the study of handwritten words is tied to the development of recognition methods to be used in real-world applications involving handwritten words, such as bank checks, postal envelopes, and handwritten texts, among o...
详细信息
the study of handwritten words is tied to the development of recognition methods to be used in real-world applications involving handwritten words, such as bank checks, postal envelopes, and handwritten texts, among others. In this work, the focus is handwritten words in the context of brazilian bank checks, specifically the months of the year, and no restrictions are placed on the types or styles of writing or the number of writers. A global feature set and two architectures of artificial neural networks (ANN) are evaluated for classification of the words. the objectives are to evaluate the performance of conventional and class-modular multiple-layer perceptron (MLP) architectures, to develop a rejection mechanism based on multiple thresholds, and to analyze the behavior of the feature set proposed in the two architectures. the experimental results demonstrate the superiority of the class-modular architecture over the conventional MLP architecture. A rejection mechanism with multiple thresholds demonstrates favorable performance in both architectures. the feature set analysis shows the importance of the structural primitives such as concavities and convexities, and perceptual primitives such as ascenders and descenders. the experimental results reveal a recognition rate of 81.75% without the rejection mechanism, and a reliability rate 91.52% with a rejection rate of 25.33%. (c) 2006 Elsevier B.V. All rights reserved.
An image analysis method has been developed to segment yeast cells. Yeasts belong to the taxonomic group fungi and have been used on fuel and food industry, for example. the method is capable of segmenting yeast cells...
详细信息
An image analysis method has been developed to segment yeast cells. Yeasts belong to the taxonomic group fungi and have been used on fuel and food industry, for example. the method is capable of segmenting yeast cells based on Watershed Transform and space-scale analysis of the Tree of Critical Lakes. We analise hierarchical, geometric and gray-scale properties of the Tree of Critical Lakes. We show experimental results for one group of yeast images obtained from the School ofFood Engineering at Unicamp, Brazil. Comparison shows that the proposed method provides cells with area 10% lower than traditional approach. Moreover, this approach preserves the cells contour, an important feature because of the performance of bioreactors and other chemical processes are greatly influenced by their morphological character. (c) 2006 Elsevier B.V. All rights reserved.
Often, it is necessary to evaluate the mid-secretory endometrium appearance in Gynecology. For this purpose, hysteroscopic videos have been used, and are of fundamental importance nowadays for diagnosis/prognosis of s...
详细信息
Often, it is necessary to evaluate the mid-secretory endometrium appearance in Gynecology. For this purpose, hysteroscopic videos have been used, and are of fundamental importance nowadays for diagnosis/prognosis of several uterine pathologies. these videos are continuous (non-interrupted) video sequences, usually recorded in full. However, only a few segments of the recorded videos are relevant for diagnosis/prognosis, and need to be evaluated and referenced later. this paper proposes a new technique to identify clinically relevant segments in diagnostic hysteroscopy videos and, consequently, to find images that present the best view of the endometrium details (e.g. glandular openings and vascularization). Our method produce a rich and compact video summary which supports fast video browsing. this method is based on an extension of known properties of the singular value decomposition (SVD), and it is adaptive, in the sense that it minimizes the need of parameter adjustments. Our preliminary experimental results indicate that our method produces compact video summaries containing a selection of clinically relevant video segments. these experimental results were validated by specialists. (c) 2006 Elsevier B.V. All rights reserved.
the map-seeking circuit (MSC) is an explicit biologically-motivated computational mechanism which provides practical solution of problems in object recognition, image registration and stabilization, limb inverse-kinem...
详细信息
the map-seeking circuit (MSC) is an explicit biologically-motivated computational mechanism which provides practical solution of problems in object recognition, image registration and stabilization, limb inverse-kinematics and other inverse problems which involve transformation discovery. We formulate this algorithm as discrete dynamical system on a set Delta = Pi(L)(l=1)Delta((l)), where each Delta((l)) is a compact subset of a nonnegative orthant of R-n, and show that for an open and dense set of initial conditions in Delta the corresponding solutions converge to either a vector with unique nonzero element in each Delta((l)) or to a zero vector. the first result implies that the circuit finds a unique best mapping which relates reference pattern to a target pattern;the second result is interpreted as "no match found". these results verify numerically observed behavior in numerous practical applications.
We present a novel method for correcting the significance level of hypothesis testing that requires multiple comparisons. It is based on the spectral graph theory, in which the variables are seen as the vertices of a ...
详细信息
We present a novel method for correcting the significance level of hypothesis testing that requires multiple comparisons. It is based on the spectral graph theory, in which the variables are seen as the vertices of a complete undirected graph and the correlation matrix as the adjacency matrix that weights its edges. the method increases the statistical power of the analysis by refuting the assumption of independence among variables, while keeping the probability of false positives low. By computing the eigenvalues of the correlation matrix, it is possible to obtain valuable information about the dependence levels among the variables of the problem, so that the effective number of independent variables can be estimated. the method is compared to other available models and its effectiveness illustrated in case studies involving high-dimensional sets of variables.
We discuss the existence of viscosity solutions for a class of anisotropic level-set methods which can be seen as an extension of the mean-curvature motion with a nonlinear anisotropic diffusion tensor. In an earlier ...
详细信息
We discuss the existence of viscosity solutions for a class of anisotropic level-set methods which can be seen as an extension of the mean-curvature motion with a nonlinear anisotropic diffusion tensor. In an earlier work (Mikula et al. in Comput. Vis. Sci. 6(4):197-209, [2004];Preusser and Rumpf in SIAM J. Appl. Math. 62(5):1772-1793, [2002]) we have applied such methods for the denoising and enhancement of static images and image sequences. the models are characterized by the fact that-unlike the mean-curvature motion-they are capable of retaining important geometric structures like edges and corners of the level-sets. the article reviews the definition of the model and discusses its geometric behavior. the proof of the existence of viscosity solutions for these models is based on a fixed point argument which utilizes a compactness property of the diffusion tensor. For the application to imageprocessing suitable regularizations of the diffusion tensor are presented for which the compactness assumptions of the existence proof hold. Finally, we consider the half relaxed limits of the solutions of auxiliary problems to show the compactness of the solution operator and thus the existence of a solution to the original problem.
the image Foresting Transform (IFT) is a tool for the design of imageprocessing operators based on connectivity, which reduces imageprocessing problems into an optimum-path forest problem in a graph derived from the...
详细信息
the image Foresting Transform (IFT) is a tool for the design of imageprocessing operators based on connectivity, which reduces imageprocessing problems into an optimum-path forest problem in a graph derived from the image. A new image operator is presented, which solves segmentation by pruning trees of the forest. An IFT is applied to create an optimum-path forest whose roots are seed pixels, selected inside a desired object. In this forest, object and background are connected by optimum paths (leaking paths), which cross the object's boundary through its "most weakly connected" parts (leaking pixels). these leaking pixels are automatically identified and their subtrees are eliminated, such that the remaining forest defines the object. Tree pruning runs in linear time, is extensible to multidimensional images, is free of ad hoc parameters, and requires only internal seeds, with little interference from the heterogeneity of the background. these aspects favor solutions for automatic segmentation. We present a formal definition of the obtained objects, algorithms, sufficient conditions for tree pruning, and two applications involving automatic segmentation: 3D MR-image segmentation of the human brain and image segmentation of license plates. Given that its most competitive approach is the watershed transform by markers, we also include a comparative analysis between them.
this paper presents a new method for the precise registration of multiple range images with low pairwise overlap. the method is based in enhanced genetic algorithms (GAs). the proposed technique minimizes the alignmen...
详细信息
this paper presents a new method for the precise registration of multiple range images with low pairwise overlap. the method is based in enhanced genetic algorithms (GAs). the proposed technique minimizes the alignment error within the common overlap area among a set of views, which is computed by a novel robust figure of merit called the surface interpenetration measure (SIM). the key idea behind this measure is the observation that mean squared error alone is insufficient to evaluate the quality of a registration solution because it fails to account for the spatial distribution of the error. the new measure explicitly forces the solution to distribute the errors across the overlap area, producing more stable, reliable solutions that limit propagation and amplification of error in the multiview problem. Our approach is not dependent on GAs as the search mechanism, but because they search in a space of transformations, GAs are capable of registering surfaces with no need for prealignment. the need for prealignment is a major weakness of methods based on the iterative closest point (ICP) algorithm, the most popular family of methods to date. the experimental results confirm that the new method ensures more precise global alignments than combined sequential pairwise alignments for registration. (c) 2006 Elsevier B.V. All rights reserved.
Generalized rigid and generalized affine registration and interpolation obtained by finite displacements and by optical flow are here developed variationally and numerically as well as with respect to a geometric mult...
详细信息
Generalized rigid and generalized affine registration and interpolation obtained by finite displacements and by optical flow are here developed variationally and numerically as well as with respect to a geometric multigrid solution process. For high order optimality systems under natural boundary conditions, it is shown that the convergence criteria of Hackbusch (Iterative Solution of Large Sparse Systems of Equations. Springer, Berlin, 1993) are met. Specifically, the Galerkin formalism is used together with a multi-colored ordering of unknowns to permit vectorization of a symmetric successive over-relaxation on imageprocessing systems. the geometric multigrid procedure is situated as an inner iteration within an outer Newton or lagged diffusivity iteration, which in turn is embedded within a pyramidal scheme that initializes each outer iteration from predictions obtained on coarser levels. Differences between results obtainable by finite displacements and by optical flows are elucidated. Specifically, independence of image order can be shown for optical flow but in general not for finite displacements. Also, while autonomous optical flows are used in practice, it is shown explicitly that finite displacements generate a broader class of registrations. this work is motivated by applications in histological reconstruction and in dynamic medical imaging, and results are shown for such realistic examples.
We present a novel method for correcting the significance level of hypothesis testing that requires multiple comparisons. It is based on the spectral graph theory, in which the variables are seen as the vertices of a ...
详细信息
We present a novel method for correcting the significance level of hypothesis testing that requires multiple comparisons. It is based on the spectral graph theory, in which the variables are seen as the vertices of a complete undirected graph and the correlation matrix as the adjacency matrix that weights its edges. the method increases the statistical power of the analysis by refuting the assumption of independence among variables, while keeping the probability of false positives low. By computing the eigenvalues of the correlation matrix, it is possible to obtain valuable information about the dependence levels among the variables of the problem, so that the effective number of independent variables can be estimated. the method is compared to other available models and its effectiveness illustrated in case studies involving high-dimensional sets of variables.
暂无评论