Learning relational structures: Applications in computer vision

We present and compare two new techniques for learning Relational Structures (RSs) as they occur in 2D pattern and 3D object recognition. These techniques, namely, Evidence-Based Networks (EBS-NNets) and Rulegraphs combine techniques from computer vision with those from machine learning and graph matching. The EBS-NNet has the ability to generalize pattern rules from training instances in terms of bounds on both unary (single part) and binary (part relation) numerical features. It also learns the compatibilities between unary and binary feature states in defining different pattern classes. Rulegraphs check this compatibility between unary and binary rules by combining evidence theory with graph theory. The two systems are tested and compared using a number of different pattern and object recognition problems.     

Application of 3-D models to computer vision

A flexible computer vision is described which is able to recognize 3-D objects if their models are given. The models can be built in a CAD process using a geometric modeler GEOMAP. Three cases are studied: surface normals are available, a part of surface normals are available, and range data is available. In order to perform efficient matching, three methods are proposed for those cases: use of EGI representation, use of relative angles between surface normals, and use of kernels.     

Fuzzy set theoretic interpretation of object shape and relational properties for computer vision

The computation of various geometrical and topological properties of objects, as well as the inter-relationships among them, is useful and important in image processing and computer vision problems. Many of these properties and relations are ill-defined and presented here are some approaches to define them using fuzzy set theoretic concepts. It is assumed that the objects are segmented into a two-tone mask from a grey tone image. The properties considered are bigness, position, convexity, circularity, elongatedness, straightness and angular orientation. The relationships considered are relative position, relative orientation, degree of surroundedness and the degree of between ness. A man-machine interaction based on these proper-lies is also proposed and illustrative examples of the results of executed algorithms are presented.     

Estimation of nonlinear errors-in-variables models for computer vision applications

In an errors-in-variables (EIV) model, all the measurements are corrupted by noise. The class of EIV models with constraints separable into the product of two nonlinear functions, one solely in the variables and one solely in the parameters, is general enough to represent most computer vision problems. We show that the estimation of such nonlinear EIV models can be reduced to iteratively estimating a linear model having point dependent, i.e., heteroscedastic, noise process. Particular cases of the proposed heteroscedastic errors-in-variables (HEIV) estimator are related to other techniques described in the vision literature: the Sampson method, renormalization, and the fundamental numerical scheme. In a wide variety of tasks, the HEIV estimator exhibits the same, or superior, performance as these techniques and has a weaker dependence on the quality of the initial solution than the Levenberg-Marquardt method, the standard approach toward estimating nonlinear models.     

计算视觉核心问题:自然图像先验建模研究综述

视觉先验是计算机视觉的核心问题之一,是认知心理层面、系统神经层面与计算视觉层面研究的交合点,涉及各个层面研究的理解与综合。视觉先验功能模拟方面,以自然图像信息为对象,挖掘自然图像一般性规律并将其数学形式化为可计算的图像模型,为众多图像处理与计算机视觉智能应用提供算法和支撑。本文对自然图像先验建模研究各流派工作进行了全面的剖析,并展示了自然图像先验建模工作在视觉信息增强和编码等方向的前瞻性应用。     

Shaped lattice graphs as models of the multiprocessor computer systems

A new family of the uniform ordinary graphs named the shaped lattice graphs was proposed and studied. As applied to the structural modeling of the multiprocessor computer systems, they have two useful characteristics such as high flexibility at choosing their size (number of vertices) and possibility of obtaining small (down to d = 2) diameters independently of the graph size. The method of cycle definition and transformation by the ring sequences of edge weights, which was previously proposed for the binary hypercubes and other Cayley graphs, was extended to the shaped lattice graphs.Translated from Avtomatika i Telemekhanika, No. 3, 2005, pp. 169–180.Original Russian Text Copyright © 2005 by Parkhomenko.This paper was recommended for publication by P.Yu. Chebotarev, a member of the Editorial Board     

Feature recognition from CAD models

This article presents a system dubbed IF² (Integrated Incremental Feature Finder), which functions as a feature recognizer or a feature model converter depending on whether the input CAD data contains design features. IF² recognizes three types of machining features: holes, slots and pockets. This article discusses recognition algorithms for slots and pockets. Recognition algorithms for holes are similar to those of slots (Han, 1996)     

Algorithmic differentiation: application to variational problems in computer vision

Many vision problems can be formulated as minimization of appropriate energy functionals. These energy functionals are usually minimized, based on the calculus of variations (Euler-Lagrange equation). Once the Euler-Lagrange equation has been determined, it needs to be discretized in order to implement it on a digital computer. This is not a trivial task and, is moreover, error- prone. In this paper, we propose a flexible alternative. We discretize the energy functional and, subsequently, apply the mathematical concept of algorithmic differentiation to directly derive algorithms that implement the energy functional's derivatives. This approach has several advantages: First, the computed derivatives are exact with respect to the implementation of the energy functional. Second, it is basically straightforward to compute second-order derivatives and, thus, the Hessian matrix of the energy functional. Third, algorithmic differentiation is a process which can be automated. We demonstrate this novel approach on three representative vision problems (namely, denoising, segmentation, and stereo) and show that state-of-the-art results are obtained with little effort.     

计算机视觉中图匹配研究进展: 从二图匹配迈向多图匹配

图匹配试图求解二图或多图之间节点的对应关系.在图像图形领域,图匹配是一个历久弥新的基础性问题.从优化的角度来看,图匹配问题是一个组合优化问题,且在一般情形下具有非确定性多项式复杂程度(non-deter-ministic polynomial, NP)难度的性质.在过去数十年间,出现了大量求解二图匹配的近似算法,并在各个领域得到了较为广泛的应用.然而,受限于优化问题本身的理论困难和实际应用中数据质量的种种限制,各二图匹配算法在匹配精度上的性能日益趋近饱和.相比之下,由于引入了更多信息且往往更符合实际问题的设定,多图的协同匹配则逐渐成为了一个新兴且重要的研究方向.本文首先介绍了经典的二图匹配方法,随后着重介绍近年来多图匹配方法的最新进展和相关工作.最后,本文讨论了图匹配未来的发展.     

Image analysis and computer vision: 1990

This paper presents a bibliography of over 1600 references related to computer vision and image analysis, arranged by subject matter. The topics covered include architectures; computational techniques; feature detection, segmentation, and image analysis; matching, stereo, and time-varying imagery; shape and pattern; color and texture; and three-dimensional scene analysis. A few references are also given on related topics, such as computational geometry, computer graphics, image input/output and coding, image processing, optical processing, visual perception, neural nets, pattern recognition, and artificial intelligence.     

Performance characterization in computer vision: A guide to best practices

It is frequently remarked that designers of computer vision algorithms and systems cannot reliably predict how algorithms will respond to new problems. A variety of reasons have been given for this situation and a variety of remedies prescribed in literature. Most of these involve, in some way, paying greater attention to the domain of the problem and to performing detailed empirical analysis. The goal of this paper is to review what we see as current best practices in these areas and also suggest refinements that may benefit the field of computer vision. A distinction is made between the historical emphasis on algorithmic novelty and the increasing importance of validation on particular data sets and problems.     

Detecting objects in images in real-time computer vision systems using structured geometric models

Methods for designing high-level image processing algorithms for real-time computer vision systems (VS) in which images of objects or their parts can be represented using structured geometric models that have step-like edge features as their primitive elements.     

SkyGraph: an algorithm for important subgraph discovery in relational graphs

A significant number of applications require effective and efficient manipulation of relational graphs, towards discovering important patterns. Some example applications are: (i) analysis of microarray data in bioinformatics, (ii) pattern discovery in a large graph representing a social network, (iii) analysis of transportation networks, (iv) community discovery in Web data. The basic approach followed by existing methods is to apply mining techniques on graph data to discover important patterns, such as subgraphs that are likely to be useful. However, in some cases the number of mined patterns is large, posing difficulties in selecting the most important ones. For example, applying frequent subgraph mining on a set of graphs the system returns all connected subgraphs whose frequency is above a specified (usually user-defined) threshold. The number of discovered patterns may be large, and this number depends on the data characteristics and the frequency threshold specified. It would be more convenient for the user if “goodness” criteria could be set to evaluate the usefulness of these patterns, and if the user could provide preferences to the system regarding the characteristics of the discovered patterns. In this paper, we propose a methodology to support such preferences by applying subgraph discovery in relational graphs towards retrieving important connected subgraphs. The importance of a subgraph is determined by: (i) the order of the subgraph (the number of vertices) and (ii) the subgraph edge connectivity. The performance of the proposed technique is evaluated by using real-life as well as synthetically generated data sets.     

DrawCAD: using deductive object‐relational databases in CAD

Computer‐aided design (CAD) involves the use of computers in the various stages of engineering design. CAD has large volumes of data with complex structures that need to be stored and managed effectively and properly. Database systems provide general purpose programs that can be used to access and manipulate large amounts of data stored in the database. They also provide an independence between the program accessing data and the database. It is therefore important to use database systems to store CAD data in the most efficient and effective manner for easy retrieval and better management. Graphical objects can be created, in CAD, by reusing previously created objects. The data of these objects have references to the other objects they contain. Deductive object‐relational databases not only provide direct support for the effective storage and efficient access to large amounts of data with complex structures on disk, but also perform the inferences and computations to obtain the complete data of graphical objects that reuse other objects. They should be able to play a major role in CAD systems. This is the idea behind the development of the DrawCAD system. DrawCAD is a CAD system built on top of the Relationlog object‐relational deductive database system. It facilitates the creation of graphical objects by reusing previously created objects. The DrawCAD system illustrates how CAD systems can be developed, using database systems to store and manage data and also perform the inferences and computations that are normally performed by the application program. Copyright © 2003 John Wiley & Sons, Ltd.     

DeViouS: A distributed environment for computer vision

Computer vision, owing to the size and complexity of its tasks and its importance to industrial and economic growth, was selected as one of the grand challenge problems by the U.S. Federal High Performance Computing Program. Integration of vision operations is identified as a key element of the challenge. A system to integrate computer vision in a distributed environment is presented here. This system, called DeViouS, is based on the client/server model and runs in a heterogeneous environment of Unix workstations. Modern computing environments include large numbers of high-powered workstations connected by a very fast network. Many of these computers are idle most of the time. DeViouS takes advantage of this feature of computing environments to distribute the execution of vision tasks. Two primary goals of DeViouS are to provide a practical distributed system and a research environment for vision computing. DeViouS is based on a modular design that allows experimentation in various aspects of algorithm design, scheduling and network programming. It can make use of any existing computer vision packages with very minor changes to DeViouS. DeViouS has been tested in an environment of SUN and Digital workstations and has shown substantial improvements in speed over sequential computing with negligible overhead.     

Viz-A-Vis: toward visualizing video through computer vision

In the established procedural model of information visualization, the first operation is to transform raw data into data tables [1]. The transforms typically include abstractions that aggregate and segment relevant data and are usually defined by a human, user or programmer. The theme of this paper is that for video, data transforms should be supported by low level computer vision. High level reasoning still resides in the human analyst, while part of the low level perception is handled by the computer. To illustrate this approach, we present Viz-A-Vis, an overhead video capture and access system for activity analysis in natural settings over variable periods of time. Overhead video provides rich opportunities for long-term behavioral and occupancy analysis, but it poses considerable challenges. We present initial steps addressing two challenges. First, overhead video generates overwhelmingly large volumes of video impractical to analyze manually. Second, automatic video analysis remains an open problem for computer vision.     

Understanding minority costumes: a computer vision perspective

Multimedia Systems - It is an extremely interesting work to understand the minority costumes in computer vision and ethnology community. It explored some crucial clue for understanding minority...     

Investigation of microstrip radial stub CAD models from 2 to 60 GHz

The accuracy of microstrip radial stub computer‐aided design (CAD) models is investigated both experimentally and against electromagnetic simulations. A dual‐resonator technique is used to eliminate confounding variables and to obtain accurate experimental data. This technique is extended beyond the earlier perturbation analysis applied to discontinuities to enable checking models that have significant electrical length. Model phase errors in excess of 16° have been found for the microstrip radial stub. © 2000 John Wiley & Sons, Inc. Int J RF and Microwave CAE 10: 95–107, 2000