Ritwik Kumar, Arunava Banerjee, et al.
IEEE TPAMI
Confidence scoring can assist in determining how to use imperfect handwriting-recognition output. We explore a confidence-scoring framework for post-processing recognition for two purposes: Deciding when to reject the recognizer's output, and detecting when to change recognition parameters e.g., to relax a word-set constraint. Varied confidence scores, including likelihood ratios and posterior probabilities, are applied to an Hidden-Markov-Model (HMM) based on-line recognizer. Receiver-operating characteristic curves reveal that we successfully reject 90% of word recognition errors while rejecting only 33% of correctly-recognized words. For isolated digit recognition, we achieve 90% correct rejection while limiting false rejection to 13%. © Springer-Verlag 2005.
Ritwik Kumar, Arunava Banerjee, et al.
IEEE TPAMI
Benedikt Blumenstiel, Johannes Jakubik, et al.
NeurIPS 2023
Fearghal O'Donncha, Albert Akhriev, et al.
Big Data 2021
Arnon Amir, M. Lindenbaum
Computer Vision and Image Understanding