PyMatting: A Python Library for Alpha Matting

Thomas Germer; Tobias Uelwer; Stefan Conrad; Stefan Harmeling

doi:10.21105/joss.02481

PyMatting: A Python Library for Alpha Matting

The Journal of Open Source Software ◽

10.21105/joss.02481 ◽

2020 ◽

Vol 5 (54) ◽

pp. 2481 ◽

Cited By ~ 1

Author(s):

Thomas Germer ◽

Tobias Uelwer ◽

Stefan Conrad ◽

Stefan Harmeling

Keyword(s):

Alpha Matting

Download Full-text

Adaptive Propagation-Based Color-Sampling for Alpha Matting

IEEE Transactions on Circuits and Systems for Video Technology ◽

10.1109/tcsvt.2014.2302531 ◽

2014 ◽

Vol 24 (7) ◽

pp. 1101-1110 ◽

Cited By ~ 6

Keyword(s):

Alpha Matting

Download Full-text

Alpha Matting Using Immune Feature Extraction Network

Multimedia and Signal Processing - Communications in Computer and Information Science ◽

10.1007/978-3-642-35286-7_27 ◽

2012 ◽

pp. 207-214

Author(s):

Hong Ge ◽

Xueming Yan ◽

Kazunori Okada ◽

Yan Li

Keyword(s):

Feature Extraction ◽

Alpha Matting

Download Full-text

Motion Segmentation and Matting by Graph Cut

Graph-Based Methods in Computer Vision ◽

10.4018/978-1-4666-1891-6.ch005 ◽

2012 ◽

pp. 95-117

Author(s):

Jiangjian Xiao

Keyword(s):

Video Sequence ◽

Graph Cut ◽

The Other ◽

Robust Approach ◽

Alpha Matting ◽

Optical Flow Field ◽

Segmentation Boundary ◽

Clustering Approach ◽

Multiple Frames ◽

Layer Segmentation

Given a video sequence, obtaining accurate layer segmentation and alpha matting is very important for video representation, analysis, compression, and synthesis. By assuming that a scene can be approximately described by multiple planar or surface regions, this chapter describes a robust approach to automatically detect the region clusters and perform accurate layer segmentation for the scene. The approach starts from optical flow field or small corresponding seed regions and applies a clustering approach to estimate the layer number and support regions. Then, it uses graph cut algorithm combined with a general occlusion constraint over multiple frames to solve pixel assignment over multiple frames to obtain more accurate segmentation boundary and identify the occluded pixels. For the non-textured ambiguous regions, an alpha matting technique is further used to refine the segmentation and resolve the ambiguities by determining proper alpha values for the foreground and background, respectively. Based on the alpha mattes, the foreground object can be transferred into the other video sequence to generate a virtual video. The author’s experiments show that the proposed approach is effective and robust for both the challenging real and synthetic sequences.

Download Full-text