Robust Face Recognition for Uncontrolled Pose and Illumination Changes
Citations
131 citations
Cites methods from "Robust Face Recognition for Uncontr..."
...Table 4 shows that our proposed system outperforms all he above-mentioned methods including the recent method proosed in (De Marsico et al., 2013) with an impressive margin of 6% in the recognition rate....
[...]
...…& Cipolla, 007), a method using Support Vector Machines (SVM) (Guo, Li, & han, 2000), a recent approach based on Hierarchical Multiscale LBP HMLBP) (Guo, Zhang, & Mou, 2010), and the method called “FACE” roposed in (De Marsico et al., 2013), which is the most recent ethod evaluated on this dataset....
[...]
...Although LFW is basically designed for metric learning for face verification, (De Marsico et al., 2013) evaluated some of the most popular face recognition algorithms as well as their own method on a subset of this database....
[...]
100 citations
Cites methods from "Robust Face Recognition for Uncontr..."
...Researchers have proposed a variety of methods [1]–[5], in which the methods based on subspace analysis is an important branch....
[...]
95 citations
Cites methods from "Robust Face Recognition for Uncontr..."
...Karuppusamy et al. [226] proposed an embedded implementation of facial landmarks detection based on both Viola-Jones face detector and facial landmarks detection using extended Active Shape Model (ASM) [227]....
[...]
...[226] proposed an embedded implementation of facial landmarks detection based on both Viola-Jones face detector and facial landmarks detection using extended Active Shape Model (ASM) [227]....
[...]
67 citations
64 citations
References
26,531 citations
18,620 citations
"Robust Face Recognition for Uncontr..." refers background in this paper
...It first submits the image to a global face detector (Viola-Jones [44] or Rowley [38]), which extracts all regions of interest (ROI) from an image that includes at least one face....
[...]
9,658 citations
"Robust Face Recognition for Uncontr..." refers result in this paper
...As an example, Sparse Representation-based Classification (SRC) [49] requires precise alignment, notwithstanding claims made by the authors, and recent results cast doubt about the usefulness of SRC for image classification [37]....
[...]
5,742 citations
"Robust Face Recognition for Uncontr..." refers methods in this paper
...In summary, FACE testing has access to a diversity of databases that includes four different data sets: CDB [56], LFW [22], SCface [17], and FERET [34]....
[...]
...databases that includes four different data sets: CDB [56], LFW [22], SCface [17], and FERET [34]....
[...]
...The LFW database contains 13 233 target face images of 5749 different individuals; 1680 people have two or more image instances, while the remaining 4069 people have just a single image instance in the database....
[...]
...F. Integrating Image Quality and System Reliability Measures The results reported in Table II show that, among databases with an acceptable resolution (therefore excluding LFW), CDB (3 img) is the most problematic one in terms of performances....
[...]
...However, while HMLBP is much better on CDB than on LFW, ILDA is better on LFW than CDB....
[...]
5,563 citations
"Robust Face Recognition for Uncontr..." refers methods in this paper
...[18] Z. Guo, L. Zhang, D. Zhang, and X. Mou, “Hierarchical multiscale LBP for face and palmprint recognition,” in Proc....
[...]
...FACE is compared against SVM, incremental SVM (ISVM), PCA, incremental LDA (ILDA), ICA, and hierarchical multiscale local binary pattern (HMLBP)....
[...]
...However, while HMLBP is much better on CDB than on LFW, ILDA is better on LFW than CDB....
[...]
...The RRs found using LFW are much lower for both FACE (local correlation module) and HMLBP, even though CDB and LWF seem to contain images with similar characteristics....
[...]
...Even in this case, performances of FACE and HMLBP on CDB and LFW are very different....
[...]