Premium
Regression‐Based Landmark Detection on Dynamic Human Models
Author(s) -
Jang DeokKyeong,
Lee SungHee
Publication year - 2017
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/cgf.13273
Subject(s) - landmark , artificial intelligence , computer science , invariant (physics) , computer vision , body shape , pattern recognition (psychology) , computer graphics , set (abstract data type) , human body , graphics , mathematics , computer graphics (images) , mathematical physics , programming language
Detecting anatomical landmarks on various human models with dynamic poses remains an important and challenging problem in computer graphics research. We present a novel framework that consists of two‐level regressors for finding correlations between human shapes and landmark positions in both body part and holistic scales. To this end, we first develop pose invariant coordinates of landmarks that represent both local and global shape features by using the pose invariant local shape descriptors and their spatial relationships. Our body part‐level regression deals with the shape features from only those body parts that correspond to a certain landmark. In order to do this, we develop a method that identifies such body parts per landmark, by using geometric shape dictionary obtained through the bag of features method. Our method is nearly automatic, as it requires human assistance only once to differentiate the left and right sides. The method also shows the prediction accuracy comparable to or better than those of existing methods, with a test data set containing a large variation of human shapes and poses.