DocumentCode :
3186903
Title :
Warp that smile on your face: Optimal and smooth deformations for face recognition
Author :
Gass, Tobias ; Pishchulin, Leonid ; Dreuw, Philippe ; Ney, Hermann
Author_Institution :
Comput. Vision Lab., ETH Zurich, Zurich, Switzerland
fYear :
2011
fDate :
21-25 March 2011
Firstpage :
456
Lastpage :
463
Abstract :
In this work, we present novel warping algorithms for full 2D pixel-grid deformations for face recognition. Due to high variation in face appearance, face recognition is considered a very difficult task, especially if only a single reference image, for example a mug-shot, per face is available. Usually model-based approaches with additional training data are used to cope with several types of variation occurring in facial imaging. Image warping contrarily yields a distance measure which is invariant with regard to several types of variation. This allows for precise recognition even using only very few reference observations. Due to the computationally complex problem of optimal 2D warping, pseudo-2D warping-based approaches in the past represented strong approximations of the original problem, and were mainly successful on data with low variability or rectified images. We propose a novel 2D warping method which is globally optimal and makes no prior assumtions on the data variability besides two-dimensional smootheness constraints which both avoid local mirroring and gaps and significantly speed up the optimization. Furthermore, we show that occlusion handling is imperative to obtain smooth warpings in a variety of domains. We evaluate our novel algorithm on various well known databases, such as the AR-Face and CMU-PIE database, and provide a detailed comparison to existing warping approaches. We show that by using simple relative 2D constraints, strong local features and a kernel, which is robust w.r.t. occlusions, our computationally complex approaches outperform state-of-the-art results for recognizing faces under varying expressions, occlusions and poses. Most interestingly, we achieve higher accuracy using fewer training instances per class compared to methods learning a model of the 3D shape.
Keywords :
approximation theory; computer graphics; face recognition; image representation; pose estimation; visual databases; 2D pixel-grid deformation; 3D shape; CMU-PIE database; computationally complex problem; data variability; face recognition; facial imaging; image warping algorithm; local mirroring; model-based approach; occlusion handling; optimal 2D warping; optimization; precise recognition; pseudo-2D warping method; relative 2D constraint; smooth deformation; smooth warping; training data; two dimensional smootheness constraint; Approximation methods; Databases; Face; Face recognition; Hidden Markov models; Optimization; Pixel;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automatic Face & Gesture Recognition and Workshops (FG 2011), 2011 IEEE International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
978-1-4244-9140-7
Type :
conf
DOI :
10.1109/FG.2011.5771442
Filename :
5771442
Link To Document :
بازگشت