Title :
Classification of KNOT defect types
Author :
Cetiner, Sbrahim ; Var, A. Ali ; Cetiner, H.
Author_Institution :
Keciborlu M.Y.O. Elektron. Teknolojisi, Suleyman Demirel Univ., Isparta, Turkey
Abstract :
In this study, the experimental studies were carried out on a database containing the types of wood knot. After preprocessing on the images in the database, specific features to knot were obtained using wavelet moments feature extraction algorithm. Type description is carried out with KNN classification algorithm by selecting most distinguishing the approximation coefficients on these features. In conclusion, knot images could be classified with the success rate of 98%.
Keywords :
feature extraction; image classification; wavelet transforms; wood; KNN classification algorithm; approximation coefficients; image preprocessing; knot defect types classification; knot image classification; wavelet moments feature extraction algorithm; wood knot; Approximation methods; Bagging; Classification algorithms; Conferences; Databases; Feature extraction; Signal processing; Approximation Coefficients; KNN Classification; Knot types; Wavelet Moment;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2014 22nd
Conference_Location :
Trabzon
DOI :
10.1109/SIU.2014.6830422
