2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLR-APPL-IP-7.9
Paper Title DEFORMATION-INVARIANT NETWORKS FOR HANDWRITTEN TEXT RECOGNITION
Authors George Retsinas, National Technical University of Athens, Greece; Giorgos Sfikas, Christophoros Nikou, University of Ioannina, Greece; Petros Maragos, National Technical University of Athens, Greece
SessionMLR-APPL-IP-7: Machine learning for image processing 7
LocationArea E
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Applications of Machine Learning: Machine learning for image processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Image deformations under simple geometric restrictions are crucial for Handwriting Text Recognition (HTR), since different writing styles can be viewed as simple geometrical deformations of the same textual elements. In this respect, the usefulness of including deformation invariance to an HTR system is indisputable. We explore different existing strategies for ensuring deformation invariance, including spatial transformers and deformable convolutions, under the context of text recognition, as well as introduce a new deformation-based algorithm, inspired by adversarial learning, which aims to reduce character output uncertainty during evaluation time. The resulting HTR system is shown to achieve state-of-the-art performance on the IAM and RIMES datasets.