Textural Features for Image Classification

By Robert Martin Haralick, K. Shanmugam, I. Dinstein. 1973

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Propagation kernels: efficient graph kernels from propagated information (2014, methodology): “We compare pk to the simple baseline labels using label counts only and to a powerful second-order statistical feature based on the graylevel co-occurrence matrix (Haralick et al. 1973) comparing intensities (glcm-gray) resp.”
Large‐scale image‐based screening and profiling of cellular phenotypes (2017, background): “…nuclear factor kappa B (NF-j B)], textural properties of the marker staining patterns [e.g., mean entropy of the gray-level co-occurrence matrix (90) based on a DNA marker], and spatial correlations between two different markers (e.g., correlation coefficient between the markers for DNA and…”
Imaging Intratumor Heterogeneity: Role in Therapy Response, Resistance, and Clinical Outcome (2014, methodology): “Many studies use the Haralick method (49), where a co-occurrence matrix element denoted Pd, u (i, j) measures the probability of starting from any image voxel with designated value i, moving d voxels along the image in direction u, and then arriving at another voxel with value j.”
Bag-of-visual-words and spatial extensions for land-use classification (2010, unknown): “We take further motivation from early work on pixellevel characterization of land-use classes in overhead imagery from Haralick et al.’s seminal work [ 8 ] on gray level co-occurrence matrices (GLCM) and the set of 14 derived textural features which represents some of the earliest work on image text”
Rotation invariant texture classification using LBP variance (LBPV) with global matching (2010, methodology): “The representative methods include the co-occurrence matrix method [5] and filtering based approaches [6], such as Gabor filtering [7,8], wavelet transform [9,10] and wavelet frames [11].”
Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network (2018, background): “The 2D level decomposition of an image displays an approximation with detailed three images that represents low and high-level frequency contents in an image, respectively [15].”