A Two-Stage Probabilistic Approach for Object Recognition
02 Jun 1998-pp 733-747
TL;DR: A probabilistic approach for solving the problem of matching and recognizing jigsaw objects under partial occlusion, rotation, translation and scaling using the maximum a posteriori (MAP) principle.
Abstract: Assume that some objects are present in an image but can be seen only partially and are overlapping each other. To recognize the objects, we have to firstly separate the objects from one another, and then match them against the modeled objects using partial observation. This paper presents a probabilistic approach for solving this problem. Firstly, the task is formulated as a two-stage optimal estimation process. The first stage, matching, separates different objects and finds feature correspondences between the scene and each potential model object. The second stage, recognition, resolves inconsistencies among the results of matching to different objects and identifies object categories. Both the matching and recognition are formulated in terms of the maximum a posteriori (MAP) principle. Secondly, contextual constraints, which play an important role in solving the problem, are incorporated in the probabilistic formulation. Specifically, between-object constraints are encoded in the prior distribution modeled as a Markov random field, and within-object constraints are encoded in the likelihood distribution modeled as a Gaussian. They are combined into the posterior distribution which defines the MAP solution. Experimental results are presented for matching and recognizing jigsaw objects under partial occlusion, rotation, translation and scaling.
Citations
More filters
TL;DR: This work uses example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter, and presents with a novel image.
Abstract: We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime.
67 citations
01 Jan 2002
TL;DR: This work frames the problem of object recognition from edge cues in terms of determining whether individual edge pixels belong to the target object or to clutter, based on the configuration of edges in their vicinity, and applies a cascade of classifiers to the image to save computation and solve the aperture problem.
Abstract: We frame the problem of object recognition from edge cues in terms of determining whether individual edge pixels belong to the target object or to clutter, based on the configuration of edges in their vicinity A classifier solves this problem by computing sparse, localized edge features at image locations determined at training time In order to save computation and solve the aperture problem, we apply a cascade of these classifiers to the image, each of which computes edge features over larger image regions than its predecessors Experiments apply this approach to the recognition of real objects with holes and wiry components in cluttered scenes under arbitrary out-of-image-plane rotation 1
45 citations
Cites background from "A Two-Stage Probabilistic Approach ..."
...In [10], a joint Gaussian model of feature locations is assumed; similarly, other recognition approaches assume that the distribution of object features in an image can be described by a Markov random field [24][7][25] or an object-specific model such as a body plan[14]....
[...]
18 Jun 2003
TL;DR: This work uses example images of the desired object in typical backgrounds to train a classifier cascade which determines whether edge pixels in an image belong to an instance of the object or the clutter, and uses the cascade to discard clutter edge pixels.
Abstract: We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge cues. We first use example images of the desired object in typical backgrounds to train a classifier cascade which determines whether edge pixels in an image belong to an instance of the object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels. The features used for this classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of complex objects in cluttered indoor scenes under arbitrary out-of-image-plane rotation.
41 citations
TL;DR: A bibliography of over 2250 references related to computer vision and image analysis, arranged by subject matter is presented, covering topics including computational techniques; feature detection and segmentation; image and scene analysis; and motion.
37 citations
01 Nov 2016
TL;DR: An approach to the automatic detection and identification of important elements in paper documents, which includes stamps, logos, printed text blocks, signatures and tables, using AdaBoost cascade of weak classifiers and Haar-like features is presented.
Abstract: In the paper we present an approach to the automatic detection and identification of important elements in paper documents. This includes stamps, logos, printed text blocks, signatures and tables. Presented approach consists of two stages. The first one includes object detection by means of AdaBoost cascade of weak classifiers and Haar-like features. Resulting image blocks are, at the second stage, subjected to verification based on selected features calculated from recently proposed low-level descriptors combined with certain classifiers representing current machine-learning approaches. The training phase, for both stages, uses bootstrapping, i.e., integrative process, aiming at increasing the accuracy. Experiments performed on large set of digitized paper documents showed that adopted strategy is useful and efficient.
16 citations
Cites background from "A Two-Stage Probabilistic Approach ..."
...Similar ideas have been applied mostly to the problems of object detection, extraction and classification in other classes of digital images [24]....
[...]
References
More filters
TL;DR: There is a deep and useful connection between statistical mechanics and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters), and a detailed analogy with annealing in solids provides a framework for optimization of very large and complex systems.
Abstract: There is a deep and useful connection between statistical mechanics (the behavior of systems with many degrees of freedom in thermal equilibrium at a finite temperature) and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters). A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems. This connection to statistical mechanics exposes new information and provides an unfamiliar perspective on traditional optimization problems and methods.
41,772 citations
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Abstract: We make an analogy between images and statistical mechanics systems. Pixel gray levels and the presence and orientation of edges are viewed as states of atoms or molecules in a lattice-like physical system. The assignment of an energy function in the physical system determines its Gibbs distribution. Because of the Gibbs distribution, Markov random field (MRF) equivalence, this assignment also determines an MRF image model. The energy function is a more convenient and natural mechanism for embodying picture attributes than are the local characteristics of the MRF. For a range of degradation mechanisms, including blurring, nonlinear deformations, and multiplicative or additive noise, the posterior distribution is an MRF with a structure akin to the image model. By the analogy, the posterior distribution defines another (imaginary) physical system. Gradual temperature reduction in the physical system isolates low energy states (``annealing''), or what is the same thing, the most probable states under the Gibbs distribution. The analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations. The result is a highly parallel ``relaxation'' algorithm for MAP estimation. We establish convergence properties of the algorithm and we experiment with some simple pictures, for which good restorations are obtained at low signal-to-noise ratios.
18,761 citations
"A Two-Stage Probabilistic Approach ..." refers methods or result in this paper
...In a way, this is similar to the line-process model [ 7 ] for differentiating edge and non-edge elements....
[...]
...The differences are: the present model makes use of relational measurements of any orders because contextual constraints play a stronger role in high level problems, whereas the model in [ 7 ] uses only unary observation....
[...]
...Global optimizers such as simulated annealing (SA) [11, 7 ] also iterate based on local energy changes....
[...]
...The present model can be compared to the coupled MRF model of [ 7 ] in that there are two coupled MRFs, one for line processes (edges) and one for intensities; and a line process variable can be on or off depending on the difference between the two neighboring intensities....
[...]
...This framework, advocated by Geman and Geman (1984) andothers, enables us to develop algorithms for a variety of vision problems system-atically using rational principles rather than relying on ad hoc heuristics....
[...]
TL;DR: In this paper, the authors proposed an iterative method for scene reconstruction based on a non-degenerate Markov Random Field (MRF) model, where the local characteristics of the original scene can be represented by a nondegenerate MRF and the reconstruction can be estimated according to standard criteria.
Abstract: may 7th, 1986, Professor A. F. M. Smith in the Chair] SUMMARY A continuous two-dimensional region is partitioned into a fine rectangular array of sites or "pixels", each pixel having a particular "colour" belonging to a prescribed finite set. The true colouring of the region is unknown but, associated with each pixel, there is a possibly multivariate record which conveys imperfect information about its colour according to a known statistical model. The aim is to reconstruct the true scene, with the additional knowledge that pixels close together tend to have the same or similar colours. In this paper, it is assumed that the local characteristics of the true scene can be represented by a nondegenerate Markov random field. Such information can be combined with the records by Bayes' theorem and the true scene can be estimated according to standard criteria. However, the computational burden is enormous and the reconstruction may reflect undesirable largescale properties of the random field. Thus, a simple, iterative method of reconstruction is proposed, which does not depend on these large-scale characteristics. The method is illustrated by computer simulations in which the original scene is not directly related to the assumed random field. Some complications, including parameter estimation, are discussed. Potential applications are mentioned briefly.
4,490 citations
"A Two-Stage Probabilistic Approach ..." refers methods in this paper
...The ICM algorithm [2] iteratively maximizes local conditional distributions in a way as a \greedy method"....
[...]
Proceedings Article•
31 Dec 1993TL;DR: Results from constrained optimization some results from algebraic geometry differential geometry are shown.
Abstract: Projective geometry modelling and calibrating cameras edge detection representing geometric primitives and their uncertainty stereo vision determining discrete motion from points and lines tracking tokens over time motion fields of curves interpolating and approximating three-dimensional data recognizing and locating objects and places answers to problems. Appendices: constrained optimization some results from algebraic geometry differential geometry.
2,744 citations
"A Two-Stage Probabilistic Approach ..." refers methods in this paper
...Here, an object model is represented by local object features, such as points, line segments or regions, subject to various constraints [3, 8, 6, 17]....
[...]
Book•
01 Jan 1988
1,771 citations
"A Two-Stage Probabilistic Approach ..." refers background or methods or result in this paper
...Global optimizers such as simulated annealing (SA) [11, 7] also iterate based on local energy changes....
[...]
...This framework, advocated by Geman and Geman (1984) andothers, enables us to develop algorithms for a variety of vision problems system-atically using rational principles rather than relying on ad hoc heuristics....
[...]
...The present model can be compared to the coupled MRF model of [7] in that there are two coupled MRFs, one for line processes (edges) and one for intensities; and a line process variable can be on or o depending on the di erence between the two neighboring intensities....
[...]
...The di erences are: the present model makes use of relational measurements of any orders because contextual constraints play a stronger role in high level problems, whereas the model in [7] uses only unary observation....
[...]
...In a way, this is similar to the line-process model [7] for di erentiating edge and non-edge elements....
[...]