Person Re-identification with End-to-End Scene Text Recognition

Person re-identification (Re-ID) has become increasingly popular in vision community. Many previous works rely on either fea-ture representation learning and/or metric learning. Different from clas-sical methods, we find that some text in images could be considered as a key cue for differentiating persons under some circumstances (e.g., racing bib number of marathon participants). Based on this observation, we propose to simplify the person Re-ID problem into an end-to-end text recognition problem. Thanks to many powerful state-of-the-art text recognition systems, we can largely improve the efficiency and accuracy of person re-identification in such circumstances. Moreover, we collect a dataset consisting of 9706 marathon images and propose an appropri-ate measurement to benchmark person identification. Our work provides a promising perspective to person Re-ID and end-to-end text recogni-tion fields, showing also high potentials for video surveillance and image retrieval.