Recognition of occluded objects with heuristic search
TL;DR: A new heuristic search based approach for recognition of partially obscured planar shapes using an admissible heuristic function which is not dependent upon the features actually used for representing the shapes.
About: This article is published in Pattern Recognition.The article was published on 1990-07-01. It has received 14 citations till now. The article focuses on the topics: Admissible heuristic & Incremental heuristic search.
Citations
More filters
TL;DR: This method is able to obtain reliable stroke correspondence and enable structural interpretation and some structural post-processing operations are applied to improve the stroke correspondence.
107 citations
Cites methods from "Recognition of occluded objects wit..."
...The strategy of dynamic line segment merging has been adopted in on-line [28] and o!-line character recognition [29], as well as in shape recognition [30]....
[...]
TL;DR: Experimental results presented here highlight the effectiveness of this method for approximating object boundaries of polygonal as well as curved shapes present in the images of complex multi-object scenes even in the presence of noise.
19 citations
01 Apr 1998
TL;DR: Results are presented which demonstrate that an iterative, coarse-to-fine sum-squared-error method that uses information from hypothesized occlusion events to perform run-time modification of scene- to-template similarity measures is reasonably robust over a large database of color test scenes containing objects at a variety of scales and tolerates minor 3D object rotations and global illumination variations.
Abstract: In this paper, we discuss an appearance-matching approach to the difficult problem of interpreting color scenes containing occluded objects. We have explored the use of an iterative, coarse-to-fine sum-squared-error method that uses information from hypothesized occlusion events to perform run-time modification of scene-to-template similarity measures. These adjustments are performed by using a binary mask to adaptively exclude regions of the template image from the squared-error computation. At each iteration higher resolution scene data as well as information derived from the occluding interactions between multiple object hypotheses are used to adjust these masks. We present results which demonstrate that such a technique is reasonably robust over a large database of color test scenes containing objects at a variety of scales, and tolerates minor 3D object rotations and global illumination variations.
17 citations
Cites background from "Recognition of occluded objects wit..."
...) Without providing a rigorous statistical analysis, it can be stated that a reasonable expectation is that the minimum-error triplet ( i∗, j∗; h∗), defined by (i∗, j∗; h∗) = arg min (i,j;h) E(2) h(i, j) (9)...
[...]
...Examples include Ansari and Delp (1990), Han and Jang (1990), Chaudhury et al. (1990), Ray and Majumder (1991), and Salari and Balaji (1991)....
[...]
TL;DR: In this paper, the phase-only filter, the inverse filter and the minimum variance -minimum average correlation energy filter are considered for pattern recognition of occluded objects, and numerical and optical results of the recognition are presented.
16 citations
TL;DR: A bibliography of over 1600 references related to computer vision and image analysis, arranged by subject matter is presented, covering topics including architectures; computational techniques; feature detection, segmentation, and imageAnalysis.
Abstract: 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.
16 citations
References
More filters
TL;DR: A partial-shape-recognition technique utilizing local features described by Fourier descriptors is introduced, and experimental results are discussed that indicate that partial contours can be recognized with reasonable accuracy.
Abstract: A partial-shape-recognition technique utilizing local features described by Fourier descriptors is introduced. A dynamic programming formulation for shape matching is developed, and a method for comparison of match quality is discussed. This technique is shown to recognize unknown contours that may be occluded or that may overlap other objects. Precise scale information is not required, and the unknown objects may appear at any orientation with respect to the camera. The segment-matching dynamic programming method is contrasted with other sequence-comparison techniques that utilize dynamic programming. Experimental results are discussed that indicate that partial contours can be recognized with reasonable accuracy. >
137 citations
01 Jan 1985
TL;DR: In this paper, a new structural approach to shape recognition using attributed string matching with merging is proposed, where each attributed string is an ordered sequence of shape boundary primi- tives, each representing abasic boundary structural unit, line segment, with twootypes of numerical attributes, length and direction.
Abstract: A newstructural approach toshape recognition using attrib- utedstring matching withmerging isproposed. After illustrating the disadvantages ofconventional symbolic string matching using changes, deletions, andinsertions, attributed strings aresuggested formatching. Eachattributed string isanordered sequence ofshape boundary primi- tives, eachrepresenting abasic boundary structural unit, line segment, withtwotypesofnumerical attributes, length anddirection. A new typeofprimitive edit operation, called merge, isthenintroduced, which canbeusedtocombine andthenmatchanynumberofconsecutive boundary primitives inoneshapewiththose inanother. Theresulting attributed string matching withmerging approach isshownuseful for recognizing distorted shapes. Experimental results prove thefeasibility oftheproposed approach forgeneral shape recognition. Somepossible extensions oftheapproach arealso included. IndexTerms-Attributed strings, boundaryprimitives, combined primitives, editdistances, matching withmerging, shaperecognition, string edit operations, string matching.
134 citations
01 Mar 1986
TL;DR: A new recognition method, the feature indexed hypotheses method, is described, which takes advantage of the similarities and differences between object types, and is able to handle cases, where there are a large number of possible objecttypes, in sub-linear computation time.
Abstract: A common task in computer vision is to recognize the objects in an image Most computer vision systems do this by matching models for each possible object type in turn, recognizing objects by the best matches This is not ideal, as it does not take advantage of the similarities and differences between the possible object types The computation time also increases linearly with the number of possible objects, which can become a problem if the number is large This paper describes a new recognition method, the feature indexed hypotheses method, which takes advantage of the similarities and differences between object types, and is able to handle cases, where there are a large number of possible object types, in sub-linear computation time A two-dimensional occluded parts recognition system using this method is described
124 citations
TL;DR: Experimental results prove the feasibility of the proposed approach for general shape recognition using attributed string matching with merging with some possible extensions of the approach also included.
Abstract: A new structural approach to shape recognition using attributed string matching with merging is proposed. After illustrating the disadvantages of conventional symbolic string matching using changes, deletions, and insertions, attributed strings are suggested for matching. Each attributed string is an ordered sequence of shape boundary primitives, each representing a basic boundary structural unit, line segment, with two types of numerical attributes, length and direction. A new type of primitive edit operation, called merge, is then introduced, which can be used to combine and then match any number of consecutive boundary primitives in one shape with those in another. The resulting attributed string matching with merging approach is shown useful for recognizing distorted shapes. Experimental results prove the feasibility of the proposed approach for general shape recognition. Some possible extensions of the approach are also included.
124 citations
TL;DR: This paper applies clustering methods to a new problem domain and presents a new method based on a cluster-structure approach for the recognition of 2-D partially occluded objects, which allows the identification of all parts of the model which match in the Occluded scene.
61 citations