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

TL;DR

This survey reviews twenty years of texture representation methods in computer vision, highlighting the evolution from Bag of Words to CNNs, covering key advances, datasets, and future challenges.

Contribution

It provides a comprehensive overview of over 200 publications on texture representation, comparing BoW, CNN, and attribute-based methods, and discusses open research challenges.

Findings

CNN-based methods outperform traditional BoW approaches.

Benchmark datasets have enabled consistent evaluation of methods.

Open challenges include robustness and real-world applicability.

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. Since 2000, texture representations based on Bag of Words (BoW) and on Convolutional Neural Networks (CNNs) 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 200 major publications are cited in this survey covering different aspects of the research, which includes (i) problem description; (ii) recent advances in the broad categories of BoW-based, CNN-based and attribute-based methods; and (iii) evaluation issues, specifically 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.