Description of interest regions with local binary patterns

By Marko Heikkilä, Matti Pietikäinen, Cordelia Schmid. Pattern Recognition, 2009

1,307 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/369634f497852e05d5e72b12874e2a3db2d3945f

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 Information Systems

Citations in the corpus

Local binary features for texture classification: Taxonomy and experimental study (2017, neutral): “The six classes of our taxonomy”
Effective and Efficient Global Context Verification for Image Copy Detection (2017, methodology): “To achieve the invariance to the linear intensity and gradient changes, similar to CS-LBP [40], we compute the signs of intensity differences of the center-symmetric bins to form a four-dimensional binary vector represented as ) , as shown in Fig.”
A survey of the recent architectures of deep convolutional neural networks (2019, background): “In literature, various exciting works have been reported to understand and/or emulate the human sensory responses such as speech and vision (Hubel and Wiesel 1962, 1968; Ojala et al. 1996; Chapelle 1998; Lowe 1999; Dalal and Triggs 2004; Bay et al. 2008; Heikkilä et al. 2009).”
A Micro-GA Embedded PSO Feature Selection Approach to Intelligent Facial Emotion Recognition (2017, background): “Center-symmetric LBP (CS-LBP) [14] aims to solve the lengthy histogram problem of LBP.”
Extended local binary patterns for texture classification (2012, methodology): “Very recently, Heikkilä et al. [22] exploit circular symmetric LBP (CS-LBP) for local interest region description, and Chen et al. present a WLD descriptor by including orientation information as a robust descriptor [23].”
Texture Feature Extraction Methods: A Survey (2019, methodology): “[94] used an LBP-based method for interest region description.”
Animal recognition in the Mojave Desert: Vision tools for field biologists (2013, methodology): “The underlying features used for classification are generated by extracting points of interest (PoIs) from the images using Difference of Gaussians as proposed in [13] for the well-known SIFT method, and then computing an LBP-like [18] feature descriptor in a window around each detected PoI, somewha”
Uniform Robust Scale-Invariant Feature Matching for Optical Remote Sensing Images (2011, methodology): “Some improvements have been suggested for the standard SIFT, such as PCA-SIFT [30], R-SIFT [27], and also those in [31]–[35].”
Image retrieval based on micro-structure descriptor (2011, background): “The CS-LBP [25] incorporates the advantage of SIFT algorithm and it can overcome this limitation.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Specifically, CS-LBP uses a SIFT-like grid and replaces the gradient information with an LBP-based feature.”
Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval (2012, methodology): “The LBP has been also used for texture segmentation [29], background modeling and detection [30], shape localization [31], interest region description [32], and biomedical image retrieval [33].”
Local binary patterns variants as texture descriptors for medical image analysis (2010, background): “Finally, in [20] center-symmetric LBP are studied in order to obtain a shorter LBP histogram.”
Feature representation for statistical-learning-based object detection: A review (2015, background): “They are distinguished by pixel organization and code computation, as follows: CS-LBP and NR-LBP: Centric-symmetric LBP (CS-LBP) [32] compares centric-symmetric pairs of pixels.”
Learning LBP structure by maximizing the conditional mutual information (2015, background): “…and its variants have been widely used in many applications, e.g. image texture classification [1] [2] [3], dynamic texture (DT) recognition [4] [5] [6] [7], scene recognition [8] [9], facial analysis [10] [11] [12] [13] [14] [15] [16] [17] [18] [19], and others [20] [21] [22] [23] [24] [25] [26].”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, methodology): “or and texture features, denoted by vR i. The detailed description is given in Fig.2. For color features, we consider RGB, HSV, and L*a*b* color spaces. For texture features, we adopt the LBP feature [71] and the responses of the LM ﬁlter bank [72]. As suggested in previous works [15], [21], the reg”