A color adjustment method for automatic seamless image blending

Authors:
Xianji Li;Dongho Kim
Affiliations:
Department of Digital Media, Graduate School of Soongsil University, Seoul, Korea;Department of Digital Media, Graduate School of Soongsil University, Seoul, Korea
Venue:
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: interaction platforms and techniques
Year:
2007

Citing 8
Cited 0

A multiresolution spline with application to image mosaics

ACM Transactions on Graphics (TOG)
Poisson image editing

ACM SIGGRAPH 2003 Papers
Lazy snapping

ACM SIGGRAPH 2004 Papers
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Poisson matting

ACM SIGGRAPH 2004 Papers
Eliminating Structure and Intensity Misalignment in Image Stitching

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Drag-and-drop pasting

ACM SIGGRAPH 2006 Papers
Filling-in by joint interpolation of vector fields and gray levels

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a stable automatic system for image composition, which can well control the color difference between two images, and produce a seamless composite image with color continuity. This is a user-friendly system that reduces the user's manual tasks. We observe that Poisson image editing written by Perez et al. [8] blends well for seamless boundary automatically. However, the color of user-selected region can be changed after applying this method. So the object loses its original color tone after blending. To solve this problem, firstly we check out the case of object color being changed rapidly. It can be done by calculating color temperatures of two input images and comparing the white balance with each other. Next, a distance ratio rule is applied to controls the pixels included in the region between the user-selected boundary and object boundary.