¹Faculty of sciences, Mohammed V University, GSCM_LRIT Laboratory, 4 Avenue Ibn Battouta B.P. 1014, Rabat, Morocco

²Faculty of sciences, Mohammed V University,LETS Laboratory, 4 Avenue Ibn Battouta B.P. 1014, Rabat, Morocco

http://www.fsr.ac.ma

Abstract:

Corner detection and feature extraction are widely used in image processing and computer vision applications. In this paper, we propose new grey level corner detection based on electrostatic model having different configurations, which demonstrate the best detection. The basic idea is to model the image as a grid of electric charges of a plan surface in electrostatic balance.The algorithm is achieved in two main steps. The first one uses an adaptive method for computing directional gradients witch permits to build an edge detection operator of 3x3 pixels size. The second one introduces this operator for determining image derivatives in order to detect the corners. The smoothed squared images derivatives are given by using a Gaussian function. For each image pixel the response function proposed by Harris and Stephens is calculated using auto-correlation matrix. A local maxima search is performed as a final step of the method. Simulation results on synthetic and real images show the performances of the proposed approach compared to that presented by an improved version of Harris detector.

Keywords: Adaptive methods, Corner detection, Edge detection, Models.

BibTex:

@ARTICLE{P1150630001,

AUTHOR = {B. Bouda and  Lh. Masmoudi and  D. Aboutajdine},

TITLE = {A New Grey Level Corner Detection Based on Electrostatic Model},

JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing},

}

(Full Paper 796KB)