Texture Analysis Using Classification Rules

Because of its accurate and robust performance, association rule-based approach is recently used for image classification. A new textural feature based on classification rules is proposed in this paper. We give a simple texture representation, which is appropriate to allows application of classification rules algorithms. The representation has several properties like grey scale invariance and invariance to rotation. Classification rules that are extracted from association rules could capture structural and statistical information and are very convenient to identify the structures that occur most frequently and have the most discriminative power. Experiment results show that this representation gives good results in texture classification