The Danger Theory Applied To Vegetal Image Pattern Classification

Artificial Immune Systems (AISs) are a type of intelligent algorithm inspired by the principles and processes of the human immune system. Despite the successful implementation of different AISs, the validity of the paradigm "self non self" have lifted many questions. The Danger theory was an alternative to this paradigm. If we involve its principles, the AIS is being applied as a classifier. However, image classification offers new prospects and challenges to data mining and knowledge extraction. It is an important tool and a descriptive task seeking to identify homogeneous groups of objects based on the values of their attributes. In this paper, we describe our initial framework in which the danger theory was apprehended by the Dendritic cells algorithm is applied to vegetal image classification. The approach classifies pixel in vegetal or soil class. Experimental results are very encouraging and show the feasibility and effectiveness of the proposed approach.