Recognition of Japanese historical text lines by an attention-based encoder-decoder and text line generation.
Anh Duc LeDaichi MochihashiKatsuya MasudaHideki MimaNam Tuan LyPublished in: HIP@ICDAR (2019)
Keyphrases
- text lines
- document images
- unconstrained handwritten
- handwriting recognition
- text line segmentation
- connected components
- hough transform
- optical character recognition
- text detection
- structural features
- complex background
- printed documents
- handwritten documents
- motion estimation
- document analysis
- document image analysis
- line extraction
- scene text
- visual attention
- computer vision