3D line image analysis—A heuristic parallel approach with learning and recognition

Wang, P. S. P.

doi:10.1016/0020-0255(94)90095-7

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been a growing interest in 3D object recognition research. Not only it is interesting and challenging in theory, but also it can be applied to solving many realistic problems in industrial parts inspection, military target recognition, CAM/CAD engineering design, scienti c experiments, and document image analysis 5,11,18,22,33,41]. However, up-to-date, most research focused on rigid objects only, with large learning sample size, low speed, and can not distinguish similar patterns 2,25].…”

Section: Introduction and Objectivesmentioning

confidence: 99%

Parallel Matching of 3d Articulated Object Recognition

Wang

1999

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

In dealing with large volume image data, sequential methods usually are too slow and unsatisfactory. This paper introduces a new system employing parallel matching in high-level recognition of 3D articulated objects. A new structural strategy using linear combination and parallel graphic matching techniques is presented for 3D polyhedral objects representable by 2D line-drawings. It solves one of the basic concerns in diffusion tomography complexities, i.e. patterns can be reconstructed through fewer projections, and 3D objects can be recognized by a few learning sample views. It also improves some of the current methods while overcoming their drawbacks. Furthermore, it can distinguish very similar objects and is more accurate than other methods in the literature. An online webpage system for understanding and recognizing 3D objects is also illustrated.

show abstract

Section: Introduction and Objectivesmentioning

confidence: 99%

Parallel Matching of 3d Articulated Object Recognition

Wang

1999

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…They interpret the line drawings without models by using Marill's minimum Standard Deviation of Angle (MSDA) principle [6], yet is faster and more accurate. Wang introduced a heuristic parallel approach [8] for 3D line image analysis by using the concept of coordinated graph, layered graph representation and parallel matching techniques. Wang also presented a new hybrid approach [7] for recognizing complicated objects including concave, partially self-occluded and articulated object from 2D line drawings; yet it was only tested on noise-free well behaved polyhedrals.…”

Section: Introductionmentioning

confidence: 99%

Recognition of 3D objects from 2D images — Some issues

Liu

Wang

1996

Advances in Structural and Syntactical Pattern Recognition

View full text Add to dashboard Cite

This paper presents a simple methods for visualizing, understanding, interpreting, and recognizing 3D objects from 2D images. It extended the linear combination methods, uses parallel pattern matching and can handle 3D rigid concave objects as well convex objects and articulated objects, yet, needs only a very small number of learning samples. Some real images are illustrated, with future research discussed.

show abstract

“…Wang introduced a heuristic parallel approach [9] for 3D line image analysis by using the concept of coordinated graph, layered graph representation and parallel matching techniques.…”

Section: Introductionmentioning

confidence: 99%

<title>3D articulated object recognition: a case study</title>

Liu¹,

Wang²

1996

SPIE Proceedings

View full text Add to dashboard Cite

A simple method for visualizing, understanding, interpreting, and recognizing 3D objects from 2D images is presented. It extended the linear combination methods, uses parallel pattern matching and can handle 3D rigid concave objects as well convex objects, yet, needs only a very small number of learning samples. Some real images are illustrated, with future research discussed including more complicated images such as 3D concave and articulated objects. Downloaded From: http://proceedings.spiedigitallibrary.org/ on 06/20/2016 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx * the model consists of several imagesminimally three for polyhedra. An unknown object is matched with a model by comparing the points in an image of the unknown object with a template-like collection of points produced from the model. In general, an unknown object can be arbitrarilly rotated, arbitrarilly translated and even arbitrarilly scaled relative to an arbitrary original position. From the SPIE Vol. 2904 115 Downloaded From: http://proceedings.spiedigitallibrary.org/ on 06/20/2016 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx

show abstract

3D line image analysis—A heuristic parallel approach with learning and recognition

Cited by 5 publications

References 12 publications

Parallel Matching of 3d Articulated Object Recognition

Parallel Matching of 3d Articulated Object Recognition

Recognition of 3D objects from 2D images — Some issues

<title>3D articulated object recognition: a case study</title>

Contact Info

Product

Resources

About