کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
535818 | 870389 | 2012 | 10 صفحه PDF | دانلود رایگان |

The classification of large number of object categories is a challenging trend in the pattern recognition field. In literature, this is often addressed using an ensemble of classifiers. In this scope, the Error-correcting output codes framework has demonstrated to be a powerful tool for combining classifiers. However, most state-of-the-art ECOC approaches use a linear or exponential number of classifiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classifiers. Evolutionary computation is used for tuning the parameters of the classifiers and looking for the best minimal ECOC code configuration. The results over several public UCI datasets and different multi-class computer vision problems show that the proposed methodology obtains comparable (even better) results than state-of-the-art ECOC methodologies with far less number of dichotomizers.
► We define a minimal ECOC design in terms of the number of dichotomizers.
► Genetic algorithms are use to look for the minimal ECOC configuration with high generalization capability.
► Genetic algorithms are used to tune the base classifier parameters.
► Results on different computer vision and machine learning data sets show performance improvements using far less number of dichotomizers.
Journal: Pattern Recognition Letters - Volume 33, Issue 6, 15 April 2012, Pages 693–702