Texture Classification Based on Empirical Wavelet Transform Using LBP Features

Ramesh P., V. Mathivanan

Abstract


Automatic inspection systems become more importance for industries with high productive plans especially in texture industry. A novel approach to Local Binary Pattern (LBP) feature for texture classification is proposed in this system. At the first, the proposed Empirical Wavelet Transform (EWT) based texture classification is tested on gray scale and color images by using Brodatz texture images. The gray scale and color image is decomposed by EWT at 2 and 3 level of decomposition. LBP features are calculated for each empirical transformed image. Extracted features are given as input to the classification stage. K-NN classifier is used for classification stage. The result of the proposed system gives satisfactory classification accuracy of over 98% for all types of images.


Keywords


Texture classification, EWT, LBP, K-NN.



DOI: http://dx.doi.org/10.11591/ijeecs.v8.i2.pp%25p

Refbacks

  • There are currently no refbacks.


Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
ISSN: 2502-4760

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

shopify stats IJEECS visitor statistics