Identifying Salient Circular Arcs on Curves

Saund, Eric

doi:10.1006/ciun.1993.1045

Cited by 14 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the wide variety of shapes that are possible during freehand sketching, one cannot assure that the majority of segments are detected correctly when using a fixed number of templates. Considering the fact that circular arcs are widely used in engineering practices, Saund [5] approached the segmentation problem from the perspective of circular arc approximations, where several criteria are used to determine accuracy including goodness of fit, uniqueness, and end abruptness. Shilman et al [21] presented a Bayesian, visual language based model for sketch segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…A robust and efficient sketch segmentation algorithm is often crucial for the computer to correctly understand the user's intent and use it as the basis of higher-level symbolic and structural analyses. To our knowledge there is no formal definition for segmentation points of freehand sketches, although Saund [5] pointed out this issue many years ago. This makes it difficult and often confusing to determine whether a segmentation result is reasonable or not.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated freehand sketch segmentation using radial basis functions

Gur

2009

Computer-Aided Design

View full text Add to dashboard Cite

Freehand sketching is widely regarded as an efficient and natural way for interaction between computers and humans. We present a robust computerized scheme to automatically segment freehand sketches into a series of components with specific geometric meaning regardless of whether these are generated online or offline. This task is a necessary first step toward sketch understanding. By exploiting the interpolation / extrapolation characteristic of Radial Basis Functions (RBFs), a greedy algorithm consisting of forward and backward operations is proposed for finding the minimum set of segmentation points that can be used to reconstruct with high fitting accuracy freehand sketches in the form of implicit functions. To obtain segmentation points, a simple angle based rule is used to remove "bridging" points that provide a smooth transition between consecutive sketch components. Feasibility of the proposed algorithm is demonstrated by a preliminary performance assessment study using ten computer generated drawings. These experiments show that in this dataset sensitivity of the segmentation was higher than 97.5% with a false positive (FP) rate of approximately 25%. The majority of false positive identifications are located on arc regions where a larger number of segmentation points are needed for reconstruction purposes. The primary contribution of this algorithm is that it transforms an ambiguous problem namely, freehand sketch segmentation, into an implicit function fitting operation. Therefore, this proposed approach has several advantages including independence of the actual sketching activity, and the ability for a satisfactory detection of the transition point between a line and an arc or between two arcs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated freehand sketch segmentation using radial basis functions

Gur

2009

Computer-Aided Design

View full text Add to dashboard Cite

show abstract

“…The incoming line drawing image is subjected to centersurround filtering, thresholding, and thinning. Curvilinear lines are collected by tracing, and perceptually salient corners are found by a multiscale corner detection algorithm (see Saund, 1993). The result is a set of primitive curve element tokens representing relatively straight curvilinear contour segments.…”

Section: Diagrammatic User Interfacementioning

confidence: 99%

Bringing the Marks on a Whiteboard to Electronic Life

Saund

1999

Cooperative Buildings. Integrating Information, Organizations, and Architecture

View full text Add to dashboard Cite

Abstract. This paper discusses our implementation and experience with a camera-based whiteboard scanner. The ZombieBoard system (so called because it brings to electronic life the marks on a whiteboard) is built into both the physical environment and the information space, while augmenting and linking the two. Computer vision underlies two key technology components. First, image mosaicing is used to obtain highresolution images of large surfaces using relatively low-resolution cameras. Second, real time activity analysis and line drawing analysis enable a Diagrammatic User Interface whereby commands are issued to the system by drawing on the whiteboard itself. The system has been in routine use at our research center for two years and has demonstrated the value of this approach to linking whiteboards with the electronic document world.

show abstract

“…They are therefore more often used in computer-aided design applications. On the other hand, conic section representation of object boundaries has the advantage of simplicity, popularity, and efficiency [9,14,20,23]. The conic sections are, therefore, the most frequently used curve forms, besides the piece-wise straight line segments, used for approximating the object boundaries in computer vision applications.…”

Section: Introductionmentioning

confidence: 99%

On the Geometries of Conic Section Representation of Noisy Object Boundaries

Zhu¹

1999

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Identifying Salient Circular Arcs on Curves

Cited by 14 publications

References 36 publications

Automated freehand sketch segmentation using radial basis functions

Automated freehand sketch segmentation using radial basis functions

Bringing the Marks on a Whiteboard to Electronic Life

On the Geometries of Conic Section Representation of Noisy Object Boundaries

Contact Info

Product

Resources

About