Fig 1 - available via license: CC BY
Content may be subject to copyright.
Source publication
Edge detection is often performed on disc-like object in Cassini astronomy images to accurately obtain the object’s center position. The existing edge extraction methods usually produce lots of false edge pixels because of noise and the interior details in disc-like objects. In the paper, an edge detection algorithm based on Extreme Learning Machin...
Contexts in source publication
Context 1
... rectangular feature introduced in the face detection system by Viola et al. [13][14] and named after the Haar wavelet. Lienhart R et al. [15] extended it further by adding rectangular features with a rotation of 45°. The extended features are roughly divided into three types: edge features, line features, center-surround features (as shown in Fig. 1). The Haar-like feature can effectively reflect the local gray change information of the image, and can also be quickly calculated through the integral ...
Context 2
... this paper, we select linear features and center-surround features as templates. The linear features Fig.1 (2a)-(2b) are computed in the dimensions of 2×3 and 2×4, respectively. They are rotated at 45° and 90° to get new features Fig.1 (2c)-(2h). ...
Context 3
... linear features Fig.1 (2a)-(2b) are computed in the dimensions of 2×3 and 2×4, respectively. They are rotated at 45° and 90° to get new features Fig.1 (2c)-(2h). The feature Fig.1 (3a) uses a 3×3 window, which is also rotated through 45° to get feature Fig.1 (3b). ...
Context 4
... are rotated at 45° and 90° to get new features Fig.1 (2c)-(2h). The feature Fig.1 (3a) uses a 3×3 window, which is also rotated through 45° to get feature Fig.1 (3b). Finally, it is calculated using the integral image and 10 feature values are extracted for each pixel. ...
Similar publications
The magnetic anomaly combines the response of various rocks with magnetic susceptibility that eventually gives fundamental information regarding the structure and dimensions of the geological features hidden underneath. Over the years, edge detection filters successfully separated the geological structures based on the sharp discontinuity in the ro...
In order to improve the accuracy of binocular vision manipulator control, a target positioning method based on improved Canny operator is proposed. First, the image acquired by the left and right cameras is converted into an HSI color model, and the range of the target in the image is located by the image color feature as a region of interest (ROI)...
Digital images captured by camera contains many useful information. Many research has been done for content retrieval from natural images, for example, object detection, face recognition and automatic text extraction. In recent years, many methods are suggested for extracting text data from images as it has wide range of applications. Three popular...
Citations
A segmentation process is usually required in order to analyze an image. One of the available segmentation approaches is by detecting the edges on the image. Up to now, there are many edge detection algorithms that researchers have proposed. Thus, the purpose of this systematic literature review is to investigate the available quality assessment methods that researchers have utilized to evaluate the performance of the edge detection algorithms. Due to the vast number of available literature in this area, we limit our search to only open-access publications. A systematic search in five publisher websites (i.e., IEEExplore, IET digital library, Wiley, MDPI, and Hindawi) and Scopus database was carried out to gather resources that are related to the edge detection algorithms. Seventy-three publications that are about developing or comparing edge detection algorithms have been chosen. From these publication samples, we have identified 17 quality assessment methods used by researchers. Among the popular quality assessment methods are visual inspection, processing time, confusion-matrix based measures, mean square error (MSE)-based measures, and figure of merit (FOM). This survey also indicates that although most of the researchers only use a small number of test images (i.e., less than 10 test images), there are available datasets with a larger number of images for digital image segmentation that researchers can utilize.
In Cassini ISS (Imaging Science Subsystem) images, contour detection is often performed on disk-resolved objects to accurately locate their center. Thus, contour detection is a key problem. Traditional edge detection methods, such as Canny and Roberts, often extract the contour with too much interior details and noise. Although the deep convolutional neural network has been applied successfully in many image tasks, such as classification and object detection, it needs more time and computer resources. In this paper, a contour detection algorithm based on H-ELM (Hierarchical Extreme Learning Machine) and DenseCRF (Dense Conditional Random Field) is proposed for Cassini ISS images. The experimental results show that this algorithm’s performance is better than both traditional machine learning methods, such as Support Vector Machine, Extreme Learning Machine and even deep Convolutional Neural Network. The extracted contour is closer to the actual contour. Moreover, it can be trained and tested quickly on the general configuration of PC, and thus can be applied to contour detection for Cassini ISS images.
