Deep Metric Learning for Scene Text Detection

The strong abilities of deep learning models have been shown in the area of text detection in natural scene images. In this paper, we introduce a new method called deep metric learning for scene text detection. We use the triplet loss [1] to replace the traditional loss function (Softmax) and learn a mapping from image regions to a compact Euclidean space where distances correspond to a measure of text similarity. By combining the CNN model with metric learning, we can make reliable binary classification between text regions and non-text ones. We show that the proposed model achieves competitive results on the ICDAR 2003, ICDAR 2011, and ICDAR 2013 datasets, with the F-measure of 0.74, 0.80, and 0.79.