Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models
By Salvador España Boquera, María José Castro Bleda, Jorge Gorbe-Moya, Francisco Zamora-Martínez. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
342 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/98b098fb3fa3f270f8dbec444612e2e2acc9607d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Hermann Ney
- Adnan Ul-Hasan
- Josep Lladós
- Alicia Fornés
- Faisal Shafait
- Volkmar Frinken
- Jean-Marc Ogier
- Thomas Breuel
In Media Technology
- Josep Lladós
- Hermann Ney
- Alicia Fornés
- Faisal Shafait
- Volkmar Frinken
- Jean-Marc Ogier
- Thomas Breuel
- Simon Wiesler
Citations in the corpus
- High-Performance OCR for Printed English and Fraktur Using LSTM Networks (2013, methodology): “Segmentation-free techniques like Hidden Markov Models (HMMs) applied to OCR [5], [6] avoid many of the difficulties of segmentation-based OCR systems, but still require careful choices of model structures, and face similar issues in heuristic modifications of their cost functions to achieve…”
- Dropout Improves Recurrent Neural Networks for Handwriting Recognition (2013, neutral): “[31] 19.”
- A Convergence Analysis of Log-Linear Training (2011, methodology): “[6], who use several specialized neural networks for preprocessing.”
- Bidirectional Language Model for Handwriting Recognition (2012, background): “Promising approaches for handwriting recognition are segmentation-free and learning-based, such as hidden Markov models (HMM) [2, 13], neural networks (NN) [6], or combinations thereof [3].”