Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions

By Xiaoyang Tan, Bill Triggs. 2007

3,391 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Dacheng Tao
3. Luc Van Gool
4. Ming-Hsuan Yang
5. Xiaoou Tang
6. Yi Yang
7. Andrew Zisserman
8. Yu Qiao

Citations in the corpus

• Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems (2016, positive): “It accounts for illumination variations as in [43], and then computes a BSIF descriptor [44].”
• Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background Statistics (2011, neutral): “NOVEL PATCH-BASED LBPs The LBP descriptor and its variants (e.g., [25], [47]) use short binary strings to encode properties of the local microtexture around each pixel.”
• Face Liveness Detection from a Single Image with Sparse Low Rank Bilinear Discriminative Model (2010, methodology): “This is done through Difference of Gaussian (DoG) filtering which is essentially a bandpass filter and has successfully been applied to remove lighting variations in face images [25].”
• Extended local binary patterns for face recognition (2016, methodology): “tried to make as few assumptions as possible and chose the simple Nearest Neighbor Classifier (NNC).”
• From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, methodology): “Additional important LBP variants include LBP-TOP, proposed by Zhao and Pietikäinen [265], a milestone in using LBP for dynamic texture analysis; the Local Ternary Patterns (LTP) of Tan and Triggs [222], introducing a pair of thresholds and a split coding scheme which allows for encoding pixel simil”
• Local Binary Patterns and Its Application to Facial Image Analysis: A Survey (2011, neutral): “To address this problem, Tan and Triggs [22] extended the original LBP to a version with 3-value codes, called Local Ternary Patterns (LTP).”
• Zero-effort payments: design, deployment, and lessons (2014, background): “However, these results are obtained by constraining subject poses to be either frontfacing [26] or constant across frames [35].”
• Domain adaptive sparse representation-based classification (2015, methodology): “After aligning the face images we transformed them into grayscale images and applied the illumination normalization step described in [29].”
• Age , Gender and Race Estimation from Unconstrained Face Images (2014, methodology): “Following the success of Difference of Gaussians (DoG) filtering based illumination normalization methods in face recognition applications [17], [18], we also use DoG filtering (σ1 = 1.”
• Heterogeneous Face Recognition Using Kernel Prototype Similarities (2013, background): “…normalized by 1) performing planar rotation to set the angle between the eyes to 0 degrees, 2) scaling the images so that the distance between the two pupils is 75 pixels, and 3) cropping the images to a height of 250 pixels and a width of 200 pixels, with the eyes horizontally…”
• Face recognition with learning-based descriptor (2010, background): “Since LBP is encoded by a handcrafted design, many LBP varieties [21, 30, 33] have been proposed to improve the original LBP.”
• Human detection from images and videos: A survey (2016, methodology): “Recently, Tan and Triggs [148] simply extended the LBP to the socalled local ternary pattern (LTP) by allowing 3-valued quantisation of intensity difference.”
• PCANet: A Simple Deep Learning Baseline for Image Classification? (2014, result): “We compare with LBP [18] and LBP of the test images being processed by illumination normalization, P-LBP [21].”
• Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval (2012, background): “The idea of local patterns (the LBP, the LDP, and the LTP) proposed in [16], [25], and [34] has been adopted to define LTrPs.”
• Local Trinary Patterns for human action recognition (2009, background): “Trits are also not new to the LBP world: [18] suggests the use of trits based on pixel values for overcoming difficult illumination conditions.”