Recognition of porosity in wood microscopic anatomical images

Authors:
Shen Pan;Mineichi Kudo
Affiliations:
Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan and Department of Information Management and Information Systems, Hefei University of Technology, Hefei, ...;Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan
Venue:
ICDM'11 Proceedings of the 11th international conference on Advances in data mining: applications and theoretical aspects
Year:
2011

Citing 6
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
A vision-based method for weeds identification through the Bayesian decision theory

Pattern Recognition
Original paper: A vision based row detection system for sugar beet

Computers and Electronics in Agriculture
Mean-shift-based color segmentation of images containing green vegetation

Computers and Electronics in Agriculture
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Original paper: Segmentation of pores in wood microscopic images based on mathematical morphology with a variable structuring element

Computers and Electronics in Agriculture

Quantified Score

Hi-index	0.00

Visualization

Abstract

The size and configuration of pores are key features for wood identification. In this paper, these features are extracted and then used for construction of a decision tree to recognize three different kinds of pore distributions in wood microscopic images. The contribution of this paper lies in three aspects. Firstly, two different sets of features about pores were proposed and extracted; Secondly, two decision trees were built with those two sets by C4.5 algorithm; Finally, the acceptable recognition results of up to 75.6% were obtained and the possibility to improve was discussed.