WAVELET TRANSFORMATION FOR GRAY-LEVEL CORNER DETECTION

Corners are very attractive features for many applications in computer vision. In this paper, a new gray-level corner detection algorithm ba sed on the wavelet transform is presented. The wavelet transform is us ed because the evolution across scales of its magnitudes and orientati ons can be used to characterize localized signals like edges and corne rs. Most conventional corner detectors detect corners based on the edg e detection information. However, these edge detectors perform poorly at corners, adversely affecting their overall performance. To overcome this drawback, we first propose a new edge detector based on the rati o of the inter-scale wavelet transform modulus. This edge detector can correctly detect edges at the corner positions, making accurate corne r detection possible. To reduce the number of points required to be pr ocessed, we apply the non-minima suppression scheme to the edge image and extract the minima image. Based on the orientation variance, these non-corner edge points are eliminated. In order to locate the corner points, we propose a new corner indicator based on the scale invariant property of the corner orientations. By examining the corner indicato r the corner points can be located accurately, as shown by experiments with our algorithm. In addition, since wavelet transform possesses th e smoothing effect inherently, our algorithm is insensitive to noise c ontamination as well.