Papers by Keyword: Edge Detection

Paper TitlePage

Authors: Xiang Rong Yuan
Abstract: The gray-scale digital image is two-dimension, most of the previous polynomial fitting methods for edge detection belong to one-dimension methods. The new method of two-dimension polynomial fitting for edge detection is presented. The grey level data of the interest area around the edge in the image are fitted by the two-dimension polynomial function. The edge of interest is identified by finding the maximum of the form of gradient of the fitting function. Because the two-dimension fitting is actually more suitable for the two-dimension image, the fitting results of two dimension method are significantly better than that of the one-dimension method. It is shown through the analysis of the synthesis image that the results of surface fitting and edge identification used of the proposed method are quite good.
Authors: Sinué Ontiveros-Zepeda, José Antonio Yagüe-Fabra, Roberto Jiménez Pacheco, Francisco Javier Brosed-Dueso
Abstract: The number of factors influencing the CT process for metrology applications increases its complexity and cause the loss of accuracy during CT measurements. One of the most critical is the edge detection also called surface extraction or image segmentation, which is the process of surface formation from the CT`s volume data. This paper presents different edge detection methods commonly used in areas like machine and computer vision and they are analyzed as an alternative to the commonly and commercially used for CT metrology applications. Each method is described and analyzed separately in order to highlight its advantages and disadvantages from a metrological point of view. An experimental comparative between two of them is also shown.
Authors: Zahari Taha, Jessnor Arif Mat Jizat
Abstract: In this paper a comparison of two approaches for collision avoidance of an automated guided vehicle (AGV) using monocular vision is presented. The first approach is by floor sampling. The floor where the AGV operates, is usually monotone. Thus, by sampling the floor, the information can be used to search similar pixels and establish the floor plane in its vision. Therefore any other objects are considered as obstacles and should be avoided. The second approach employs the Canny edge detection method. The Canny edge detection method allows accurate detection, close to real object, and minimum false detection by image noise. Using this method, every edge detected is considered to be part of an obstacle. This approach tries to avoid the nearest obstacle to its vision. Experiments are conducted in a control environment. The monocular camera is mounted on an ERP-42 Unmanned Solution robot platform and is the sole sensor providing information for the robot about its environment.
Authors: Song Yang, Long Tan Shao, Xiao Xia Guo, Xiao Liu, Bo Ya Zhao
Abstract: A segmentation method of combining gray-level threshold and fractal feature for crack images is proposed, and the fractal law for the perimeter and area of the target is introduced as the constraint condition for the image segmentation of crack. At first, Otsu algorithm is used for the initial segmentation of the crack image, and then the edge of crack is optimized in accordance with fractal law. At last, boundary of crack is determined, and the final result of the image segmentation is obtained. This method makes full use of the fractal geometry law and image information, to effectively solve the problems such as crack contour detection, regional connection and cross crack identification. Several typical examples are analyzed, and the results show that this method has a good segmentation effect on crack images, and it can also be used to identify the other images which have fractal feature.
Authors: Yang Lei, Ying Zhang
Abstract: A vehicle plate location algorithm under complex scenes is presented that based on interest region extraction and morphology. First of all, extract the edge of the lane, obtain the driveway area from the edge of the road, confirm the region of interest with the experiences in the driveway area, it can reduce the scope for searching. Then preprocessing is used in the vehicle image, including gray, edge detection and binary transformation is used. Then a series of morphological operations are used to look for candidate regions that probably contain the characters in range of sizes. Finally, the vehicle license plate can be found according to the median filter.
Authors: Yuan Luo, Chao Ji, Yi Zhang, Zhang Fang Hu
Abstract: Application of machine vision method for MEMS dynamic parameters were measured, the testing image have a certain degree of ambiguity.This paper presents a sub-pixel algorithm based on fractal and wavelet transform: Firstly, using self-similar characteristics of fractal interpolation to overcome the problem ,that can not be accurate interpolation and the edge of the image reconstruction. Then because of abilities of high resolution and anti-noise,using wavelet transform modulus maxima,the image edge detection.The experimental results show that the algorithm can reach 0.02 pixel accuracy.
Authors: Dan Tian, Jing Fei Wu, Ya Jie Yang
Abstract: This paper proposes a novel fractional-order Laplacian operator for image edge detection. The proposed operator can be seen as generalization of the second-order Laplacian operator. The goal is to utilize the global characteristic of the fractional derivative for extracting more edge details. A thresholding is set based on the average fractional-order gradient for marking the edge points, and then the image edge can be extracted. Experiments show that the proposed fractional-order operator yields good visual effects.
Authors: Sheng Hua Teng, Ning Yang
Abstract: To solve the dense matching problem for stereoscopic satellite images, a hybrid matching scheme integrating multiple methods is proposed. This scheme utilizes two types of matching element including grid points and edge points. First the geometrically constrained cross-correlation (GC3) method is used to extract matching grids. While in less textured regions using GC3 cannot get sufficient matching grids, so the local affine transformation is used to establish the region correspondence, and more matching grids can be generated. Edges are extracted by Canny operator and approximated with a series of straight edge segments using a polygon approximation. Based on these approximated edges, edge correspondences between image pairs are established using GC3. This scheme fuses the region based and the feature based matching methods. It has been tested with real satellite images and the results demonstrate its accuracy and efficiency.
Authors: Dong Mei Li, Jing Lei Zhang
Abstract: Images matching is the basis of image registration. For their difference, a improved SURF(speeded up robust features) algorithm was proposed for the infrared and visible images matching. Firstly, edges were extracted from the images to improve the similarity of infrared and visible images. Then SURF algorithm was used to detect interest points, and the dimension of the point descriptor was 64. Finally, found the matching points by Euclidean distance. Experimental results show that some invalid data points were eliminated.
Authors: Muralindran Mariappan, Manimehala Nadarajan, Rosalyn R. Porle, Vigneswaran Ramu, Brendan Khoo Teng Thiam
Abstract: Biometric identification has advanced vastly since many decades ago. It became a blooming area for research as biometric technology has been used extensively in areas like robotics, surveillance, security and others. Face technology is more preferable due to its reliability and accuracy. By and large, face detection is the first processing stage that is performed before extending to face identification or tracking. The main challenge in face detection is the sensitiveness of the detection to pose, illumination, background and orientation. Thus, it is crucial to design a face detection system that can accommodate those problems. In this paper, a face detection algorithm is developed and designed in LabVIEW that is flexible to adapt changes in background and different face angle. Skin color detection method blending with edge and circle detection is used to improve the accuracy of face detected. The overall system designed in LabVIEW was tested in real time and it achieves accuracy about 97%.
Showing 1 to 10 of 272 Paper Titles