Show simple item record

dc.contributor.advisor Ji, Hao en
dc.contributor.author Zhu, Vincent en
dc.date.accessioned 2019-11-01T16:33:32Z en
dc.date.available 2019-11-01T16:33:32Z en
dc.date.issued 2019-11-01 en
dc.identifier.uri http://hdl.handle.net/10211.3/214069 en
dc.description.abstract Many real-life intelligent applications such as human beautification and recommender systems, demand accurate hair segmentation from a single portrait image. Recent advances in deep learning achieve or even surpass human-level performance in a multitude of intelligent applications ranging from image classification to game playing. However, due to the lack in a large scale of facial images labeled with high-quality hair masks, current deep learning models appear to have difficulty classifying hair strands accurately. For this research, focusing on semantic hair segmentation, we investigate the use of image matting in deep learning to generate accurate hair masks. In particular, we apply image matting to expand from an initial segmented hair region from deep learning models, via different sampling and propagation matting methods to recover missing hair strands. Afterwards, an ensemble learning approach is proposed to find an optimal performance through the combination of multiple matting results. The experimental results show that image matting applied to hair masks can achieve notably improved results with fine details in hair segmentation. en
dc.format.extent 41 pgs. en
dc.language.iso en en
dc.publisher California State Polytechnic University, Pomona en
dc.rights.uri http://www.cpp.edu/~broncoscholar/rightsreserved.html en
dc.subject machine learning en
dc.subject image matting en
dc.subject hair segmentation en
dc.title Improving Hair Segmentation using Image Matting en
dc.type Thesis en
dc.contributor.department Department of Computer Science en
dc.description.degree M.S. en
dc.contributor.committeeMember Sun, Yu en
dc.contributor.committeeMember Young, Gilbert en
dc.rights.license All rights reserved en

Files in this item


This item appears in the following Collection(s)

Show simple item record

Search DSpace

My Account

RSS Feeds