Study on Image Recognition and Classification of Wood Skin Defects Based on BOW Model

DOI

10.2991/meees-18.2018.16How to use a DOI?

Keywords

wood skin defect, image recognition, feature extraction, BOW model, support vector machine.

Abstract

To solve the problem of wood skin recognition and classification in wood processing industry, a method based on BOW model for image recognition of wood skin defects is proposed. First, we extract the HOG feature of wood skin defect image, and then build the BOW model to describe the wood skin defect image. Finally, we use different kernel functions combined with support vector machine (SVM) to identify the types of wood skin defects. The experimental results show that the average recognition rate of the proposed method is 85.4% for wood skin defect image recognition and classification, indicating that the BOW model is effective and feasible for wood skin defect image recognition and classification.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fan Yang
AU  - Yuzeng Wang
PY  - 2018/05
DA  - 2018/05
TI  - Study on Image Recognition and Classification of Wood Skin Defects Based on BOW Model
BT  - Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering & Science (MEEES 2018)
PB  - Atlantis Press
SP  - 80
EP  - 84
SN  - 2352-5401
UR  - https://doi.org/10.2991/meees-18.2018.16
DO  - 10.2991/meees-18.2018.16
ID  - Yang2018/05
ER  -