Open AccessBody-Boundary-Refined Human Parsing Network based on Fully Convolutional Network and Conditional Random Fields
Author(s) -
Hang Zhao,
Xin Ma
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/646/1/012028
Subject(s) - parsing , segmentation , computer science , conditional random field , pascal (unit) , boundary (topology) , artificial intelligence , prior probability , image segmentation , human body , pattern recognition (psychology) , pixel , computer vision , mathematics , mathematical analysis , bayesian probability , programming language
Human parsing is still a big challenge in computer vision task to accurately label every body part in an image. Current methods of sematic segmentation mainly focus on dividing each independent part and ignore the structural priors of human body. However, the position relationships of different parts, especially which around the area of boundary, indicate their associations and also contribute to the semantic segmentation. In our work, we propose a body-boundary-refined part to refine the segmentation result of human part edge by simply utilizing the structure priors around the body boundary. It puts a penalty mechanism on wrong marginal pixels to improve segmentation performance around the area of body boundary. The network achieves competitive performance on the PASCAL-Parts-dataset and especially the area around the body boundary has been refined.