Texture segmentation based on fuzzy grammar for cork parquet quality control

Abstract

This paper presents an approach for image texture segmentation based on the wavelets transform and on a fuzzy grammar inference system. It was developed for the Portuguese cork industry, specifically for the quality control in the cork parquet sector. The main purpose was to deal with major quality issues related with texture features. The segmentation procedure reveals a good performance indicated by high classification rates. This approach was integrated in a vision system leading to an industrial prototype that has already been tested, revealing good perspectives of full industrialization.