COMPARATIVE STUDY OF SECOND-ORDER GRAY LEVEL TEXTURE STATISTICS TO EVALUATE CORK QUALITY

摘要

In this paper we study the use of second-order gray-level statistical texture analysis to solve a classification problem existing in the cork industry: the cork stopper/disk classification according to their quality using a visual inspection system. Cork is a natural and heterogeneous material, therefore, its automatic classification (usually, seven different quality classes exist) is very difficult. We think the quality of a cork stopper/disk could be based on the cork texture in that stopper/disk. This cork texture can be studied using statistical texture analysis. In this paper we attempt to evaluate the performance of a total of 9 different textural features in order to conclude which of them is the most appropriate for the cork industry, and therefore, obtains the best cork classification results. In conclusion, our experiments show that the contrast, entropy and energy are the features which obtain the best results in this application field.