Foreground editing technique to reduce interaction

In this paper we introduce a method to extract foreground from an image or a video and blend it into another environment. We analyze the weakness of previous algorithms, and propose a new method to improve the automaticity of the algorithm and reduce interactions with users. Self-adaption threshold and segmentation technique are used to preprocess the images or frames. And then we use the image matting and illustration technique to refine the segmentation results. Our method is also suitable for video editing to reduce the users operation. The experiment demonstrates that our algorithm can be used under several challenging scenarios.

[1]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Carlo Tomasi,et al.  Alpha estimation in natural images , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Yule Yuan,et al.  Automatic foreground extraction of clothing images based on GrabCut in massive images , 2012, 2012 IEEE International Conference on Information Science and Technology.

[4]  Michael F. Cohen,et al.  Optimized Color Sampling for Robust Matting , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Hyeran Byun,et al.  Accurate Foreground Extraction Using Graph Cut with Trimap Estimation , 2006, PSIVT.

[7]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  R. Ciupa,et al.  International Conference , 2023, In Vitro Cellular & Developmental Biology - Animal.