Local Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-Order Local Pattern Descriptor

By Baochang Zhang, Yongsheng Gao, Sanqiang Zhao, Jianzhuang Liu. IEEE Transactions on Image Processing, 2010

1,104 citations recorded by the source corpus.

This paper proposes a novel high-order local pattern descriptor, local derivative pattern (LDP), for face recognition. LDP is a general framework to encode directional pattern features based on local derivative variations. The nth-order LDP is proposed to encode the (n-1)th -order local derivative direction variations, which can capture more detailed information than the first-order local pattern used in local binary pattern (LBP). Different from LBP encoding the relationship between the central point and its neighbors, the LDP templates extract high-order local information by encoding various distinctive spatial relationships contained in a given local region. Both gray-level images and Gabor feature images are used to evaluate the comparative performances of LDP and LBP. Extensive experimental results on FERET, CAS-PEAL, CMU-PIE, Extended Yale B, and FRGC databases show that the high-order LDP consistently performs much better than LBP for both face identification and face verification under various conditions.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2c06c14b68f6621b4d1b9e1cf8fe81069a8d42ce

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

In Signal Processing

Citations in the corpus

Local Directional Number Pattern for Face Analysis: Face and Expression Recognition (2013, methodology): “Given that SVM makes binary decisions, multi-class clas-siﬁcation can be achieved by adopting the one-against-one or one-against-all techniques.”
Learning Compact Binary Face Descriptor for Face Recognition (2015, neutral): “0 LDP [68] 94.”
Discriminative multi-manifold analysis for face recognition from a single training sample per person (2011, methodology): “Ten state-of-the-art local feature methods were compared, including LBP [1], LGBP [60], HGGP [57], POEM [42], LDP [56], G-LDP (Gabor-based LDP) [56], RSA (robust and scale approach) [35], GV-LBP [35], and the methods proposed in [61] and [43], respectively.”
Gabor Convolutional Networks (2017, background): “The Gabor wavelets (kernels or filters) are defined as follows [30, 33]:”
Local binary features for texture classification: Taxonomy and experimental study (2017, neutral): “Guo et al”
Application-Oriented License Plate Recognition (2013, background): “However, surprisingly, while many face recognition works report performance on an FRR with a preselected FAR [25], [26], many LPR works, including the aforementioned and those selected for the performance comparison reported in Section IV-B, have not provided the associated FPR and FAR.”
A Micro-GA Embedded PSO Feature Selection Approach to Intelligent Facial Emotion Recognition (2017, background): “Local derivative pattern (LDP) [15] is a high-order local pattern descriptor, which encodes directional pattern features based on local derivative variations.”