“EasyCut” — Automatic Foreground Extraction
Date Issued
2012
Date
2012
Author(s)
Yang, Ying-Ming
Abstract
Image segmentation is an essential topic in computer vision. It is generally applied to extract foreground objects out of an image for further usages, such as tracking, recognition or image editing. Retrieving perfect segmentation results automatically is a difficult issue. Therefore, the concept of “interactive segmentation” allows users to provide prior knowledge in order to obtain better outcome.
This thesis presents an automatic extraction technique based on Snake (Active Contour) and GrabCut method. It aims to generate more robust result without user interaction. A Gaussian pyramid of the input image is created firstly, Snake algorithm then derives rough foreground and background separation on each level as the initial for GrabCut. Two novel schemes are exploited to provide more robustness and flexibility during GrabCut’s iterative energy minimization process. These mechanisms simulate the Latent Dirichlet Allocation (LDA) model and unsupervised probabilistic stochastic process called Chinese Restaurant Process. In other words, they assist to refine Gaussian Mixture Models (GMM) and adaptively determine the number of Gaussian components in used.
The experimental result shows that proposed method can automatically generate satisfactory extraction output from images which contain obvious foreground objects.
This thesis presents an automatic extraction technique based on Snake (Active Contour) and GrabCut method. It aims to generate more robust result without user interaction. A Gaussian pyramid of the input image is created firstly, Snake algorithm then derives rough foreground and background separation on each level as the initial for GrabCut. Two novel schemes are exploited to provide more robustness and flexibility during GrabCut’s iterative energy minimization process. These mechanisms simulate the Latent Dirichlet Allocation (LDA) model and unsupervised probabilistic stochastic process called Chinese Restaurant Process. In other words, they assist to refine Gaussian Mixture Models (GMM) and adaptively determine the number of Gaussian components in used.
The experimental result shows that proposed method can automatically generate satisfactory extraction output from images which contain obvious foreground objects.
Subjects
Image Segmentation
Foreground Extraction
Active Contour
Gaussian Mixture Model
Latent Dirichlet Allocation
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-101-R99944035-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):eaf73fd56b5fe99668c905d2d965c7b4