7 pixels it is much lower as in other low resolution OCR situations. Modern OCR approaches for such very low resolution text use a classification-based segmentation where the underlying classifier plays an important role. This paper presents a multiple classifier system for the classification of single characters. This system is used as a subsystem for the classification-based segmentation within a system to read screen-rendered text. The paper shows that the presented multiple classifier system outperforms the best former single classifier system on single characters by far and it shows the impact of using the multiple classifier system on the word reading performance. [ABSTRACT FROM AUTHOR]

This paper presents a novel visual speech recognition approach based on motion segmentation and hidden Markov models (HMM). The proposed method identifies utterances from mouth video, without evaluating voice signals. The facial movements in the video data are represented using 2D spatial-temporal templates (STT). The proposed technique combines discrete stationary wavelet transform (SWT) and Zernike moments to extract rotation invariant features from the STTs. HMMs are used as speech classifier to model English phonemes. The preliminary results demonstrate that the proposed technique is suitable for phoneme classification with a high accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a performance evaluation of a set of fast block matching motion estimation methods of recent development. These methods are Kite-Cross-Diamond search (KCDS), Cross-Diamond-Hexagonal search (CDHS), Efficient-Hexagonal-Inner search (EHIS) and a newly proposed in this paper, called Cross-Half-Diamond low resolution search (CHDS), which is an improvement of Cross-Diamond-Hexagonal search. Also, Diamond search (DS) and Full search (FS) algorithms are implemented. These methods are evaluated based on the mean square error and the number of search points. Based on experimental results, it is concluded that DS, CDHS, CHDS and EHIS are appropriate for small and large motion contents, except EHIS for high frequencies and complex motion contents. The KCDS method has the lowest performance compared with other algorithms. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of estimating the 3D rigid pose of a CT volume of an object from its 2D X-ray projections. We use maximization of mutual information, an accurate similarity measure for multi-modal and mono-modal image registration tasks. However, it is known that the standard mutual information measure only takes intensity values into account without considering spatial information and its robustness is questionable. In this paper, instead of directly maximizing mutual information, we propose to use a variational approximation derived from the Kullback-Leibler bound. Spatial information is then incorporated into this variational approximation using a Gibbs random field model. The newly derived similarity measure has a least-squares form and can be effectively minimized by a multi-resolution Levenberg-Marquardt optimizer. Experimental results are presented on X-ray and CT datasets of a plastic phantom and a cadaveric spine segment. [ABSTRACT FROM AUTHOR]

The paper focusses on a group of segmentation problems dealing with 3D data sets showing thin objects that appear disconnected in the data due to partial volume effects or a large spacing between neighbouring slices. We propose a modification of the speed function for the well-known level set method to bridge these discontinuities. This allows for the segmentation of the object as a whole. In this paper we are concerned with treelike structures, particularly dendrites in microscopic data sets, whose shape is unknown prior to segmentation. Using the modified speed function, our algorithm segments dendrites and their spines, even if parts of the object appear to be disconnected due to artifacts. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new manifold representation capable of being applied for visual speech recognition. In this regard, the real time input video data is compressed using Principal Component Analysis (PCA) and the low-dimensional points calculated for each frame define the manifolds. Since the number of frames that from the video sequence is dependent on the word complexity, in order to use these manifolds for visual speech classification it is required to re-sample them into a fixed number of keypoints that are used as input for classification. In this paper two classification schemes, namely the k Nearest Neighbour (kNN) algorithm that is used in conjunction with the two-stage PCA and Hidden-Markov-Model (HMM) classifier are evaluated. The classification results for a group of English words indicate that the proposed approach is able to produce accurate classification results. [ABSTRACT FROM AUTHOR]

This paper provides some information regarding the winning system at the GREC'2005 contest on arc segmentation. Important facts are first recalled, then the changes made on the system since its first presentation at GREC'2001 are detailed. The obtained results are briefly commented, and the paper finally concludes with some clues for possible, future improvements regarding the system. [ABSTRACT FROM AUTHOR]

Optical Music Recognition consists in the identification of music information from images of scores. In this paper, we propose a method for the early stages of the recognition: segmentation of staff lines and graphical primitives in handwritten scores. After introducing our work with modern musical scores (where projections and Hough Transform are effectively used), an approach to deal with ancient handwritten scores is exposed. The recognition of such these old scores is more difficult due to paper degradation and the lack of a standard in musical notation. Our method has been tested with several scores of 19th century with high performance rates. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel and efficient algorithm for rendering light-emitting fluids such as fire. For this purpose, we extend the well-known photon mapping algorithm for volumetric environments. The photons emitted from the fluids are stored in a voxelized space, instead of k-d tree in the original photon mapping scheme. We further propose an efficient photon collecting algorithm based on Bresenham's algorithm, which can collect photons in reduced computational loads. We prove the effectiveness and efficiency of the proposed algorithm by visualizing light-emitting fluids such as fire in various styles. [ABSTRACT FROM AUTHOR]

This paper presents the design and development of a web-based interface for the visualization of high dimensional data such as microarray data. A co-ordinate based method, namely, 3D Star Coordinate (3SC) projection technique is used for the visualization. The proposed web-based interface enables the user to choose an existing dataset from the database or upload a dataset and visualize the best possible projection of the data on an applet running on the client web browser. The proposed projection algorithm runs in Matlab at the server side for faster computation and using Java Servlets the results are delivered to the client machine. Keywords: Data Projection, Web-based Interface, Coordinate-based & Axis-based Visualization, Dimensionality Reduction and Data Integration. [ABSTRACT FROM AUTHOR]

Applying advanced video technology to understand human activity and intent is becoming increasingly important for video surveillance. In this paper, we perform automatic activity recognition by classification of spatial temporal features from video sequence. We propose to incorporate class labels information to find optimal heating time for dimensionality reduction using diffusion via random walks. We perform experiments on real data, and compare the proposed method with existing random walk diffusion map method and dual root minimal spanning tree diffusion method. Experimental results show that our proposed method is better. [ABSTRACT FROM AUTHOR]

Detecting regions of interest in video sequences is one of the most important tasks in many high level video processing applications. In this paper a novel approach based on support vector data description is presented, which detects foreground regions in videos with quasi-stationary backgrounds. The main contribution of this paper is the novelty detection approach which automatically segments video frames into background/foreground regions. By using support vector data description for each pixel, the decision boundary for the background class is modeled without the need to statistically model its probability density function. The proposed method is able to achieve very accurate foreground region detection rates even in very low contrast video sequences, and in the presence of quasi-stationary backgrounds. As opposed to many statistical background modeling approaches, the only critical parameter that needs to be adjusted in our method is the number of background training frames. [ABSTRACT FROM AUTHOR]

This paper addresses some properties of G1 continuity conditions between two B-spline surfaces with arbitrary degrees and generally structured knots. Key issues addressed in the paper include necessary G1 continuity conditions between two B-spline surfaces, general connecting functions, continuities of the general connecting functions, and intrinsic conditions of the general connecting functions along the common boundary. In general, one may use piecewise polynomial functions, i.e. B-spline functions, as connecting functions for G1 connection of two B-spline surfaces. Based on the work reported in this paper, some recent results in literature using linear connecting functions are special cases of the general connecting functions reported in this paper. In case that the connecting functions are global linear functions along the common boundary commonly used in literature, the common boundary degenerates as a Bézier curve for proper G1 connection. Several examples for connecting two uniform biquadratic B-spline surfaces with G1 continuity are also presented to demonstrate the results. [ABSTRACT FROM AUTHOR]