Abstract
Edge detection is a widely used feature extraction method in various fields, such as image processing, computer vision, machine vision, and so forth. However, it is still a challenging task to extract edges from art images, due to the false edge, shadow, and double lines of art images. In this paper, we propose a dynamic mode decomposition algorithm (DMD) based method for edge detection of art images. This is achieved by proposing a new color space based denoise method to deal with the shadow issue. Then, the false edge and double lines can be resolved by employing DMD method, which can be used to extract sparse features from the denoised images. Here, the sparse features have been enhanced by a new designed eight direction gradient operator. Finally, the effectiveness of our method will be demonstrated through detecting the edges of three classical types of art images (Comic, Oil Painting, and Printmaking).
Highlights
Edge detection is a widely used feature extraction method in image processing [1], [2], computer vision [3], [4], and machine vision [5]–[7]
We provide an edge detection framework for art images to solve the problems including false edge, shadow and double lines
We have proposed an edge detection algorithm based on dynamic mode decomposition, which is used to detect edges of art images
Summary
Edge detection is a widely used feature extraction method in image processing [1], [2], computer vision [3], [4], and machine vision [5]–[7]. The main idea of these methods is using differential operator to calculate a first-order derivative expression These algorithms have good performance for natural images. Art images contain Comic, Oil Painting and Printmaking, which have different features: 1) Comics: in order to show different artistic effects, comics usually contain rich colors and Shadows The main idea of our algorithm contains three steps: Firstly, in order to resolve the shadow issue, we propose a color space denoise method.
Sign-in/Register to view highlights & summary 
Published Version
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.
