Elsevier

Pattern Recognition Letters

Volume 8, Issue 5, December 1988, Pages 311-318
Pattern Recognition Letters

Corner characterization by differential geometry techniques

https://doi.org/10.1016/0167-8655(88)90080-3Get rights and content

Abstract

An algorithm is presented for the characterization of the corner points in an image by means of three parameters of easily understandable physical meaning, namely the amplitude, aperture, and smoothness of the blurred wedge that best fits the data. Formulas are also given for the computation of the gradients and curvatures for the surface obtained convolving the step wedge of amplitude A and aperture φ with the bidimensional Gaussian function with variance σ2.

References (6)

There are more references available in the full text version of this article.

Cited by (38)

  • Geometric rosette patterns analysis and generation

    2017, Journal of Cultural Heritage
    Citation Excerpt :

    A large number of corner detectors have been proposed in the literature. They can be grouped broadly into three categories: Gray-level based methods [14–19], contour based methods [20–24] and parametric model based methods [25–27]. In this paper, we use the Förstner method presented in [23] and its implementation described in [24,25,28].

  • Visual recognition of aircraft mechanical parts for smart maintenance

    2017, Computers in Industry
    Citation Excerpt :

    To do so, several operators have been proposed in the past. Among the others, we can mention the Harris corner detector [17] and its improved Harris-Laplace version [18], the Differences of Gaussian (DoG) operator [19], the Speeded Up Robust Features (SURF) [20]) and the Features from Accelerated Segment Test (FAST) [21]. In particular, the last three (DoG, SURF and FAST) have the advantage of being invariant with respect to rotation and scale, and, according to the comparison made by Tuytelaars and Mikolajczyk [22], they are characterized by having good degrees of repeatability (low sensitivity to the viewing conditions), accuracy (precision of localization), and robustness (low sensitivity to image noise, discretization effects, compression artifacts, blur, etc.).

  • Detecting and matching feature points

    2005, Journal of Visual Communication and Image Representation
    Citation Excerpt :

    Rohr's corner model was in turn inspired by Berzins (1984), who worked on the problem that Laplacian edge detectors encounter near corners. Guiducci (1998) uses a model which is similar to Rohr's, but only looks at the difference in intensity between the wedge and its background. The model is then fitted analytically from image derivatives rather than directly from the image intensities.

  • Measuring Corner Properties

    1999, Computer Vision and Image Understanding
  • Analysis of gray level corner detection1

    1999, Pattern Recognition Letters
View all citing articles on Scopus
View full text