Abstract
In this work, we propose a novel method for head pose estimation and face recovery, particularly to solve the potential impacts of noises in signal processing to get an efficient and effective model that is more resilient with annoying effects through adding affine transformation with the low-rank robust subspace regression. Consequently, the corrupted images can be correctly recovered by affine transformations to render more best regression outcomes. Thereby, we need to search so as to get optimal parameters which can be regarded as convex constrained optimization techniques. Afterward, the alternating direction method for multipliers (ADMM) approach is considered and a new set of updated equations is well established so as to update the optimization parameters and affine transformations iteratively in a round-robin manner. Additionally, the convergence of these new updating equations is well scrutinized as well. Thus, the experimental simulations reveal that the proposed method outperforms the state-of-the-art works for head pose estimation and face recovery on some public databases.
Highlights
Four baseline methods, including T-robust principal component analysis (RPCA) [24] +LSR, partial singular value thresholding (PSVT) [23] +LSR, low-rank robust regression (LR-RR) [30], and LRSRR [33] and the proposed one are conducted for comparison, where tensor robust principal component (T-RPCA) + LSR and PSVT + LSR first perform T-RPCA and PSVT on the illuminated and corrupted input data, respectively, and conduct regression on the error free data using the standard least square regression. en, first we try to evaluate the effectiveness of the proposed method based on the synthetic datasets
E comparison of RAEF and RAEY using the aforementioned methods based on the generated synthetic data is shown in Table 1, from which we can see that PSVT + LSR yields better performance than T-RPCA + LSR, as it employs the truncated nuclear norm instead of using more tensors to deal with the outliers and heavy sparse noises
LR-RR is superior to PSVT + LSR and T-RPCA + LSR, as it cleans noises and outliers in and outside subspaces in a supervised manner to yield more precise prediction
Summary
Images, processing for the head pose estimation and image recovery, have been important research potential topics and can have applications in a variety of areas such as surveillance systems [1, 2], signal processing [3, 4], image denoising [5,6,7,8,9] and recovery [10, 11], communications [12], computational imaging [13, 14], and computer vision [15,16,17,18,19]. After the inception of the pioneering baselines of robust principal component analysis (RPCA) by Candes et al [20], a myriad of methods has been considered for robust sparselow-rank image recovery, e.g., [21, 22]. These methods do not work well when the outliers and heavy sparse noises are not normally distributed. Ji et al [26] addressed a regularized sparse regression via combining RPCA [22, 27] with lasso regression [28] to mitigate the influence of outliers in the head pose
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
