中文
Published date:2014-03-27    Provided by:
 
Title: Face recognition against large pose variation 
Guest SpeakerLiu WanquanCurtin University, Australia
Time2014-1-16, 4:00-6:00
LocationMeeting Room 7215, School of Science
Content &Introduction 
In this talk, I propose a novel method for face recognition with multiple view images to overcome the large pose variation and missing pose issue. By introducing a novel mixed norm, the proposed method automatically selects candidates from the gallery to best represent a group of high correlated face images in a query set to improve classification accuracy. This mixed norm combines the advantages of both sparse representation based classification (SRC) and joint sparse representation based classification (JSRC). A tradeoff between the L1 -norm from SRC and L1, 2-norm from JSRC is introduced to achieve this goal. Due to this property, the proposed method decreases the influence when a face image is unseen and has large pose variation in recognition process. And when some face images with a certain degree of unseen pose variation appear, this mixed norm will find an optimal representation for these query images based on the shared information induced from multiple views. Moreover, we also address an open problem in robust sparse representation and classification which is using L1 –norm on the loss function to achieve a robust solution. To solve this formulation, we derive a simple, yet provably convergent algorithm based on the powerful alternative directions method of multipliers (ADMM) framework.