Robustness of Rotation Invariant Descriptors for Texture Classification

Vieira, Raissa Tavares; Negri, Tamiris Trevisan; Gonzaga, Adilson

doi:10.1007/978-3-319-50835-1_25

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several approaches based on local mapped patterns have been proposed as feature descriptor [43]- [45]. The local mapped pattern approach has also been extended for circular neighborhoods: the method, called sampled local mapped pattern [46], considers the neighborhood of a center pixel as a set of values within a circular symmetry radius. In 2016, Vieira et al [46] proposed a new texture descriptor for classification of rotated textures, the so-called sampled local mapped pattern magnitude, based on the local mapped patterns approach.…”

Section: E Local Mapped Patterns-based Approaches 1) Conceptmentioning

confidence: 99%

Texture Feature Extraction Methods: A Survey

2019

View full text Add to dashboard Cite

Texture analysis is used in a very broad range of fields and applications, from texture classification (e.g., for remote sensing) to segmentation (e.g., in biomedical imaging), passing through image synthesis or pattern recognition (e.g., for image inpainting). For each of these image processing procedures, first, it is necessary to extract-from raw images-meaningful features that describe the texture properties. Various feature extraction methods have been proposed in the last decades. Each of them has its advantages and limitations: performances of some of them are not modified by translation, rotation, affine, and perspective transform; others have a low computational complexity; others, again, are easy to implement; and so on. This paper provides a comprehensive survey of the texture feature extraction methods. The latter are categorized into seven classes: statistical approaches, structural approaches, transform-based approaches, model-based approaches, graph-based approaches, learning-based approaches, and entropybased approaches. For each method in these seven classes, we present the concept, the advantages, and the drawbacks and give examples of application. This survey allows us to identify two classes of methods that, particularly, deserve attention in the future, as their performances seem interesting, but their thorough study is not performed yet.

show abstract

Section: E Local Mapped Patterns-based Approaches 1) Conceptmentioning

confidence: 99%