Can fuzzy logic improve the cork quality classification? A comparative study

This paper presents the results obtained after the performance of a comparative study on classification algorithms. Four classification systems were studied and also a fifth classification system based on fuzzy logic to give a solution to a problem existing in the cork industry: cork stopper/disk classification according to their quality. Cork is a natural and heterogeneous material; therefore, its automatic classification (seven quality classes exist) is very difficult. The solution proposed in this paper shows the stages made in our study: quality discriminatory features extraction and classifiers analysis. In conclusion, our experiments show that the best results are obtained by a system that works with the features: cork area occupied by defects (after thresholding), size of the biggest defect within the cork area (morphological operations), and the Laws TEMs E5L5TR, E5E5TR, S5S5TR, W5W5TR, all working on a Neuro-Fuzzy classifier. The obtained results have highly improved other results obtained in similar studies.