Wood classification based on edge detections and texture features selection

One of the properties of wood is a mechanical property, includes: hardness, strength, cleavage resistance, etc. Among these properties there that can be measured or estimated by visual observation on cross-sectional areas of wood, which is based on inter-fiber density, fiber size, and lines that build the annual rings. In this paper, we proposed a new wood quality classification method based on edge detections. Edge detection is applied to the wood test images with the aim to improving the characteristics of wood fibers so as to make it easier to distinguish their quality. Gray Level Cooccurrence Matrix (GLCM) used to obtain wood texture features, while the wood quality classification done by Naïve Bayes classifier. Found in our experimental results that the first-order edge detection is likely to provide a good accuracy rate and precision. The second order edge detection is highly dependent on the choice of parameters and tends to give worse classification results, as filtering the original wood image, thus blurring characteristics related to wood density. Selection of features obtained from co-occurrence matrix is also quite affected the classification results.