Classifier ensemble based-on bi-coded chromosome genetic algorithm for automatic image annotation

Using image classification approach for automatic image annotation is one promising method. In order to improve image annotation accuracy, recent researchers propose to use AdaBoost algorithm for the ensemble of classifiers. But in these researches, only fewer features are used. We construct multi-class classifiers for all the image low-level feature of multimedia content description interface and their potential combinations respectively, k-nearest neighbor classifier is used as the base classifier and dasiaone vs. onepsila scheme is chosen to build multi-class classifiers. A bi-coded chromosome genetic algorithm is used to select the optimal classifier subset as weak classifiers and corresponding weights, which are used for the combination of an ensemble classifier by weighted majority voting scheme. The results of experiment over 2000 classified Corel images show that the approach selects 4 of 325 multi-class classifiers as weak classifiers as well as corresponding optimized weights to generate an ensemble classifier. The ensemble classifier created by the bi-coded chromosome genetic algorithm has higher accuracy than that by AdaBoost algorithm.