Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization

Mokhtarian, Farzin; Bober, Miroslaw

doi:10.1007/978-94-017-0343-7

Cited by 218 publications

(185 citation statements)

References 39 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…Since our method is essentially a global-driven method, it may fail for more or less non-rigid deformations. It is adapted better for rigid deformations as define for part A experiment in [17,18]. In this article, the authors have considered three different stages according to the three parts of the MPEG-7 Core Experiment CE-Shape-1: the part A that deals with robustness to scaling and to rotation is defined as a necessary condition to satisfy.…”

Section: Of 33mentioning

confidence: 99%

“…To overcome this problem, increasingly more pattern analysis (or pattern description) techniques are based on multiscale or multiresolution representation methods [9,14]. Within this context, methods based on the pattern itself [3,6,19,20] exist as well as methods based on pattern contour behaviour [7,8,10,12,13,15,16,17,18]. This study deals exclusively with pattern contour methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale contour description for pattern recognition

Kpalma

Ronsin

2006

Pattern Recognition Letters

View full text Add to dashboard Cite

In this paper, we present a new method and its preliminary results within the context of pattern analysis and recognition. This method is based on the multiscale analysis of a curve and deals with the contour of planar objects. Our method uses a low-pass Gaussian kernel to gradually smooth the contour by decreasing the filter bandwidth. Applying gain control to the smoothed contour stretches it to the same scale as the original one so that both contours intersect. By varying the bandwidth and marking all the intersection points between the smoothed contour and the original one we can generate the Intersection Points Map (IPM) function. The initial results obtained by applying this method to various contours appears to indicate that the IPM function has some very interesting properties within the context of pattern recognition. It is translation and rotation insensitive and also scale change resistant for a large range of scaling. The IPM function generated when applied to noisy contours shows that the method is resistant to noise for a range of noise energy. Applying the features extracted by this method to retrieve a pattern from a database confirms the efficiency of the method.

show abstract

Section: Of 33mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiscale contour description for pattern recognition

Kpalma

Ronsin

2006

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…For example, in [2], firstly surface feature points such as maximum curvature locations are identified. Then triples of feature points are combined using a geometric hashing algorithm in a way that is scaling invariant.…”

Section: Geometric Invariantsmentioning

confidence: 99%

“…There exist numerous well known practical 3D shape applications in computer vision including 3D scan matching, alignment and merging [1], 3D object matching, and 3D object classification and recognition [2]. 3D object databases are an active research area.…”

Section: Introductionmentioning

confidence: 99%

A Scale Invariant Surface Curvature Estimator

Rugis

Klette

2006

Advances in Image and Video Technology

View full text Add to dashboard Cite

show abstract

“…Curvature scale space (CSS) [12] is included in the MPEG-7 standard. First simplified contours are obtained by convolution with a Gaussian kernel.…”

Section: Grid Descriptormentioning

confidence: 99%