Open AccessA Dynamic Mode Decomposition Based Edge Detection Method for Art Images
Author(s) -
Chongke Bi,
Ye Yuan,
Ronghui Zhang,
Yiqing Xiang,
Yuehuan Wang,
Jiawan Zhang
Publication year - 2017
Publication title -
ieee photonics journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.725
H-Index - 73
eISSN - 1943-0655
pISSN - 1943-0647
DOI - 10.1109/jphot.2017.2766881
Subject(s) - engineered materials, dielectrics and plasmas , photonics and electrooptics
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).