Robust image corner detection through curvature scale space

Mokhtarian, Farzin; Suomela, Riku

doi:10.1109/34.735812

Cited by 457 publications

(173 citation statements)

References 27 publications

(15 reference statements)

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…One of the most popular multiscale curvature representation of 2D curves is the curvature scalespace [17], which has been improved and applied in different works [1,3,11,18,19,20,25,33,35,36].…”

Section: The Curvature Space-scale Techniquementioning

confidence: 99%

“…This algorithm designed by Mokhtarian and Suomela [20] requires the Canny edge operator applied to the gray level image to obtain a binary edge image. 4 …”

Section: The Curvature Space-scale Techniquementioning

confidence: 99%

“…Moreover, we introduce a novel procedure that searches for multiscale algorithm parameters, in a particular database, and combine it to the idea underlying inter-scale correlation to detect dominant points in planar shapes. The proposed method is also assessed and compared with three methods [14,20,23] including the well known curvature scale-space (CSS). Furthermore, the performance evaluation of the algorithms rely on ground-truth based measures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiscale Corner Detection in Planar Shapes

Paula

Medeiros

Bezerra³

et al. 2012

J Math Imaging Vis

View full text Add to dashboard Cite

This paper presents a multiscale corner detection method in planar shapes, which applies an undecimated Mexican hat wavelet decomposition of the angulation signal to identify significant points on a shape contour. The advantage of using this wavelet is that it is well suited for detecting singularities as corners and contours due to its excellent selectivity in position. Thus, this wavelet plays an important role in our approach because it identifies changes in non-stationary angulation signals, and it can be extended to multidimensional approaches in an efficient way when approximating this wavelet by difference of Gaussian. The proposed algorithm detects peaks on a correlation signal which is generated from different wavelet scales and retains relevant points on the decomposed angulation signal while discards poor information. Our approach assumes that only peaks which persist through several scales correspond to corners. Furthermore, we introduce a novel procedure to tune parameters for the corner detection algorithms that corresponds to the best relation between Precision and Recall measures. This technique guides the parameter adjustment of the algorithms according to the image database and it improves their performance with regard to true corner detection. Concerning the performance assessment of the algorithms, we compare the proposed one to other corner detectors by using Precision and Recall measures which are based on ground-truth information. Tests were carried out using more than a hundred images from a non-homogenous database that contains noisy and non-noisy binary shapes 1

show abstract

Section: The Curvature Space-scale Techniquementioning

confidence: 99%

“…This algorithm designed by Mokhtarian and Suomela [20] requires the Canny edge operator applied to the gray level image to obtain a binary edge image. 4 …”

Section: The Curvature Space-scale Techniquementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale Corner Detection in Planar Shapes

Paula

Medeiros

Bezerra³

et al. 2012

J Math Imaging Vis

View full text Add to dashboard Cite

show abstract

“…We show the results of the ROC analysis when applied to a number of artificial and natural images, particularly a series of cube images within a laboratory environment (Fig. 3), and a second set of images containing an artificial corner test image from Smith and Brady (1997), a laboratory scene from Mokhtarian and Suomela (1998) and an image of a staircase (Fig. 5).…”

Section: Evaluation Of Detection Performance Compared To Other Junctimentioning

confidence: 99%

“…Unlike local approaches as proposed in computer vision (Harris, 1987;Mokhtarian and Suomela, 1998), the new scheme is based on a more global, recurrent long-range interaction for the coherent computation of contour responses. Such nonlocal interactions evaluate local responses within a more global context and generate a robust contour representation.…”

Section: Introductionmentioning

confidence: 99%

A Biologically Motivated Scheme for Robust Junction Detection

Hansen

Neumann

2002

Biologically Motivated Computer Vision

View full text Add to dashboard Cite

Abstract. Junctions provide important cues in various perceptual tasks, such as the determination of occlusion relationship for figureground separation, transparency perception, and object recognition, among others. In computer vision, junctions are used in a number of tasks like point matching for image tracking or correspondence analysis. We propose a biologically motivated approach to junction detection. The core component is a model of V1 based on biological mechanisms of colinear long-range integration and recurrent interaction. The model V1 interactions generate a robust, coherent representation of contours. Junctions are then implicitly characterized by high activity for multiple orientations within a cortical hypercolumn. A local measure of circular variance is used to extract junction points from this distributed representation. We show for a number of generic junction configurations and various artificial and natural images that junctions can be accurately and robustly detected. In a first set of simulations, we compare the detected junctions based on recurrent long-range responses to junction responses as obtained for a purely feedforward model of complex cells. We show that localization accuracy and positive correctness is improved by recurrent long-range interaction. In a second set of simulations, we compare the new scheme with two widely used junction detection schemes in computer vision, based on Gaussian curvature and the structure tensor. Receiver operator characteristic (ROC) analysis is used for a threshold-free evaluation of the different approaches. We show for both artificial and natural images that the new approach performs superior to the standard schemes. Overall we propose that nonlocal interactions as realized by long-range interactions within V1 play an important role for the detection of higher order features such as corners and junctions.

show abstract