Statistic metrics for evaluation of binary classifiers without ground-truth

In this paper, we present a number of statistically grounded performance evaluation metrics capable of evaluating binary classifiers in absence of annotated Ground Truth. These metrics are generic and can be applied to any type of classifier but are experimentally validated on binarization algorithms. We applied the statistically grounded metrics and compared them with metrics based on annotated data. Our approach has statistically significant better than random results in classifiers selection, and our evaluation metrics requiring no Ground Truth have high correlation with traditional metrics. We conducted experiments on the images from the DIBCO binarization contests between 2009 and 2013.