End-to-End Text Recognition with Hybrid HMM Maxout Models
This work addresses the challenging problem of scene text recognition for computer vision applications, representing an incremental improvement by integrating existing methods into a new system.
The authors tackled the problem of detecting and recognizing text in natural scenes by proposing an end-to-end system that combines character and word recognition solutions using hybrid HMM Maxout models, achieving state-of-the-art results on ICDAR 2003 and SVT benchmark datasets.
The problem of detecting and recognizing text in natural scenes has proved to be more challenging than its counterpart in documents, with most of the previous work focusing on a single part of the problem. In this work, we propose new solutions to the character and word recognition problems and then show how to combine these solutions in an end-to-end text-recognition system. We do so by leveraging the recently introduced Maxout networks along with hybrid HMM models that have proven useful for voice recognition. Using these elements, we build a tunable and highly accurate recognition system that beats state-of-the-art results on all the sub-problems for both the ICDAR 2003 and SVT benchmark datasets.