Contour-based Corner Detectors Research Articles

An efficient corner detector based on ratio of parallelogram diagonal

Corner is an important local feature of image which has been widely applied on various computer vision and image processing tasks. Here, a contour-based corner detector is developed by using the ratio of parallelogram diagonals (RPD) to estimate the curve curvature. The main advantage of RPD detector is that only once square root operation is required to calculate the curvature value at each point on a contour while maintaining good noise robustness. The contributions of this paper include the following three aspects: First, the motivation of the proposed RPD curvature is illustrated by means of parallelogram theory; second, a complete corner detector is proposed based on RPD curvature; third, comprehensive experiments are carried out and the experimental results show superior performances of the proposed method against another five strong baselines. In these experiments, RPD runs 100% faster than the prior works. Moreover, a mean accuracy of 83.87% is reported on GCM dataset which is an improvement of about 0.9% and a mean accuracy of 74.21% is reported on CPDA dataset which is an improvement of about 0.2%.

Corner detection using the point‐to‐centroid distance technique

Corners, highly important local features of images and corner finding, play a crucial role in computer vision and image processing, such as object tracking and vehicle detection. Proposing effective and efficient corner detectors is the aim of corner detection. In this study, the authors first present a new measure of corner sharpness termed as the point-to-centroid distance (PCD) and then examine its behaviours, which display beneficial characteristics that help distinguish corners from non-corners. Based on PCD behaviours, the authors propose a novel corner detector. Extensive experimental results demonstrate that the PCD technique is effective and simultaneously efficient for corner detection compared with six other contour-based corner detectors in terms of two commonly used evaluation metrics – average repeatability and localisation error.

Discrete Curvature Representations for Noise Robust Image Corner Detection.

Image corner detection is very important in the fields of image analysis and computer vision. Curvature calculation techniques are used in many contour-based corner detectors. We identify that existing calculation of curvature is sensitive to local variation and noise in the discrete domain and does not perform well when corners are closely located. In this paper, discrete curvature representations of single and double corner models are investigated and obtained. A number of model properties have been discovered, which help us detect corners on contours. It is shown that the proposed method has a high corner resolution (the ability to accurately detect neighboring corners), and a corresponding corner resolution constant is also derived. Meanwhile, this method is less sensitive to any local variations and noise on the contour; and false corner detection is less likely to occur. The proposed detector is compared with seven state-of-the-art detectors. Three test images with ground truths are used to assess the detection capability and localization accuracy of these methods in cases with noise-free and different noise levels; 24 images with various scenes without ground truths are used to evaluate their repeatability under affine transformation, JPEG compression, and noise degradations. The experimental results show that our proposed detector attains a better overall performance.

Contour-based corner detection via angle difference of principal directions of anisotropic Gaussian directional derivatives

This paper presents a contour-based corner detector using the angle difference of the principal directions of anisotropic Gaussian directional derivatives (ANDDs) on contours. The noise -robust ANDDs can characterize fine directional intensity variations around edge pixels and corners. The proposed corner detector consists of three steps: Extraction of edge map by the Canny edge detector, improvement of contours by the Douglas-Peucker (D-P) polygonal approximation and filling small gaps between contours, and finding corners from contours by using the angle difference of the principal directions of the ANDDs as the corner measure. Different from the existing contour-based detectors where corner measures correspond to the geometric properties of a contour, the new corner measure utilizes the directional intensity variations at the pixels on a contour and thus has high angular resolution, good localization, and noise-robustness. The proposed detector is compared with the three state-of-the-art detectors from two aspects. Two test images with ground truths are used to assess its detection capability and localization accuracy. Twenty-four test images with various scenes and without ground truths are used to evaluate its repeatability under affine transforms, JPEG compression, and noise degradation. The experimental results show that the proposed detector attains better overall performance.

Effective and efficient contour-based corner detectors

Corner detection is an essential operation in many computer vision applications. Among the contour-based corner detectors in the literature, the Chord-to-Point Distance Accumulation (CPDA) detector is reported to have one of the highest repeatability in detecting robust corners and the lowest localization error. However, based on our analysis, we found that the CPDA detector often fails to accurately detect the true corners when a curve has multiple corners but the sharpness of one or a few of them is much more prominent than the rest. This detector also might not perform well when the corners are closely located. Furthermore, the CPDA detector is also computationally very expensive. To overcome these weaknesses, we propose two effective and efficient corner detectors using simple triangular theory and distance calculation. Our experimental results show that our proposed detectors outperform CPDA and nine other existing corner detectors in terms of repeatability. Our proposed detectors also have a relatively low or comparable localization error and are computationally more efficient.

Corner detection using Gabor filters

This study proposes a contour-based corner detector using the magnitude responses of the imaginary part of the Gabor filters on contours. Unlike the traditional contour-based methods that detect corners by analysing the shape of the edge contours and searching for local curvature maxima points on planar curves, the proposed corner detector combines the pixels of the edge contours and their corresponding grey-variation information. Firstly, edge contours are extracted from the original image using Canny edge detector. Secondly, the imaginary parts of the Gabor filters are used to smooth the pixels on the edge contours. At each edge pixel, the magnitude responses at each direction are normalised by their values and the sum of the normalised magnitude response at each direction is used to extract corners from edge contours. Thirdly, both the magnitude response threshold and the angle threshold are used to remove the weak or false corners. Finally, the proposed detector is compared with five state-of-the-art detectors on some grey-level images. The results from the experiment reveal that the proposed detector is more competitive with respect to detection accuracy, localisation accuracy, affine transforms and noise-robustness.

Performance Comparisons of Contour-Based Corner Detectors

Corner detectors have many applications in computer vision and image identification and retrieval. Contour-based corner detectors directly or indirectly estimate a significance measure (e.g., curvature) on the points of a planar curve, and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors have been proposed over the last four decades, there is no comparative study of recently proposed detectors. This paper is an attempt to fill this gap. The general framework of contour-based corner detection is presented, and two major issues-curve smoothing and curvature estimation, which have major impacts on the corner detection performance, are discussed. A number of promising detectors are compared using both automatic and manual evaluation systems on two large datasets. It is observed that while the detectors using indirect curvature estimation techniques are more robust, the detectors using direct curvature estimation techniques are faster.