• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.4
• /
• pp.339-345
• /
• 2010

This paper introduces GP(Genetic Programming) based robust corner detectors for scaled and rotated images. Various empirical algorithms have been studied to improve computational speed and accuracy including approaches, such as the Harris and SUSAN, FAST corner detectors. These techniques are highly efficient for well-defined corners, but are limited to corner-like edges which are often generated in rotated images. It is very difficult to detect correctly edges which have characteristics similar to corners. In this paper, we have focused the above challenging problem and proposed Genetic Programming-based automated generation of corner detectors which is robust to scaled and rotated images. The proposed method is compared to the existing corner detectors on test images and shows superior results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.580-585
• /
• 2009

This paper introduces GP(Genetic Programming) based corner detectors for an image processing. Various empirical algorithms have been studied to improve computational speed and accuracy including typical approaches, such as Harris and SUSAN. The these techniques are highly efficient, because properties of corner points are inspected and reflected into the algorithms. However these approaches are limited in discovering an innovative algorithm. In this study, we try to discover a more efficient technique by creating corner detector automatically using evolution of GP. The proposed method is compared to the existing corner detectors for test images.

• Journal of information and communication convergence engineering
• /
• v.12 no.4
• /
• pp.263-270
• /
• 2014

Corner detection and feature extraction are essential aspects of computer vision problems such as object recognition and tracking. Feature detectors such as Scale Invariant Feature Transform (SIFT) yields high quality features but computationally intensive for use in real-time applications. The Features from Accelerated Segment Test (FAST) detector provides faster feature computation by extracting only corner information in recognising an object. In this paper we have analyzed the efficient object detection algorithms with respect to efficiency, quality and robustness by comparing characteristics of image detectors for corner detector and feature extractors. The simulated result shows that compared to conventional SIFT algorithm, the object recognition system based on the FAST corner detector yields increased speed and low performance degradation. The average time to find keypoints in SIFT method is about 0.116 seconds for extracting 2169 keypoints. Similarly the average time to find corner points was 0.651 seconds for detecting 1714 keypoints in FAST methods at threshold 30. Thus the FAST method detects corner points faster with better quality images for object recognition.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.253-261
• /
• 2017

In this paper, a corner detection method based on a new non-cornerness measure is presented. Rather than evaluating local gradients or surface curvatures, as done in previous approaches, a non-cornerness function is developed that can identify stable corners by testing an image region against a set of desirable corner criteria. The non-cornerness function is comprised of two steps: 1) eliminate any pixel located in a flat region and 2) remove any pixel that is positioned along an edge in any orientation. A pixel that passes the non-cornerness test is considered a reliable corner. The proposed method also adopts the idea of non-maximum suppression to remove multiple corners from the results of the non-cornerness function. The proposed method is compared with previous popular methods and is tested with an artificial test image covering several corner forms and three real-world images that are universally used by the community to evaluate the accuracy of corner detectors. The experimental results show that the proposed method outperforms previous corner detectors with respect to accuracy, and that it is suitable for real-time processing.

• Journal of Korea Multimedia Society
• /
• v.14 no.5
• /
• pp.622-631
• /
• 2011

Corners play an important role in describing object features for pattern recognition and identification. This paper proposed a fast and adaptive corner detector in both coarse and fine scale, followed by the framework of the curvature scale space (CSS). An adaptive curvature threshold and evaluating of angles of corner candidates are added to original CSS to remove round corners and false corners in the detecting process. The efficiency of proposed method is compared to other popular detectors in both accuracy criteria, stability and time consuming. Results illustrate that the proposed method performs extremely surpass in both areas.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.1
• /
• pp.37-55
• /
• 2023

In this paper we propose a new algorithm for detecting and counting flowers in a complex background based on digital images. The algorithm mainly includes the following parts: edge contour extraction of flowers, edge contour determination of overlapped flowers and flower counting. We use a contour detection technique in Computer Vision (CV) to extract the edge contours of flowers and propose an improved algorithm with a concave point detection technique to find accurate segmentation for overlapped flowers. In this process, we first use the polygon approximation to smooth edge contours and then adopt the second-order central moments to fit ellipse contours to determine whether edge contours overlap. To obtain accurate segmentation points, we calculate the curvature of each pixel point on the edge contours with an improved Curvature Scale Space (CSS) corner detector. Finally, we successively give three adaptive judgment criteria to detect and count flowers accurately and automatically. Both experimental results and the proposed evaluation indicators reveal that the proposed algorithm is more efficient for flower counting.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.241-245
• /
• 2003

This paper introduces a method that can derive information about the movement of a spreader and skew in order to drive ALS(Automatic Landing System) in the crane used at a harbor. Some methods that use LDL Corner detectors a kind of 2D Laser scanner sensor or Laser distance measuring units to obtain the information in ALS are used presently. But these have some defects in economic efficiency and performance. Therefore, to correct these defects, we propose a method to acquire the information for the movement of a spreader, skew and sway angle using CCD camera image data and Laser distance measuring unit data.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.8
• /
• pp.906-912
• /
• 2012

This paper presents the new method for a six-degree-of-freedom (DOF) motion measurement and those dynamic characterizations in an ultraprecision linear stage using angle sensor-implemented grating interferometry. It consists of a diffractive optical element, a corner cube, four separate two-dimensional position sensitive detectors, four photodiodes and auxiliary optics components. From the previous study, it was confirmed that the proposed optical system could measure a six-DOF motion error in a linear stage. In this article, six-DOF motion dynamic characteristics of the stage were investigated through the step response and with respect to the conditions with a different speed of a slide table. As a result, the natural frequency and damping ratio according to a six-DOF direction was obtained. Also, it was seen that the speed of slide table had an significant effect on a six-DOF displacement motion, especially, X, which was considered as the effect of friction mechanism and local elastic mechanical deformation in a slide guide.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1679-1684
• /
• 2004

This paper introduces a novel approach that can provide the three dimensional information on the movement of a spreader by using two CCD cameras and a laser distance sensor, which enables an ALS (Automatic Landing System) to be used for yard cranes at a harbor. So far a kind of 2D Laser scanner sensor or laser distance measuring units are used as corner detectors for the geometrical matching between the spreader and a container, which provides only 2D information which is not enough for an accurate and fast ALS system required presently. In addition to this deficiency in performance, the price for the system is too high to be adopted widely for the ALS. Therefore, to overcome these defects, a novel method to acquire the three dimensional information for the movement of a spreader including skew and sway angles is proposed using two CCD cameras and a laser distance sensor. To show the efficiency of proposed algorithm, real experiments are performed to show the accuracy improvement in distance measurement by fusing the sensory information of CCD camera and laser distance sensor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3086-3103
• /
• 2017

Video images captured by vehicle cameras often contain blurry or dithering frames due to inadvertent motion from bumps in the road or by insufficient illumination during the morning or evening, which greatly reduces the perception of objects expression and recognition from the records. Therefore, a real-time electronic stabilization method to correct fuzzy video from driving recorders has been proposed. In the first stage of feature detection, a coarse-to-fine inspection policy and a scale nonlinear diffusion filter are proposed to provide more accurate keypoints. Second, a new antiblurry binary descriptor and a feature point selection strategy for unintentional estimation are proposed, which brought more discriminative power. In addition, a new evaluation criterion for affine region detectors is presented based on the percentage interval of repeatability. The experiments show that the proposed method exhibits improvement in detecting blurry corner points. Moreover, it improves the performance of the algorithm and guarantees high processing speed at the same time.