Car plate recognition by whole 2-D image

This study did not extract the characters in the car plate separately. Instead, a whole 2-D car plate was processed as an entity; subsequently, it was recognized. In this study a ring-to-line mapping technique is used to map a car plate image to several straight-line signals. Moreover, the vector magnitude invariant transform technique is used to transfer a car plate signal to an invariant vector magnitude for comparison, a procedure that can solve the image-rotation problem. Various vertical magnitude strips are generated to manage the image-shifting problem. The algorithm developed in this study can precisely identify car plate images.     

A fast algorithm for computing moments of gray images based on NAM and extended shading approach

Computing moments on images is very important in the fields of image processing and pattern recognition. The non-symmetry and anti-packing model (NAM) is a general pattern representation model that has been developed to help design some efficient image representation methods. In this paper, inspired by the idea of computing moments based on the S-Tree coding (STC) representation and by using the NAM and extended shading (NAMES) approach, we propose a fast algorithm for computing lower order moments based on the NAMES representation, which takes O(N) time where N is the number of NAM blocks. By taking three idiomatic standard gray images ‘Lena’, ‘F16’, and ‘Peppers’ in the field of image processing as typical test objects, and by comparing our proposed algorithm with the conventional algorithm and the popular STC representation algorithm for computing the lower order moments, the theoretical and experimental results presented in this paper show that the average execution time improvement ratios of the proposed NAMES approach over the STC approach, and also the conventional approach are 26.63%, and 82.57% respectively while maintaining the image quality.     

Semantic Vector Models and Functional Models for Pregroup Grammars

We show that vector space semantics and functional semantics in two-sorted first order logic are equivalent for pregroup grammars. We present an algorithm that translates functional expressions to vector expressions and vice-versa. The semantics is compositional, variable free and invariant under change of order or multiplicity. It includes the semantic vector models of Information Retrieval Systems and has an interior logic admitting a comprehension schema. A sentence is true in the interior logic if and only if the ‘usual’ first order formula translating the sentence holds. The examples include negation, universal quantifiers and relative pronouns.     

A pseudo-sensitivity based discrete-variable approach to structural topology optimization with multiple materials

An algorithm has been developed which uses material as a discrete variable in multi-material topology optimization and thus provides an alternative to traditional methods using material interpolation and level-set approaches. The algorithm computes ‘pseudo-sensitivities’ of the objective and constraint functions to discrete material changes. These are used to rank elements, based on which a fraction of elements are selected for material ID modification during the optimization iteration. The algorithm is of general applicability and avoids frequent matrix factorizations so that it is applicable to large structural problems. In addition to the conventionally used evolutionary and morphogenesis approaches for iteration, a new iteration scheme of ‘resubstitution’ which combines the two approaches is presented. The application and functioning of the algorithm is demonstrated through case studies and comparisons with a few benchmark problems, showing its capability in providing mass-optimal topologies under stiffness constraints for various structural problems where multiple materials are considered.     

A linear algorithm for the pos/neg-weighted 1-median problem on a cactus

The 1-median problem on a network asks for a vertex minimizing the sum of the weighted shortest path distances from itself to all other vertices, each associated with a certain positive weight. We allow fornegative weights as well and devise an exact algorithm for the resulting ‘pos/neg-weighted’ problem defined on a cactus. The algorithm visits every vertex just once and runs thus in linear time. This research has been supported by the Spezialforschungsbereich F 003 ‘Optimierung und Kontrolle’, Projektbereich Diskrete Optimierung.     

Robust classification of arbitrary object classes based on hierarchical spatial feature-matching

We present a novel approach to the robust classification of arbitrary object classes in complex, natural scenes. Starting from a re-appraisal of Marr's ‘primal sketch’, we develop an algorithm that (1) employs local orientations as the fundamental picture primitives, rather than the more usual edge locations, (2) retains and exploits the local spatial arrangement of features of different complexity in an image and (3) is hierarchically arranged so that the level of feature abstraction increases at each processing stage. The resulting, simple technique is based on the accumulation of evidence in binary channels, followed by a weighted, non-linear sum of the evidence accumulators. The steps involved in designing a template for recognizing a simple object are explained. The practical application of the algorithm is illustrated, with examples taken from a broad range of object classification problems. We discuss the performance of the algorithm and describe a hardware implementation. First successful attempts to train the algorithm, automatically, are presented. Finally, we compare our algorithm with other object classification algorithms described in the literature.     

Visual Acuity in Day for Night

In film production, it is sometimes not convenient or directly impossible to shoot some night scenes at night. The film budget, schedule or location may not allow it. In these cases, the scenes are shot at daytime, and the ‘night look’ is achieved by placing a blue filter in front of the lens and under-exposing the film. This technique, that the American film industry has used for many decades, is called ‘Day for Night’ (or ‘American Night’ in Europe.) But the images thus obtained don’t usually look realistic: they tend to be too bluish, and the objects’ brightness seems unnatural for night-light. In this article we introduce a digital Day for Night algorithm that achieves very realistic results. We use a set of very simple equations, based on real physical data and visual perception experimental data. To simulate the loss of visual acuity we introduce a novel diffusion Partial Differential Equation (PDE) which takes luminance into account and respects contrast, produces no ringing, is stable, very easy to implement and fast. The user only provides the original day image and the desired level of darkness of the result. The whole process from original day image to final night image is implemented in a few seconds, computations being mostly local.     

Color Subspaces as Photometric Invariants

Complex reflectance phenomena such as specular reflections confound many vision problems since they produce image ‘features’ that do not correspond directly to intrinsic surface properties such as shape and spectral reflectance. A common approach to mitigate these effects is to explore functions of an image that are invariant to these photometric events. In this paper we describe a class of such invariants that result from exploiting color information in images of dichromatic surfaces. These invariants are derived from illuminant-dependent ‘subspaces’ of RGB color space, and they enable the application of Lambertian-based vision techniques to a broad class of specular, non-Lambertian scenes. Using implementations of recent algorithms taken from the literature, we demonstrate the practical utility of these invariants for a wide variety of applications, including stereo, shape from shading, photometric stereo, material-based segmentation, and motion estimation.     

Object Recognition Based on Human Saccadic Behaviour

The automated recognition of targets in complex backgrounds is a difficult problem, yet humans perform such tasks with ease. We therefore propose a recognition model based on behavioural and physiological aspects of the human visual system. Emulating saccadic behaviour, an object is first memorised as a sequence of fixations. At each fixation an artificial visual field is constructed using a multi-resolution/ orientation Gabor filterbank, edge features are extracted, and a new saccadic location is automatically selected. When a new image is scanned and a ‘familiar’ field of view encountered, the memorised saccadic sequence is executed over the new image. If the expected visual field is found around each fixation point, the memorised object is recognised. Results are presented from trials in which individual objects were first memorised and then searched for in collages of similar objects acting as distractors. In the different collages, entries of the memorised objects were subjected to various combinations of rotation, translation and noise corruption. The model successfully detected the memorised object in over 93% of the ‘object present’ trials, and correctly rejected collages in over 98% of the trials in which the object was not present in the collage. These results are compared with those obtained using a correlation-based recogniser, and the behavioural model is found to provide superior performance. Received: 15 July 1998?Received in revised form: 24 December 1998?Accepted: 9 February 1999     

Solving certain queueing problems modelled by toeplitz matrices

By using the concept of generating function associated with a Toeplitz matrix, we analyze existence conditions for the probability invariant vector π of certain stochastic semi-infinite Toeplitz-like matrices. An application to the shortest queue problem is shown. By exploiting the functional formulation given in terms of generating functions, we devise a weakly numerically stable algorithm for computing the probability invariant vector π. The algorithm is divided into three stages. At the first stage the zeros of a complex function are numerically computed by means of an extension of the Aberth method. At the second stage the first k components of π are computed by solving an interpolation problem, where k is a suitable constant associated with the matrix. Finally, at the third stage a triangular Toeplitz system is solved and its solution is refined by applying the power method or any other refinement method based on regular splittings. In the solution of the triangular Toeplitz system and at each step of the refinement method, special FFT-based techniques are applied in order to keep the arithmetic cost within the O(n log n) bound, where n is an upper bound to the number of the computed components. Numerical comparisons with the available algorithms show the effectiveness of our algorithm in a wide set of cases.     

Rule-based document structure understanding with a fuzzy combination of layout and textual features

Document image processing is a crucial process in office automation and begins at the ‘OCR’ phase with difficulties in document ‘analysis’ and ‘understanding’. This paper presents a hybrid and comprehensive approach to document structure analysis. Hybrid in the sense that it makes use of layout (geometrical) as well as textual features of a given document. These features are the base for potential conditions which in turn are used to express fuzzy matched rules of an underlying rule base. Rules can be formulated based on features which might be observed within one specific layout object. However, rules can also express dependencies between different layout objects. In addition to its rule driven analysis, which allows an easy adaptation to specific domains with their specific logical objects, the system contains domain-independent markup algorithms for common objects (e.g., lists). Received June 19, 2000 / Revised November 8, 2000     

Practical fast computation of Zernike moments

The fast computation of Zernike moments from normalized gometric moments has been developed in this paper,The computation is multiplication free and only additions are needed to generate Zernike moments .Geometric moments are generated using Hataming‘s filter up to high orders by a very simple and straightforward computaion scheme.Other kings of monents(e.g.,Legendre,pseudo Zernike)can be computed using the same algorithm after giving the proper transformaitons that state their relations to geometric moments.Proper normaliztions of geometric moments are necessary so that the method can be used in the efficient computation of Zernike moments.To ensure fair comparisons,recursive algorithms are used to generate Zernike polynoials and other coefficients.The computaional complexity model and test programs show that the speed-up factor of the proposed algorithm is superior with respect ot other fast and /or direct computations It perhaps is the first time that Zernike moments can be computed in real time rates,which encourages the use of Zernike moment features in different image retrieval systems that support huge databases such as the XM experimental model stated for the MPEG-7 experimental core.It is concluded that choosing direct copmutation would be impractical.     

Towards a natural language semantics without functors and operands

The paper sets out to offer an alternative to the function/argument approach to the most essential aspects of natural language meanings. That is, we question the assumption that semantic completeness (of, e.g., propositions) or incompleteness (of, e.g., predicates) exactly replicate the corresponding grammatical concepts (of, e.g., sentences and verbs, respectively). We argue that even if one gives up this assumption, it is still possible to keep the compositionality of the semantic interpretation of simple predicate/argument structures. In our opinion, compositionality presupposes that we are able to compare arbitrary meanings in term of information content. This is why our proposal relies on an ‘intrinsically’ type free algebraic semantic theory. The basic entities in our models are neither individuals, nor eventualities, nor their properties, but ‘pieces of evidence’ for believing in the ‘truth’ or ‘existence’ or ‘identity’ of any kind of phenomenon. Our formal language contains a single binary non-associative constructor used for creating structured complex terms representing arbitrary phenomena. We give a finite Hilbert-style axiomatisation and a decision algorithm for the entailment problem of the suggested system.     

Kernel Nearest-Neighbor Algorithm

The ‘kernel approach’ has attracted great attention with the development of support vector machine (SVM) and has been studied in a general way. It offers an alternative solution to increase the computational power of linear learning machines by mapping data into a high dimensional feature space. This ‘approach’ is extended to the well-known nearest-neighbor algorithm in this paper. It can be realized by substitution of a kernel distance metric for the original one in Hilbert space, and the corresponding algorithm is called kernel nearest-neighbor algorithm. Three data sets, an artificial data set, BUPA liver disorders database and USPS database, were used for testing. Kernel nearest-neighbor algorithm was compared with conventional nearest-neighbor algorithm and SVM Experiments show that kernel nearest-neighbor algorithm is more powerful than conventional nearest-neighbor algorithm, and it can compete with SVM. This revised version was published online in June 2006 with corrections to the Cover Date.     

The FEM optimization of active vibration control in structures by solving the corresponding two-point-boundary-value problem

An algorithm for solving optimal active vibration control problems by the finite element method (FEM) is presented. The optimality equations for the problem are derived from Pontryagin’s principle in the form of a set of the fourth order ordinary differential equations that, together with the initial and final boundary conditions, constitute the boundary value problem in the time domain, which in control is referred to as a two-point-boundary-value problem. These equations decouple in the modal space and can be solved by the FEM technique. An analogy between the optimality equations and the governing equations for a set of certain static beams permits obtaining numerical solutions to the optimal control problem with the help of standard ‘structural’ FEM software. The optimal action of actuators is automatically calculated by applying the independent modal space control concept. The structure’s response to actuation forces is also determined and can independently be verified for spillover effects. As an illustration, the algorithm is used for the analysis of optimal action of actuators to attenuate vibrations of an elastic fin.     

A visual-inertial servoing method for tracking object with two landmarks and an inertial measurement unit

This paper introduces a robot visual-inertial tracking algorithm for a robot manipulator intended to track an object using inertial sensors incorporated into the object. To create this algorithm, the inertial Jacobian is first newly defined in order to show the relationship between an angle set velocity vector of the object and the angular velocity vector of the robot tip. Then, the inertial Jacobian is combined with the conventional image Jacobian. Therefore, the proposed algorithm requires only two landmarks with the help of an inertial measurement unit to track a moving object with six degrees of freedom, while at least three landmarks are required in the conventional stereo visual servoing algorithm. Further, the possession of a multi-rate controller allows the integration system to out-perform conventional systems in the tracking of an object’s attitude change. A suggested application of the proposed method is tracking and selection of a container from a shipping vessel that is being affected by large waves. Simulations and experiments were conducted to verify the feasibility of the proposed methodology.     

Impact of object extraction methods on classification performance in surface inspection systems

In surface inspection applications, the main goal is to detect all areas which might contain defects or unacceptable imperfections, and to classify either every single ‘suspicious’ region or the investigated part as a whole. After an image is acquired by the machine vision hardware, all pixels that deviate from a pre-defined ‘ideal’ master image are set to a non-zero value, depending on the magnitude of deviation. This procedure leads to so-called “contrast images”, in which accumulations of bright pixels may appear, representing potentially defective areas. In this paper, various methods are presented for grouping these bright pixels together into meaningful objects, ranging from classical image processing techniques to machine-learning-based clustering approaches. One important issue here is to find reasonable groupings even for non-connected and widespread objects. In general, these objects correspond either to real faults or to pseudo-errors that do not affect the surface quality at all. The impact of different extraction methods on the accuracy of image classifiers will be studied. The classifiers are trained with feature vectors calculated for the extracted objects found in images labeled by the user and showing surfaces of production items. In our investigation artificially created contrast images will be considered as well as real ones recorded on-line at a CD imprint production and at an egg inspection system.     

An informational divergence geometry for stochastic matrices

Summary The informational divergence between stochastic matrices is not a metric. In this paper we show that, however, consistent definitions can be given of ‘spheres’, ‘segments’ and ‘straight lines’ using the divergence as a sort of ‘distance’ between stochastic matrices. The geometric nature of many ‘reliability functions’ of Information Theory and Mathematical Statistics is thus clarified. This work has been done within the GNIM-CNR research activity.     

一种起始点无关的小波系数形状匹配

小波变换的多分辨率特征使其在计算机视觉中得到广泛的应用,在形状匹配中,小波变换对起始点的依赖制约了小波变换的应用。为了克服小波变换对起始点的依赖,引入Zernike矩,提出一种起始点无关的小波系数形状匹配算法。对输入图像进行预处理后提取目标轮廓,生成具有平移、尺度不变的形状链状表达,并通过小波变换进行多尺度分析。最后计算各个尺度下的各阶Zernike矩,来解决小波变换的起始点问题,实现形状表达的旋转不变性。实验结果表明该算法适用于轮廓较明显的目标,同时具有速度快、精度高、鲁棒性强的优点。