Textons, the elements of texture perception, and their interactions

By B. Julesz. 1981

Subfields: Neuroscience, Cognitive Science & Psychology

How researchers see this paper

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

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

Describing Textures in the Wild (2013, background): “The study of perceptual attributes of textures has a long history starting from pre-attentive aspects and grouping [16], to coarse high-level attributes [1, 2, 33], to some recent work aimed at discovering such attributes by automatically mining descriptions of images from the Internet [3, 12].”
Multi-class texture analysis in colorectal cancer histology (2016, methodology): “Lower-order statistics can be used to describe texture 23,24 .”
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images (2015, methodology): “Julesz’ ideas were framed probabilistically by Zhu and Mumford [55] and their generation-by-sampling framework was later approximated by Portilla and Simoncelli [35] as a pre-image problem which can be seen as a special case of the inversion method discussed here.”
Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis (2017, background): “The concept was first studied by Julesz [9], who suggested that the visual system discriminates between different textures based on the average responses of certain image filters.”
Texture Analysis (1993, background): “His later counter-examples to this conjecture were the result of a careful construction of texture pairs that have identical second-order statistics (see Figure 4(b)) [14,15,16].”
Recognition-by-components: a theory of human image understanding. (1987, background): “Instead those regions are represented through the statistical processing that characterizes their texture (for example, Beck, Prazdny, & Rosenfeld, 1983;Julesz, 1981), although we retain a capacity to zoom down and attend to the volumetric nature of the individual elements.”
Contour and Texture Analysis for Image Segmentation (2001, background): “Julesz introduced the term texton, analogous to a phoneme in speech recognition, nearly 20 years ago (Julesz, 1981) as the putative units of preattentive human texture perception.”
Reduced Generalization in Autism: An Alternative to Weak Central Coherence (2001, background): “Making elements larger and more sparse effectively increases the differentiation between them, so that they are perceived as forms rather than simply as texture (Julesz, 1981).”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, background): “The term texton was coined by (Julesz 1981) for describing human textural perception, and is somewhat analogous to phonemes used in speech recognition.”
Classifying materials in the real world (2010, background): “While the notion of textons is familiar from the work of Julesz and Bergen [18], it was only recently defined for greyscale images as a cluster center in a feature space formed by the output of a filter bank.”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “Aiming at seeking essential ingredients in terms of features and statistics in human texture perception, in the early 1980s Julesz [93, 94] proposed the texton theory to explain texture preattentive discrimination, which states that textons (composed of local conspicuous features such as corners,…”