Shape Analysis of Local Facial Patches for 3D Facial三维人脸局部面部斑块形状分析.pptVIP

Publication Xia BAIQIANG ,Boulbaba Ben Amor ,Hassen,Mohamed Daoudi ,Lahoucine Ballihi, “Gender and 3D Facial Symmetry What’s the Relationship?” ,The 10th IEEE Conference on Automatic Face and Gesture Recognition, 2013. * End * * * * * * * * * * * * * * * * * * * * * * * * Gender and 3D Facial Symmetry: What’s the Relationship ? Xia BAIQIANG (University Lille1/LIFL) Boulbaba Ben Amor (TELECOM Lille1/LIFL) Hassen Drira (TELECOM Lille1/LIFL) Mohamed Daoudi (TELECOM Lille1/LIFL) Lahoucine Ballihi (University Lille1/LIFL) Journee doctorant , December 12, 2012. * Outline Introduction State-of-the-art Proposed approach Methodology Symmetry Capture Dense Scalar Field (DSF) Gender Classification Experiments Robustness to age and gender variations Robustness to expression variations Conclusions and future directions * * Introduction Motivation to this work Why come to this idea ? Gender is essential visual attribute in human face Human faces are approximately symmetric Why use 3D face, not 2D face ? Robust to illumination and pose changes Capture more details face information * * State-of-the-art Liu et al. used Variance Ratio (Vr) of symmetric height and orientation differences in face regions for gender classification. 111 full 3D face models were used and a result of 96.22% was achieved with a linear classifier. cooperative Based on small dataset * * * * Training stage 3D scan preprocessing Testing stage Symmetry Capture (DSF) Random Forest Adaboost SVM PCA-based transformation Female Reduced feature space Classification Training 3D scan Testing 3D scan Proposed approach Symmetry Capture * * Equal angular curves extraction On the face Preprocessed face Nose tip Radial curves On the face Represent facial surface S by a set of parameterized radial curves emanating from the nose tip. Symmetry Capture * * Corresponding symmetrical curves , . Capture symmetry by shape comparison of and . Shape Analysis