常用纹理数据库

常用纹理数据库

 

参考网站：

https://www.robots.ox.ac.uk/~vgg/data/dtd/

 

 

1. Describable Textures Dataset (DTD)

https://www.robots.ox.ac.uk/~vgg/data/dtd/

https://www.robots.ox.ac.uk/~vgg/data/dtd/eval.html

 

The Describable Textures Dataset (DTD) is an evolving collection of textural images in the wild, annotated with a series of human-centric attributes, inspired by the perceptual properties of textures. This data is made available to the computer vision community for research purposes.

This research is based on work done at the 2012 CLSP Summer Workshop

The development of the describable textures dataset started in June and July 2012 at the Johns Hopkins Centre for Language and Speech Processing (CLSP) Summer Workshop. The authors are most grateful to Prof. Sanjeev Khudanpur and Prof. Greg Hager.

CLSP Summer Workshop at JHU

CLSP organizes and hosts a few international teams for an intensive 6-week research workshop on speech and language engineering

 

 

 

 

 

Vision Texture

http://vismod.media.mit.edu/vismod/imagery/VisionTexture/vistex.html

Welcome to the Vision Texture homepage. The VisTex database is a collection of texture images. The database was created with the intention of providing a large set of high quality textures for computer vision applications. In particular, the set was made as an alternative to the Brodatz texture library, which is not freely available for research use. 

Unlike other texture collections, the images in VisTex do not conform to rigid frontal plane perspectives and studio lighting conditions. The goal of VisTex is to provide texture images that are representative of real world conditions. While VisTex can serve as a replacement for traditional texture collections, it includes examples of many non-traditional textures. The database has 4 main components:

Reference Textures: 100+ homogeneous textures in frontal and oblique perspectives.
  

Texture Scenes: Images with multiple textures. ("real-world") scenes.
  

Video Textures: Sequences of temporal textures. (UNDER CONSTRUCTION)

Video Orbits: Images within a common projective group.(UNDER CONSTRUCTION)
 

Outex

http://www.outex.oulu.fi/

CVOnline

http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm#texture

 

CUReT: Columbia-Utrecht Reflectance and Texture Database

http://www1.cs.columbia.edu/CAVE/software/curet/index.php

DynTex

A comprehensive database of Dynamic Textures.

http://dyntex.univ-lr.fr/database.html

 

The DynTex database is a diverse collection of high-quality dynamic texture videos. Currently we are finalizing the structure of the database. In the meantime, more than 650 sequences are available for downloading. For an overview of the total contents of the DynTex database, we provide a page of key frames of all sequences currently available. To be able to play the corresponding sample video files the password obtained at registration is required.

Central to the database is the so-called golden set of high-quality dynamic texture sequences that satisfy all criteria of the acquisition protocol. This set will be further structured by its underlying physical processes, e.g turbulent motion, waving motion, discrete units etc. Additionally, they will be classified by their shot type, i.e. either as closeup (shot consisting entirely of the dynamic texture, no segmentation required), or as context (the dynamic texture is shown in its context). Next to the golden set we will offer various other sets. Examples are a collection of dynamic texture sequences recorded with a moving camera, and a collection with several dynamic textures per sequence.

 

The Prague Texture Segmentation Datagenerator and Benchmark

http://mosaic.utia.cas.cz/index.php?act=bench_form

This server allows users:

• to obtain customized experimental texture mosaics and their corresponding ground-truths (U),
• to obtain the benchmark texture mosaic set with their corresponding ground-truths,
• to evaluate your working segmenters and compare them with the state of art algorithms (U),
• to include your algorithm's details (reference, abstract, benchmark results) into the benchmark database (U),
• to check single mosaics' evaluation details (the criteria values and the resulting thematic maps),
• to rank segmentation algorithms according to the most common benchmark criteria,
• to assess noise robustness with respect to noise,
• to obtain LaTeX coded resulting criteria tables or export data in MATLAB format (U),
• to select a user-defined subset of the criteria (U).

 

Dataset

• Computer generated texture mosaics and benchmarks are composed from the following image types:
  • monospectral textures,
  • multispectral textures,
  • BTF (bidirectional texture function) textures [UTIA BTF, BTF Bonn],
  • ALI hyperspectral satellite images [Earth Observing 1],
  • very-high-resolution GeoEye RGB images,
  • dynamic textures [DynTex],
  • rotation invariant texture set,
  • scale invariant texture set,
  • illumination invariant texture set.
• All generated texture mosaics can be corrupted with additive Gaussian noise, Poisson or salt&pepper noise.
• The corresponding trainee sets (hold out) are supplied in the classification (supervised) mode.

 

Benchmark evaluation

• Submitted results are stored in the server database and used for the algorithm ranking based on a selected criterion from the following criteria set:
  • average RANK (over displayed criteria),
  • region-based  (including the sensitivity graphs):
    • CS - correct segmentation,
    • OS - over-segmentation,
    • US - under-segmentation,
    • ME - missed error,
    • NE - noise error,
  • pixel-wise:
    • O - omission error,
    • C - commission error,
    • CA - class accuracy,
    • CO - recall = correct assignment,
    • CC - precision = object accuracy,
    • I. - type I error,
    • II. - type II error,
    • EA - mean class accuracy estimate,
    • MS - mapping score,
    • RM - root mean square proportion estimation error,
    • CI - comparison index,
    • F-measure (weighted harmonic mean of precision and recall) graph,
  • consistency measures:
    • GCE - global consistency error,
    • LCE - local consistency error,
  • clustering:
    • dM - Mirkin metric,
    • dD - Van Dongen metric,
    • dVI - variation of information.

Texture Database

http://www-cvr.ai.uiuc.edu/ponce_grp/data/#texture

Kylberg Texture Dataset v. 1.0

(Uppsala texture dataset of surfaces and materials)

http://www.cb.uu.se/~gustaf/texture/

转载于:https://www.cnblogs.com/yizhichun/p/6339908.html