Affordable Access

Access to the full text

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

Authors
  • Liu, Li1, 2
  • Chen, Jie2
  • Fieguth, Paul3
  • Zhao, Guoying2
  • Chellappa, Rama4
  • Pietikäinen, Matti2
  • 1 National University of Defense Technology, Changsha, China , Changsha (China)
  • 2 University of Oulu, Oulu, Finland , Oulu (Finland)
  • 3 University of Waterloo, Waterloo, Canada , Waterloo (Canada)
  • 4 University of Maryland, College Park, USA , College Park (United States)
Type
Published Article
Journal
International Journal of Computer Vision
Publisher
Springer-Verlag
Publication Date
Nov 08, 2018
Volume
127
Issue
1
Pages
74–109
Identifiers
DOI: 10.1007/s11263-018-1125-z
Source
Springer Nature
Keywords
License
Green

Abstract

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention over several decades. Since 2000, texture representations based on Bag of Words and on Convolutional Neural Networks have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 250 major publications are cited in this survey covering different aspects of the research, including benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research.

Report this publication

Statistics

Seen <100 times