Bekir DİZDAROĞLU

Gradient domain photomontage via interactive object selection

One of the most critical steps in photomontage is marking an object that is to be copied from a source image to a target image efficiently. Some unexpected and unwanted effects such as bleeding usually occur on the resulting image if the object is roughly marked, copied, and then pasted to the target region, even when using the Poisson equation approach. Moreover, original color information for the pasted object cannot be preserved, and color values for the boundary pixels of the pasted object may change and/or blurriness may occur when using some methods described in the literature. The proposed methods presented in this paper are designed to efficiently overcome these problems. The problem of rough selection is solved by employing the modified intelligent scissors method. In order to prevent diffusion around the boundary of the pasted object, a band region is created, and the texture information from the source image is used. In order to better preserve the color information of the pasted object, a fidelity term is added to the Poisson equation. Our approach for producing a photomontage is more efficient than other methods in the literature in terms of interactive object selection and automated band region creation. In our approach, readjustment is not necessary for required parameters in the operations. Qualitative and quantitative results prove the advantages of the proposed methods.

PDF

___

Canny J. A computational approach to edge detection. IEEE T Pattern Anal 1986; 8: 679-698.
Mortensen EN, Barrett WA. Intelligent scissors for image composition. In: The 22nd Annual Conference on Computer Graphics and Interactive Techniques; 1995. New York, NY, USA: ACM. pp. 191-198.
Chuang YY, Curless B, Salesin DH, Szeliski R. A Bayesian approach to digital matting. In: 2001 IEEE Computer Society Conference; 8–14 December 2001; Kauai, HI, USA. Los Alamitos, CA, USA: IEEE. pp. 264-271.
Levin A, Lischinski D, Weiss Y. A closed-form solution to natural image matting. IEEE T Pattern Anal 2008; 30:228-242.
Nguyen TNA, Cai J, Zhang J, Zheng J. Robust interactive image segmentation using convex active contours. IEEE T Image Process 2012; 21: 3734-3742.
Criminisi A, Sharp T, Blake A. GeoS: Geodesic image segmentation. In: The 10th European Conference on Computer Vision; 12–18 October 2008; Marseille, France. Berlin, Germany: Springer. pp. 99-112.
Grady L. Random walks for image segmentation. IEEE T Pattern Anal 2006; 28: 1768-1783.
Boykov Y, Jolly MP. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: The 8th IEEE International Conference on Computer Vision; July 2001; Vancouver, Canada. Danvers, MA,USA: IEEE. pp. 105-112.
Iserles A. A First Course in the Numerical Analysis of Differential Equations. 2nd ed. New York, NY, USA: Cambridge University Press, 2009.
Bhat P, Curless B, Cohen M, Zitnick CL. Fourier analysis of the 2D screened Poisson equation for gradient domain problems. In: The 10th European Conference on Computer Vision; 12–18 October 2008; Marseille, France. Berlin, Germany: Springer. pp. 114-128.
Morel JM, Petro AB, Sbert C. Fourier implementation of Poisson image editing. Pattern Recogn Lett 2012; 33: 342-348.
Cuadros VA, Nonato LG, Pascucci V. Combinatorial Laplacian image cloning. In: The 24th SIBGRAPI Conference on Graphics, Patterns, and Images Tutorials; 28–30 August 2011; Maceio, Brazil. Danvers, MA, USA: IEEE. pp.236-241.
Yang W, Zheng J, Cai J, Rahardja S, Chen CW. Natural and seamless image composition with color control. IEEE T Image Process 2009; 18: 2584-2592.
Jia J, Sun J, Tang CK, Shum HY. Drag-and-drop pasting. ACM T Graphic 2006; 20: 631-637.
Tao MW, Johnson MK, Paris S. Error-tolerant image compositing. Int J Comput Vision 2013; 103: 178-189.
Perez P, Gangnet M, Blake A. Poisson image editing. ACM T Graphic 2003; 22: 313-318.