Illumination-Invariant Morphological Texture Classification

Hanbury, Allan; Kandaswamy, Umasankar; Adjeroh, Donald A.

doi:10.1007/1-4020-3443-1_34

Cited by 46 publications

(39 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Structural methods (i) consider the texture as a set of textural elements organized according to some spatial rule. Usually, mathematical morphology operations are successively applied on the image in order to describe the evolution of textural elements [2,32,52] . Recently, some methods proposed the use of keypoint detectors and descriptors to characterize the texture elements [39,64] .…”

Section: Related Workmentioning

confidence: 99%

Texture recognition based on diffusion in networks

Gonçalves

Silva

Costa

et al. 2016

Information Sciences

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Texture recognition based on diffusion in networks

Gonçalves

Silva

Costa

et al. 2016

Information Sciences

View full text Add to dashboard Cite

“…Concerning radiometric invariant analysis of texture, the benefit of using contrast invariant morphological operators to recognize texture under various illumination conditions has not yet been demonstrated. Hanbury et al (2005) have developed an illumination invariant morphological scheme to index textures, but they achieve invariance thanks to histogram modification techniques and not by using the contrast invariant properties of morphological analysis.…”

Section: Previous and Related Workmentioning

confidence: 99%

Shape-based Invariant Texture Indexing

2009

View full text Add to dashboard Cite

This paper introduces a new texture analysis scheme, which is invariant to local geometric and radiometric changes. The proposed methodology relies on the topographic map of images, obtained from the connected components of level sets. This morphological tool, providing a multi-scale and contrast-invariant representation of images, is shown to be well suited to texture analysis. We first make use of invariant moments to extract geometrical information from the topographic map. This yields features that are invariant to local similarities or local affine transformations. These features are invariant to any local contrast change. We then relax this invariance by computing additional features that are invariant to local affine contrast changes and investigate the resulting analysis scheme by performing classification and retrieval experiments on three texture databases. The obtained experimental results outperform the current state of the art in locally invariant texture analysis.

show abstract

“…Although all filters are important, classification using individual filters does not provide satisfactory results. For instance, the best result (73.90%) on the UIUC dataset using individual filter was obtained by the edge filter at scale (2,6) while all filters (MR8 filter bank) provided 94% (see Table 1). …”

Section: Parameter Evaluationmentioning

confidence: 99%

“…Structural methods are based on primitives and hierarchical arrangements of these primitives. In this context, mathematical morphology becomes an important tool for texture description as proposed in [1,2]. Recently, feature detectors and descriptors have been proposed to find and describe texture primitives efficiently [3].…”

Section: Introductionmentioning

confidence: 99%