Skip to content. Skip to navigation
McGill Home SOCS Home
Personal tools
You are here: Home Announcements and Events Seminars profile

Seminars
Fall 2014 Schedule
Winter 2015 Schedule
Archive


         
     
 
2013/10/18, *MC320* (not our usual location MC103), 12 - 12:30

End-to-End Text Recognition with Hybrid HMM Maxout Models
Ouais Alsharif , McGill, SOCS, Reasoning and Learning Lab

Abstract:

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.