A Preliminary Study of Wood Species Classifacation System Based on Wood Knot Texture Using K-Nearest Neighbour With Optimized Features From Binary Magnetic Optimization Algorithm Selection
The Classification of wood type can be done by studying the texture of the wood knot. This paper proposed a classification of wood species using k-Nearest Neighbour with optimized features. The images of wood knots are taken from Universiti Teknologi Malaysia’s CAIRO Wood Database. The database cons...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/10656/1/2013_Conf._3July_SETNC2013_%282%29.pdf http://eprints.utem.edu.my/id/eprint/10656/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The Classification of wood type can be done by studying the texture of the wood knot. This paper proposed a classification of wood species using k-Nearest Neighbour with optimized features. The images of wood knots are taken from Universiti Teknologi Malaysia’s CAIRO Wood Database. The database consists of 25 species of tropical woods. The features of the wood knot images are extracted using Gray Level Co-Occurrence Matrix. Binary Magnetic Optimization Algorithm is use to optimize the feature selection process. Binary Magnetic Optimization Alogirthm also use to optimize parameters of k-Nearest Neighbour and Gray Level Co-Occurrence Matrix. The result indicates that the proposed approach can perform as good as previous literature with fewer features used as input for the classifier. |
|---|