Local Higher-Order Statistics (LHS) for Texture Categorization and Facial Analysis

142 citations recorded by the source corpus.

How researchers see this paper

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

Describing Textures in the Wild (2013, methodology): “Furthermore, IFV is conceptually simpler than the multiple specialized features used in [31] for material recognition.”
Face Recognition Systems: A Survey (2020, background): “• Bhattacharyya distance [104,105]: The Bhattacharyya distance is a statistical measure that quantifies the similarity between two discrete or continuous probability distributions.”
Learning Compact Binary Face Descriptor for Face Recognition (2015, unknown): “30 LHS [51] 81.”
Texture Feature Extraction Methods: A Survey (2019, methodology): “The feature encoding step may use vector of locally aggregated descriptors (VLAD) [232], [233], Fisher vector and improved Fisher vector [234]–[236].”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, methodology): “For instance recognition, CUReT, UIMD, UIUC are saturated by modern techniques such as Sifre and Mallat (2013); Sharma et al. (2012) and Sulc and Matas (2014), with accuracies above ≥ 99 %.”
Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection (2014, background): “, [17]–[20]) have reported performance on LFW, but all of them can be classified as single media (image vs.”
Fisher Vector Faces in the Wild (2013, methodology): “In [29], the Fisher vector encoding of local intensity differences was used as a face descriptor.”