Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

By Timo Ojala, Matti Pietikäinen, Topi Mäenpää. 2002

15,301 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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 Representation & Self-Supervised Learning

Citations in the corpus

Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, background): “texture descriptors, and GIST feature are global features that describe the overall statistical properties of an entire image scene in terms of certain spatial cues such as color [56, 99], texture [104-106], or spatial structure information [107], so they”
Describing Textures in the Wild (2013, methodology): “However, LBP u was developed on the Outex data, and it is therefore not surprising that it works so well.”
SUN database: Large-scale scene recognition from abbey to zoo (2010, background): “We also try the rotation invariant extension version [2] of LBP to examine whether rotation invariance is suitable for scene recognition.”
Deep Learning Face Attributes in the Wild (2014, methodology): “Existing methods [12, 2, 1, 15, 26] for attribute recognition first detect faces and their landmarks, and then extract high-dimensional features, such as HOG [3] or LBP [17], from image patches centered on landmarks.”
Inverting Visual Representations with Convolutional Networks (2015, methodology): “LBP is interesting because it is not differentiable, and hence gradient-based methods cannot invert it.”
Multi-class texture analysis in colorectal cancer histology (2016, background): “The third feature set was based on local binary patterns (LBP) 25 .”
Learning kernel logistic regression in the presence of class label noise (2014, methodology): “Now, the images are passed through a series of pre-processing steps: we extracted a meaningful visual vocabulary using dense SIFT [26], then extracted texture information using Local Binary Pattern (LBP) [33], and finally extracted Pyramid Histogram of Oriented Gradients (PHOG) descriptors [13].”
Towards Open World Recognition (2014, background): “Local Binary Patterns (LBP): Local Binary Patterns (LBP) [32] is a texture feature based on occurrence histogram of local binary patterns.”
SUN Database: Exploring a Large Collection of Scene Categories (2014, background): “For both LBP and LBP-HF, we use histogram intersection kernel.”
Parsing IKEA Objects: Fine Pose Estimation (2013, methodology): “For this purpose, we use a well-known texture classification feature, Local Binary Pattern (LBP) [15].”
Oriented Response Networks (2017, methodology): “Orientation information has been explicitly encoded in classical hand-crafted features including Weber’s Law descriptor [5], Gabor features [15, 17], SIFT [31], and LBP [33, 1].”
Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY (2020, methodology): “It has been used in several defect detector applications on varied materials [12,33–35 , 150]”
Distance Metric Learning with Eigenvalue Optimization (2012, methodology): “To compare with the state-of-the-art methods in face verification, we further investigated three types of features for the “aligned” images: 1) raw pixel data by concatenating the intensity value of each pixel in the image; 2) Local Binary Patterns (LBP) (Ojala et al., 2002); and 3) LBP’s variation,”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “More speciﬁ-cally, we have implemented a standard SVM-based sliding window pipeline, with 3 diﬀerent features, namely HOG [4], LBP [78], and LTP [79].”
Robust Facial Expression Recognition Based on Local Directional Pattern (2010, methodology): “Among the appearance-based feature extraction methods, the local binary pattern (LBP) method which was originally introduced for the purpose of texture analysis [23] and its variants [24], [25] were used as a feature descriptor for facial expression representation [9].”
Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns (2015, background): “define a novel mapping from intensities to illumination invariant, 3D spaces, based on the well-known Local Binary Patterns (LBP) feature transform [25, 27, 26].”
CENTRIST: A Visual Descriptor for Scene Categorization (2011, background): “Note that the Census Transform is equivalent (modulo a difference in bit ordering) to the local binary pattern code LBP8;1 [29].”