Showing papers on "Corner detection published in 1999"
TL;DR: A new approach called gradient-direction corner detector for the corner detection is presented which is developed from the popular Plessey corner detection and is based on the measure of the gradient module of the image gradient direction and the constraints of the false corner response suppression.
199 citations
TL;DR: A new measure for corner detection based on the eigenvalues of the covariance matrix of boundary points over a small region of support that avoids false alarms for superfluous corners on circular arcs is presented.
116 citations
TL;DR: Yang et al. as discussed by the authors proposed an operator for the detection of the true location and orientation of corners, where corner points are detected as intensity patterns that are anisotropic along several directions.
69 citations
TL;DR: It is demonstrated that corners are located at the saddle-points of the magnitude of the vector-potential, which correspond to the intersections of saddle-ridge and saddle-valley structures, i.e. to junctions of the edge and symmetry lines.
47 citations
TL;DR: Compared with existing methods, the proposed approach is superior in that it explains the curve, instead of simple labeling, and it performs based on human perception.
Abstract: The problem of corner detection on planar curves is examined based on human perception of local graphic features. First, a set of fuzzy patterns of contour points are established. Then, corner detection is characterized as a fuzzy classification problem that contains three stages: evaluation, classification, and location. Compared with existing methods, the proposed approach is superior in that it explains the curve, instead of simple labeling, and it performs based on human perception. Experimental results on shapes of various complexities are presented. The performance with respect to noise is also addressed.
45 citations
20 Sep 1999
TL;DR: This work uses both a region model, based on distributions of pixel colors, and an edge model, which removes false positives, to perform corner detection on color images whose regions contain texture.
Abstract: Corner models in the literature have lagged behind edge models with respect to color and shading. We use both a region model, based on distributions of pixel colors, and an edge model, which removes false positives, to perform corner detection on color images whose regions contain texture. We show results on a variety of natural images at different scales that highlight the problems that occur when boundaries between regions have curvature.
26 citations
TL;DR: A new algorithm is proposed for representing and characterising the contours of 2D objects, as well as detecting their corners, based on circular histograms of the contour chain code which defines a circular mean of variable origin.
Abstract: A new algorithm is proposed for representing and characterising the contours of 2D objects, as well as detecting their corners. The novelty lies in the curvature estimation technique which is based on circular histograms of the contour chain code. Two histograms are calculated at the neighbourhood of every point, and instead of considering them of linear type and being compared by correlation, they are considered to be circular and compared by a new method which defines a circular mean of variable origin. The main advantages of this method are its low computational overhead and the precision of the obtained curvature functions.
22 citations
17 Oct 1999
TL;DR: Presents several extensions of the basic control point assessment (CPA) algorithm and discusses how least-squares operator norm information can be coupled with anisotropic diffusion to produce smoothed images without corner degradation.
Abstract: Presents several extensions of the basic control point assessment (CPA) algorithm. First, we compare CPA to standard corner detection algorithms and then turn to the question of selecting control points with adequate dispersion, since this is crucial for accurate registration. Two selection methods are proposed. The first consists of clustering the control points via the Lloyd algorithm (S.P. Lloyd, 1957, 1982) followed by selecting the dominant control point in each cluster. This "gold standard" approach produces excellent dispersion but is costly in terms of computational effort. The second selection method consists of subdividing the image and then selecting dominant control points in each subdivision. This is extremely fast and produces results comparable to the Lloyd selection method. The paper concludes with a discussion of how least-squares operator norm information can be coupled with anisotropic diffusion to produce smoothed images without corner degradation.
20 citations
TL;DR: An algorithm for extracting a robust mosaic representation of video content from sparse interest image points is described, which features the geometric and kinematic description of all salient objects in the scene, being well suited for video browsing, indexing and retrieval by visual content.
Abstract: Compact yet intuitive representations of digital videos are required to combine high quality storage with interactive video indexing and retrieval capabilities. The advent of video mosaicing has provided a natural way to obtain content-based video representations which are both retrieval-oriented and compression-efficient. In this paper, an algorithm for extracting a robust mosaic representation of video content from sparse interest image points is described. The representation, which is obtained via visual motion clustering and segmentation, features the geometric and kinematic description of all salient objects in the scene, being thus well suited for video browsing, indexing and retrieval by visual content. Results of experiments on several TV sequences provide an insight into the main characteristics of the approach.
20 citations
TL;DR: A novel generalized feature extraction method based on the expansion matching (EXM) method and on the Karhunen-Loeve transform that incorporates a significant reduction in computational complexity by representing a large set of EXM filters by a relatively small number of eigen filters derived by the KL transform of the basic EXM filter set.
Abstract: A novel generalized feature extraction method based on the expansion matching (EXM) method and on the Karhunen-Loeve transform (KLT) is presented. The method provides an efficient way to locate complex features of interest like corners and junctions with reduced number of filtering operations. The EXM method is used to design optimal detectors for a set of model elementary features. The KL representation of these model EXM detectors is used to filter the image and detect candidate interest points from the energy peaks of the eigen coefficients. The KL coefficients at these candidate points are then used to efficiently reconstruct the response and differentiate real junctions and corners from arbitrary features in the image. The method is robust to additive noise and is able to successfully extract, classify, and find the myriad compositions of corner and junction features formed by combinations of two or more edges or lines. This method differs from previous works in several aspects. First, it treats the features not as distinct entities, but as combinations of elementary features. Second, it employs an optimal set of elementary feature detectors based on the EM approach. Third, the method incorporates a significant reduction in computational complexity by representing a large set of EXM filters by a relatively small number of eigen filters derived by the KL transform of the basic EXM filter set. This is a novel application of the KL transform, which is usually employed to represent signals and not impulse responses as in our present work.
16 citations
15 Mar 1999
TL;DR: An improved, wavelet-based technique for corner detection, in 2-D planar curves, is presented and it exploits wavelet transform modulus maxima (WTMM) to detect corners.
Abstract: An improved, wavelet-based technique for corner detection, in 2-D planar curves, is presented. This boundary based technique is simple to implement and computationally efficient and exploits wavelet transform modulus maxima (WTMM) to detect corners. The proposed algorithm is robust with respect to object geometry. We also report results under additive white Gaussian noise (AWGN).
24 Oct 1999
TL;DR: This paper presents a robust and flexible method for the extraction of mouth corners from videophone sequences that allows to efficiently perform the fusion of several sources of information.
Abstract: This paper presents a robust and flexible method for the extraction of mouth corners from videophone sequences. Robustness is referred to illumination conditions, speaker variability, pose and image quality, while flexibility is given by the fuzzy environment which allows to efficiently perform the fusion of several sources of information.
24 Oct 1999
TL;DR: This paper addresses the problems of object corner detection and the applications of corners to affine-similar object matching for object retrieval from a database with two simple and efficient corner detection methods.
Abstract: This paper addresses the problems of object corner detection and the applications of corners to affine-similar object matching for object retrieval from a database. Two simple and efficient corner detection methods are presented. One is based on detecting sharp angles on a smoothed object boundary curve, and the other is based on a 2D rotationally symmetric bandpass filter applied onto an image. Two object matching approaches which exploit these corners are then investigated. In the first approach, affine objects are retrieved by matching their features derived from the corners. Dissimilarity measures for objects are formulated based on these features. In the second approach, affine objects are retrieved by matching object boundary curves modeled by a constrained active B-spline curve model. The model differs from the conventional B-spline by retaining significant object corners as a subset of B-spline knot points. This enables better correspondences of corners and easy selection of starting points for modeled curves, and hence a more accurate affine object matching. Various images and object boundary curves were used to verify the proposed methods, and the experimental results are convincing.
31 Oct 1999
TL;DR: An algorithm for robust corner detection in variable illumination scenes, which is necessary in many real applications, is presented and experimental results are given to validate its effectiveness.
Abstract: Corners are useful features in computer vision tasks. In this paper we present an algorithm for robust corner detection in variable illumination scenes, which is necessary in many real applications. The new algorithm is analyzed based on the perception of human vision system, and experimental results are given to validate its effectiveness.
01 Jan 1999
TL;DR: A new method for image point feature detection based on the curvature scale space (CSS) representation, which is very robust to noise and performed better than three other detectors it was compared to.
Abstract: This paper describes a new method for image point feature detection based on the curvature scale space (CSS) representation. The first step is to extract edges from the original image using a Canny detector. The corner points of an image are defined as points where image edges have their maxima of absolute curvature. The corner points are detected at a high scale of the CSS image and the locations are tracked through multiple lower scales to improve localization. The curvature zero-crossing points of the edge contours form a different set of image point features. The CSS corner detector is very robust to noise and performed better than three other detectors it was compared to. An improvement to the Canny edge detector's performance is also proposed.
09 Mar 1999
TL;DR: Experimental results show that this multi-scale wavelet-based non-parametric algorithm for detecting and locating corners in 2D images has high precision and stability of the corner detection and location.
Abstract: A multi-scale wavelet-based non-parametric algorithm for detecting and locating corners in 2D images is proposed. First using zero-crossing-based 2D edge detector we can get the edge elements, after edge linking and give each planar curve its orientation space representation we can get the orientation curves. Based on the multi-scale wavelet transform of the orientation curves we can utilize the information of local maximum positions to detect and locate the corners. Experimental results with some synthetic and real images show that this algorithm has high precision and stability of the corner detection and location.
04 Oct 1999
TL;DR: A novel relaxation based corner tracking system is combined with existing corner tracking techniques to produce corner trajectories that are virtually free of large errors.
Abstract: We present a robust motion based segmentation system. We combine a novel relaxation based corner tracking system with existing corner tracking techniques to produce corner trajectories that are virtually free of large errors. This technique is used in conjunction with a probabilistic segmentation algorithm to find and track objects in image sequences.