Estimating the Optimal Training Set Size of Keyword Spotting for Historical Handwritten Document Transcription.
Giuseppe De GregorioAngelo MarcelliPublished in: IGS (2023)
Keyphrases
- keyword spotting
- handwritten documents
- handwriting recognition
- training set size
- speech recognition
- character recognition
- hidden markov models
- training set
- document images
- text retrieval
- digital libraries
- learning curves
- document image analysis
- machine learning
- word recognition
- printed documents
- poor quality
- image collections