Deep Tattoo Recognition

Abstract

Tattoo is a soft biometric that indicates discriminative characteristics of a person such as beliefs and personalities. Automatic detection and recognition of tattoo images is a difficult problem. We present deep convolutional neural network-based methods for automatic matching of tattoo images based on the AlexNet and Siamese networks. Furthermore, we show that rather than using a simple contrastive loss function, triplet loss function can significantly improve the performance of a tattoo matching system. Extensive experiments on a recently introduced Tatt-C dataset show that our method is able to capture the meaningful structure of tattoos and performs significantly better than many competitive tattoo recognition algorithms.