Shadow Removal and Hierarchical Graph Cut


Input Image	Output Image

We developed a method to remove the shadow area in an image. We removed the shadow of single image using a hierarchical graph cut which is faster than alpha-expansion method. The users can interactively specify the region where they want to remove the shadow.

Source code: Source code of only the hierarchical graph cut. We can never release the shadow removal software to the public.
Image data: The input images and output images. Only the images taken by Daisuke Miyazaki are included due to the copyright problem. These images can be used for research or educational purpose only. We independently implemented the other author's software, and thus we never guarantee that the output images of other methods, alpha expansion/Ishikawa's method/Finlayson's method/Wu's method, are true; that is, we never guarantee that our implementation is the same as the software developed in the original paper.

Interactive removal of shadows from a single image using hierarchical graph cut: Daisuke Miyazaki, Yasuyuki Matsushita, Katsushi Ikeuchi; IPSJ Transactions on Computer Vision and Applications (CVA); vol. 2, pp. 235-252, 2010/9; https://www.jstage.jst.go.jp/browse/ipsjtcva; Paper: English; Miyazaki-CVA2010.pdf; http://id.nii.ac.jp/1001/00101523/

Interactive shadow removal from a single image using hierarchical graph cut: Daisuke Miyazaki, Yasuyuki Matsushita, Katsushi Ikeuchi; The Ninth Asian Conference on Computer Vision (ACCV2009); 2009/9/26 (2009/9/23-27); Grand New World Hotel, Xi'an, China; http://www.accv2009.org/; Paper: English, Presentation: English; Oral Session 6: Image Enhancement & Visual Attention; Miyazaki-ACCV2009.pdf
http://dx.doi.org/10.1007/978-3-642-12307-8_22
Miyazaki-ACCV2009(compressed).ppt
Miyazaki-ACCV2009(uncompressed).pptx

Back to publication page