Year-end Sale % OFF 
Abstract
Edge detection has been widely used in computer vision and image processing. However, the performance evaluation of the edge-detection results is still a challenging problem. A major dilemma in edge-detection evaluation is the difficulty to balance the objectivity and generality: a general-purpose edge-detection evaluation independent of specific applications is usually not well defined, while an evaluation on a specific application has weak generality. Aiming at addressing this dilemma, this paper presents new evaluation methodology and a framework in which edge detection is evaluated through boundary detection, that is, the likelihood of retrieving the full object boundaries from this edge-detection output. Such a likelihood, we believe, reflects the performance of edge detection in many applications since boundary detection is the direct and natural goal of edge detection. In this framework, we use the newly developed ratio-contour algorithm to group the detected edges into closed boundaries. We also collect a large data set () of real images with unambiguous ground-truth boundaries for evaluation. Five edge detectors (Sobel, LoG, Canny, Rothwell, and Edison) are evaluated in this paper and we find that the current edge-detection performance still has scope for improvement by choosing appropriate detectors and detector parameters.
Highlights
Edge detection is a very important feature-extraction method that has been widely used in many computer vision and image processing applications
Our goal is to evaluate edge detection according to the likelihood of locating the ground-truth object boundary from edge-detection results
Following many prior human-vision and computer-vision studies, we formulate the boundary detection as a boundarygrouping process, in which a closed boundary is obtained by identifying a subset of the detected edges and connecting them sequentially into a closed boundary
Summary
Edge detection is a very important feature-extraction method that has been widely used in many computer vision and image processing applications. This strongly motivates the development of a general and systematic way of evaluating the edge-detection results. Prior edge-detection evaluation methods can be categorized in several ways. They can be classified as subjective and objective methods. The former uses the humanvisual observation and decision to evaluate the performance of edge detection. Quantitative measures are defined based solely on images and the edge-detection results. Edge-detection evaluation methods can be categorized according to their requirement of the ground truth. Edge detection can be quantitatively evaluated in a more credible way. Edge-detection evaluation methods can be categorized based on test images: synthetic-image-based methods and real-image-based methods. A more detailed discussion on various edge detectors and edge-detection evaluation methods can be found in [11]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
