Learning Multi-scale Block Local Binary Patterns for Face Recognition

By Shengcai Liao, Xiangxin Zhu, Zhen Lei, Lun Zhang, S. Li. International Conference on Biometrics, 2007

678 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/52f8eb239997d9a324d4794529c60522db8d08bf

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. Yi Yang
5. Ling Shao
6. Tao A. Xiang
7. Yu Qiao
8. Ming-Hsuan Yang

Citations in the corpus

• Recent advances and trends in visual tracking: A review (2011, background): “Many variants of LBP have been recently proposed, including Local Ternary Patterns (LTP) [39] and multi-scale block LBP (MB-LBP) [40].”
• When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition (2015, methodology): “ features of different facial componets and scales. Similar ideas have widely been used to improve the facial representation capacity of hand-crafted features such as multi-scale local binary pattern [16], multi-scale local phase quantisation [4] and high-dimensional local features [7]. Table 6. Com”
• Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition (2014, neutral): “LBP (TP-LBP) [11] and multi-block LBP (MB-LBP) [12].”
• People detection and tracking from aerial thermal views (2014, background): “Consequently, we focus on the integration of the better performing INRIA-trained detectors in our particle filter framework, dropping LBP cascade from further analysis.”
• Local Binary Patterns and Its Application to Facial Image Analysis: A Survey (2011, positive): “…introduced in [57]: Three-Patch LBP (TP-LBP) and Four-Patch LBP (FP-LBP) are proposed to compare distances between the whole blocks (patches) concerned, instead of single pixel [1] or average intensity in [55], and any distance function can be used (e.g., L 2 norm of their gray level differences).”
• An efficient framework for counting pedestrians crossing a line using low-cost devices: the benefits of distilling the knowledge in a neural network (2020, methodology): “Line 5 uses the cascade classifier with the LBP feature [11, 12, 21] to detect pedestrians and record the attributes x , y , w , and h for each detected pedestrian where x , y , w , and h denote x position, y position, width, and height respectively.”
• Learning Discriminant Face Descriptor (2014, methodology): “In MBLBP [26], multiscale mean filters are applied at the first step, followed with the similar operation of LBP.”
• Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes (2010, methodology): “Inspired by [5], in this work we further develop a Multiscale Block-based SILTP (MB-SILTP) operator to consider the spatial scale.”