Confidence modeling for verification post-processing for handwriting recognition
Tóm tắt
We apply confidence-scoring techniques to verify the output of a handwriting recognizer. We evaluate a variety of scoring functions, including likelihood ratios and estimated posterior probabilities of correctness, in a postprocessing mode to generate confidence scores at the character or word level. Using the post-processor in conjunction with an HMM-based on-line handwriting recognizer for large-vocabulary word recognition, receiver-operating-characteristic (ROC) curves reveal that our post-processor is able to reject correctly 90% of recognizer errors while only falsely rejecting 33% of correctly-recognized words. For isolated-digit recognition, we achieve a correct rejection rate of 90% while keeping false rejection down to 13%.
Từ khóa
#Handwriting recognition #Character recognition #Character generation #Hidden Markov models #Error correction #Error analysis #Costs #Automation #Humans #VocabularyTài liệu tham khảo
koo, 2001, Speech recognition and utterance verification based on a generalized confidence score, IEEE Transactions on Speech and Audio Processing, 9, 821, 10.1109/89.966085
10.1109/ICDAR.1997.620677
10.1109/ICASSP.1997.596078
10.1109/ICASSP.1992.226112
perrone, 1993, Improving regression estimation Averaging methods for variance reduction with extensions to general convex measure optimization
perrone, 1993, When networks disagree: Ensemble method for neural networks, Artificial Neural Networks for Speech and Vision, 10
beigi, 1995, Real-time on-line unconstrained handwriting recognition using statistical methods, Proceedings of ICASSP 1995 IEEE International Conference on Acoustics Speech and Signal Processing, 4, 2619, 10.1109/ICASSP.1995.480098
10.1109/ICASSP.1996.541144
10.1109/ICASSP.1996.550777
stolcke, 1997, Explicit word error minimization in n-best list rescoring, Proceedings of Eurospeech '97, 1, 163
10.1109/29.103088