Problem Of Object Recognition Research Articles

A System for Environment Recognition by Multiple Mobile Robots with Monocular Cameras under Human Supervision

In this paper, we propose an environment recognition method for operation of multiple mobile robots. Until now, we have been developing a system for multiple mobile robot operation by a single human user. In order that the user operates multiple robots appropriately, he/she must know information of an environment around the robots. Hence we build a virtual environment and show it to the user. To build the virtual environment, we must solve two problems ; one is an object recognition problem and the other is a robot-positioning problem. Concerning the former issue, the two robots that equip a monocular camera on each acquire a 3-dimensional position of a point in an environment with a stereo vision method. As for the latter issue, we set markers on the robots by which the robots can measure their relative positions. In each phase mentioned above, the human user gives commands to the robots appropriately. Solving the above problems, we can make a virtual environment in the computer. The virtual environment displays remote site information to the user. We verified effectiveness of the proposed method by experiments.

Using an ICA representation of local color histograms for object recognition

This paper applies a Bayesian classification scheme to the problem of object recognition through probabilistic modeling of local color histograms. In this context, the density estimation is generally performed via nonparametric kernel methods and the high dimensionality does not allow precision in the results. We propose a local independent component analysis (ICA) representation of the data. Within this representation, the components can be assumed statistically independent and, for this particular problem, sparsity of the independent components is observed. We show how these two characteristics simplify and add accuracy to the density estimation and develop a Bayesian decision scheme within this representation. We propose a set of possible density estimations for supergaussian densities, the density type associated with a sparse representation. Two experiments were performed. The first one illustrates the properties of the ICA representation for local color histograms. The second experiment tests the ICA classification model for a large set of pharmaceutical products and compares this scheme with a nonparametric technique based on Gaussian Kernels, two nearest-neighbor techniques and global histogram approach.

Invariant object recognition in the visual system with novel views of 3D objects.

To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.

Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class

The classical way of attempting to solve the face (or object) recognition problem is by using large and representative data sets. In many applications, though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate for imprecisely localized, partially occluded, and expression-variant faces even when only one single training sample per class is available to the system. To solve the localization problem, we find the subspace (within the feature space, e.g., eigenspace) that represents this error for each of the training images. To resolve the occlusion problem, each face is divided into k local regions which are analyzed in isolation. In contrast with other approaches where a simple voting space is used, we present a probabilistic method that analyzes how "good" a local match is. To make the recognition system less sensitive to the differences between the facial expression displayed on the training and the testing images, we weight the results obtained on each local area on the basis of how much of this local area is affected by the expression displayed on the current test image.

Using relaxation technique for region-based object recognition

Abstract We address the problem of object recognition in computer vision. We represent each model and the scene in the form of attributed relational graph (ARG). A multiple region representation is provided at each node of the scene ARG to increase the representation reliability. The process of matching the scene ARG against the stored models is facilitated by a novel method for identifying the most probable representation from among the multiple candidates. The scene and model graph matching is accomplished using probabilistic relaxation which has been modified to minimise the label clutter. The experimental results obtained on real data demonstrate promising performance of the proposed recognition system.

Learning to recognize three-dimensional objects.

A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability. The key assumption underlying this work is that objects can be recognized (or discriminated) using simple representations in terms of syntactically simple relations over the raw image. Although the potential number of these simple relations could be huge, only a few of them are actually present in each observed image, and a fairly small number of those observed are relevant to discriminating an object. We show that these properties can be exploited to yield an efficient learning approach in terms of sample and computational complexity within the PAC model. No assumptions are needed on the distribution of the observed objects, and the learning performance is quantified relative to its experience. Most important, the success of learning an object representation is naturally tied to the ability to represent it as a function of some intermediate representations extracted from the image. We evaluate this approach in a large-scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Library. Experimental results exhibit good generalization and robustness properties of the SNoW-based method relative to other approaches. SNoW's recognition rate degrades more gracefully when the training data contains fewer views, and it shows similar behavior in some preliminary experiments with partially occluded objects.

Representation and Recognition of 3D Free-Form Objects

Mamic, G., and Bennamoun, M., Representation and Recognition of 3D Free-Form Objects, Digital Signal Processing 12 (2002) 47–76 The problem of 3D object recognition has been one that has perplexed the computer vision community for the past two decades. This paper describes and analyzes techniques which have been developed for object representation and recognition. A set of specifications, which all object recognition systems should strive to meet, forms the basis upon which this critical review has been formulated. The literature indicates that there is a powerful requirement for a precise and accurate representation, which is simultaneously concise in nature. Such a representation must be relatively inexpensive and provide a means for determining the error in the surface fit such that the effects of error propagation may be analyzed in the system and appropriate confidence bounds determined in the subsequent pose estimation.

Partially Occluded Object Recognition Using Statistical Models

In this paper, we present a new Bayesian framework for partially occluded object recognition based on matching extracted local features on a one-to-one basis with object features. We introduce two different statistical models for occlusion: one model assumes that each feature in the model can be occluded independent of whether any other features are occluded, whereas the second model uses spatially correlated occlusion to represent the extent of occlusion. Using these models, the object recognition problem reduces to finding the object hypothesis with largest generalized likelihood. We develop fast algorithms for finding the optimal one-to-one correspondence between scene features and object features to compute the generalized likelihoods under both models. We conduct experiments illustrating the differences between the two occlusion models using different quantitative metrics. We also evaluate the recognition performance of our algorithms using examples extracted from object silhouettes and synthetic aperture radar imagery, and illustrate the performance advantages of our approach over alternative algorithms.

Visual Tracking and Object Recognition

In this paper, we will discuss the closely related problems of visual tracking and object recognition. The solution involves adaptive and robust control in conjunction with multiscale methods from signal processing, and shape recognition theory from computer vision. We should note that the problem of visual tracking differs from standard tracking problems in that the feedback signal is measured using imaging sensors. In particular, it has to be extracted via computer vision algorithms and interpreted by a reasoning algorithm before being used in the control loop. Recognition will be accomplished using a novel invariant theoretic approach to shape analysis.

Robust scene recognition using a GA and real-world raw-image

This paper presents a new concept of scene recognition by a genetic algorithm (GA), using the 2-D gray-scale image of a working space, termed here as raw-image, and a model shaping the 2-D top-surface of a target object. In fact here, the problem of object recognition in the raw-image is changed into an optimization problem of a model-based evaluation function. We make use in this research of a GA, as a search and optimization method. This GA employs a model-based fitness function as its objective function to perform the search of a target in the raw-image. In this research, three object models, namely a frame model, a surface model, and a surface-strips model are investigated in order to determine which one is the best for scene recognition in a noisy environment. Also, in order to appraise the recognition performance of each model, a comparative study is performed by analyzing the answers to the following criteria questions: sensitivity, reliability, and speed. The effectiveness of the method has been verified through experiments using real-world raw-images, and the method has shown its robustness of object recognition with the surface-strips model, in spite of the noises in the scene.

A NOVEL PROBABILISTIC MODEL FOR OBJECT RECOGNITION AND POSE ESTIMATION

In this paper we consider the problem of object recognition and localization in a probabilistic framework. An object is represented by a parametric probability density, and the computation of pose parameters is implemented as a nonlinear parameter estimation problem. The presence of a probabilistic model allows for recognition according to Bayes rule. The introduced probabilistic model requires no prior segmentation but characterizes the statistical properties of observed intensity values in the image plane. A detailed discussion of the applied theoretical framework is followed by a concise experimental evaluation which demonstrates the benefit of the proposed approach.

Model-based recognition of 3D objects from single images

In this work, we treat major problems of object recognition which have received relatively little attention lately. Among them are the loss of depth information in the projection from a 3D object to a single 2D image, and the complexity of finding feature correspondences between images. We use geometric invariants to reduce the complexity of these problems. There are no geometric invariants of a projection from 3D to 2D. However, given certain modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions can be either a particular model or a generic assumption about a class of models. Here, we use such assumptions for single-view recognition. We find algebraic relations between the invariants of a 3D model and those of its 2D image under general projective projection. These relations can be described geometrically as invariant models in a 3D invariant space, illuminated by invariant light rays, and projected onto an invariant version of the given image. We apply the method to real images.

Probabilistic Methods for Finding People

Finding people in pictures presents a particularly difficult object recognition problem. We show how to find people by finding candidate body segments, and then constructing assemblies of segments that are consistent with the constraints on the appearance of a person that result from kinematic properties. Since a reasonable model of a person requires at least nine segments, it is not possible to inspect every group, due to the huge combinatorial complexity. We propose two approaches to this problem. In one, the search can be pruned by using projected versions of a classifier that accepts groups corresponding to people. We describe an efficient projection algorithm for one popular classifier, and demonstrate that our approach can be used to determine whether images of real scenes contain people. The second approach employs a probabilistic framework, so that we can draw samples of assemblies, with probabilities proportional to their likelihood, which allows to draw human-like assemblies more often than the non-person ones. The main performance problem is in segmentation of images, but the overall results of both approaches on real images of people are encouraging.

Joint Invariant Signatures

A new, algorithmic theory of moving frames is applied to classify joint invariants and joint differential invariants of transformation groups. Equivalence and symmetry properties of submanifolds are completely determined by their joint signatures, which are parametrized by a suitable collection of joint invariants and/or joint differential invariants. A variety of fundamental geometric examples are developed in detail. Applications to object recognition problems in computer vision and the design of invariant numerical approximations are indicated.

Global shape invariants: a solution for 3D free-form object discrimination/identification problem

A method for solving the 3D object recognition problem is described in this paper. The method uses a new set of global features as discriminant parameters. The general purpose of our approach is to achieve simplicity, speed and efficiency by using global invariants. For this, two new global parameters are introduced, which are invariant to rotation, translation and scaling: canonical length (CL), which provides an indirect measurement of object surface and weighted principal directions (WPDs) corresponding to the meaningful normal directions of the object surface. Abundant experimentation has been conducted with a real world system in order to validate the method.

Assortment of Materials Due to Visual Characteristics by a Robotic ARM

This paper presents a live application of a robust, fast, cost effective and an integratable subsystem solution for the object recognition problems in industrial applications. The well defined moment invariants are used for acquiring rotation, tranlation and size independent features from the image of the objects. For classification minimum distance classifier is used with an adaptive radius of cluster for unknown objects.

Object Recognition in Digital Photogrammetry

Object recognition and image understanding have increasingly become major subjects of interest for research activity in digital photogrammetry. This paper provides an overview of object recognition in photogrammetry, beginning with a problem statement and brief paradigm description. In order to exemplify the concept, automatic interior orientation is presented as an object recognition problem. Subsequent sections discuss the current status of object recognition by identifying relevant criteria, such as modelling, system strategies and inference components. Such criteria are useful for comparing object recognition systems or proposed approaches. Strengths and weaknesses of current systems are summarized, followed by a more detailed analysis of the modelling problem. Finally, two new approaches (scale‐space and fusion of multisensor/multispectral data) are mentioned. These approaches serve as examples of promising new trends which have the potential of advancing object recognition to a new level.

A Perceptual Grouping Hierarchy for Appearance-Based 3D Object Recognition

In this paper we consider the problem of 3D object recognition and the role that perceptual grouping processes must play. In particular, we argue that reliance on a single level of perceptual grouping is inadequate, since it is responsible for the specific weaknesses of several well-known recognition techniques. Instead, recognition must use a hierarchy of perceptual grouping processes. We describe an appearance-based system that uses four distinct levels of perceptual grouping to represent 3D objects in a form that allows not only recognition, but reasoning about 3D manipulation of a sort that has been supported in the past only by 3D geometric models. The results of the algorithms have been previously reported, and the main contribution of this paper is the development of the perceptual organization hierarchy.

Projective Shape Analysis

Emulating human vision, computer vision systems aim to recognize object shape from images. The main difficulty in recognizing objects from images is that the shape depends on the viewpoint. This difficulty can be resolved by using projective invariants to describe the shape. For four colinear points the cross-ratio is the simplest statistic that is invariant to projective transformations. Five coplanar sets of points can be described by two independent cross-ratios. Using the six-fold set of symmetries of the cross-ratio, corresponding to six permutations of the points, we introduce an inverse stereographic projection of the linear cross-ratio (c) to a stereographic cross-ratio (ξ). To exploit this symmetry, we study the distribution of cos 3ξ when the four points are randomly distributed under appropriate distributions and find the mapping of the cross-ratio so that the distribution of ξ is uniform. These mappings provide a link between projective invariants and directional statistics so that well-established techniques of directional statistics can be used. For example, the goal in object recognition could be to determine whether there is a “false” alarm. We show that the testing of false alarm with a possible specific alternative can be reduced to testing the hypotheses of uniformity on the circle. Furthermore, the goals of the analysis in machine vision might be to discriminate among objects. In such cases the cross-ratio will be expected not to be too variable—that is, concentrated. We show that the analysis of variance type identity is shown to hold for concentrated cross-ratios under maps up to angles. We apply our results to an object recognition problem involving both collinear and coplanar sets of points. A characterization of projective shape spaces is also given.

Shape representation and recognition based on invariant unary and binary relations

The problem of transformation invariant object recognition is considered. We develop a projective transformation invariant representation for both scene and model which facilitates an attributed relational graph object matching based only on unary and binary relations. The unary and binary measurements used for matching are derived from sets of reference points such as corners and bi-tangent points which are stable under the various transformations considered. Each set of reference points is used to generate a distinct barycentric coordinate basis system associated with one node of the object graph representation. We show that barycentric coordinates of the reference image points can be made invariant under any arbitrary projective transformation. The conditions that must hold for a basis to be valid are stated. We illustrate the construction of the barycentric coordinate systems for the affine and perspective transformations. For the object and scene representation we use the barycentric coordinates of the reference points generating the barycentric coordinate system, together with auxiliary measurements such as colour and texture as the node's unary measurements. For binary measurements we use the product of the barycentric coordinate system for one node with the inverse of the barycentric coordinate system associated with another node. The unary and binary relations provide an orthogonal decomposition of the shape being matched. They are used in a relaxation process to detect instances of objects consistent with a given model. We demonstrate the proposed methodology of projective transformation invariant object representation on several examples. First we illustrate the stability of the shape representation in terms of unary relations both visually and numerically. We then experimentally demonstrated the invariance of binary relations on a star-like object. We show experimentally that the binary relations derived are invariant. The final example demonstrates the proposed approach as a tool for 3D object recognition. The aim is to recognize 3D objects in terms of planar faces. A hexagonal model shape is hypothesized in the image. The only instance of the hypothesized model is successfully recovered.