Fast Corner Detection Using Approximate Form of Second-Order Gaussian Directional Derivative

Abstract

High-efficiency image corner detection, one of the most important and critical basic technology in industrial image processing, is to detect point features from an input image in real-time. In this paper, we propose a new corner detection method which has both good performance of corner detection and real-time processing abilities. Firstly, the integral image and the box filter are combined to obtain the secondorder derivative response in each direction of the image. Secondly, a new coarse screening mechanism for candidate corners is presented to reduce the complexity of the corner metric. Thirdly, a non-maximum suppression operation is utilized to obtain corners. Finally, the performance evaluation on accuracy of corner detection, localization error, average repeatability, region repeatability, different lighting conditions, and execution time are used to assess the proposed method against twelve state-of-the-art methods. The experimental results show that our proposed detector has good corner detection performance and achieves the requirement of real-time processing. INDEX TERMS Corner detection, real-time processing, directional derivative, detection performance.

Corner Detection of the Computer VR Microscope Image Based on the 3D Reconstruction Algorithm

“…Gao et al proposed a pseudorandom sequence; due to the uniqueness of the window, each different subsequence can find the absolute position in the whole sequence; it is widely used in spatial coding schemes. Spatial encoding can be regarded as a sequence set based on pseudorandom numbers; the encoding pattern is generated by a Hamming window or an N-dimensional Euler path; the feature positions are determined by observing the line colors stored in the same window [8]. In 1998, Peng et al…”

“…Gao et al proposed a pseudorandom sequence; due to the uniqueness of the window, each different subsequence can find the absolute position in the whole sequence; it is widely used in spatial coding schemes. Spatial encoding can be regarded as a sequence set based on pseudorandom numbers; the encoding pattern is generated by a Hamming window or an N -dimensional Euler path; the feature positions are determined by observing the line colors stored in the same window [ 8 ]. In 1998, Peng et al proposed an orthogonal vertical grid color coding, which uses the peak concentration to detect the intersection, and at the same time, it converts the color from the RGB space to the HSI space for encoding, but in the decoding process, due to the different reflection of illuminance, the H channel is sensitive, which leads to new problems [ 9 ].…”

Image Feature Information Extraction for Interest Point Detection: A Comprehensive Review

“…Following the LoG [31] and DoG [42] methods, different types of filters (e.g., piece-wise triangle filters [86] or Box filters [87], [88]) were used to obtain the second-order derivatives along a pair of orthogonal directions with multiple scales or adaptive scales from an input image for detecting interest points. Bay et al [43] aimed to reduce the computational complexity in image convolution of the DoG method [42].…”

Image Feature Information Extraction for Interest Point Detection: A Comprehensive Review

“…the candidate interest point may be marked as an edge point (e.g., ς=6). Following the LoG [32] and DoG [68] methods, different types of filters (e.g., piece-wise triangle filters [117] or Box filters [118,119]) were used to obtain the second-order derivatives along a pair of orthogonal directions with multiple scales or adaptive scales from an input image for detecting interest points. Bay et al [69] aimed to reduce the calculation complexity in image convolution of the DoG method [68].…”

“…Zhang and Sun [35] applied the second-order generalized Gaussian directional derivative (SOGGDD) filters to derive the SOGGDD representations of step edge, L-type corner, Y-or T-type corner, X-type corner, and star-type corner. In order to reduce the time complexity of the algorithms, Gao et al [119] applied integral image and box filter to approximate the convolution process of SOGGDD filter and proposed a coarse screening mechanism based on the sum of multi-directional second order derivatives to detect corner. The SOGGDD representations of a step edge and different types of corners indicate that the SOGGDD of a step edge is zero in each direction and the SOGGDD filters along a pair of orthogonal directions cannot obtain enough IFI to accurately describe the second-order directional derivative at corners.…”