Texture Classification from Random Features

By Li Liu, Paul W. Fieguth. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

321 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/82850b725a3d7d95fc75a3bce228591d92ed5c20

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. Luc Van Gool
3. Ming-Hsuan Yang
4. Liangpei Zhang
5. Dacheng Tao
6. Junwei Han
7. Lei Zhang
8. Yu Qiao

Citations in the corpus

• From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, methodology): “For approaches requiring a learned codebook, kmeans clustering [110, 114, 125, 237, 263] and Gaussian Mixture Models (GMM) [34, 36, 107, 91, 179, 209] are the most popular and successful methods.”
• Median Robust Extended Local Binary Pattern for Texture Classification (2016, methodology): “outperformed by dense approaches [41]–[43], upon which we”
• Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern (2014, background): “PRICoLBPg also exceeds the performance of several bag-of-words methods, [43], [44], [5], [45], and [46].”
• Local binary features for texture classification: Taxonomy and experimental study (2017, methodology): “For CUReT, we use the same subset of images as in [18,122].”
• Remote Sensing Image Classification: No Features, No Clustering (2015, methodology): “projection (SRP) of five local features [30], [31] was developed by the same authors, who claimed to achieve significant improvements compared with the the method of [29].”
• Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery (2016, methodology): “The noise-like filters shown in (10), called random projection (RP) filters [49], are generated from an independent zero-mean, unit-variance normal distribution.”
• Unsupervised Feature Learning Via Spectral Clustering of Multidimensional Patches for Remotely Sensed Scene Classification (2015, background): “Random projection (RP) [53] is a simple yet effective dimensionality reduction method.”
• Real-Time Compressive Tracking (2012, background): “A typical measurement matrix satisfying the restricted isometry property is the random Gaussian matrix R ∈ Rn×m where rij ∼ N(0, 1), as used in numerous works recently [14, 9, 18].”