Measuring the distance between concepts is an important field of study of Natural Language Processing, as it can be used to improve tasks related to the interpretation of those same concepts. In this paper, we explore a distance for WordNet synsets based on visual features, instead of conceptual-semantic and lexical relations. For this purpose, we extract visual-semantic features generated within a deep convolutional neural networks trained to identify ImageNet synsets and use those features to generate a representative of each synset. Finally, based on those representatives, we define a distance measure of synsets, which complements the traditional lexical distances.