Augmentation-based Pseudo-Ground truth Generation for Deep Learning in Historical Document Segmentation for Greater Levels of Archival Description and Access.
Chulwoo PackYi LiuLeen-Kiat SohElizabeth LorangPublished in: ACM Journal on Computing and Cultural Heritage (2022)
Keyphrases
- deep learning
- ground truth
- unsupervised learning
- unsupervised feature learning
- image segmentation
- level set
- segmentation algorithm
- test images
- machine learning
- information retrieval
- mental models
- segmentation method
- shape prior
- document images
- multiscale
- medical images
- document clustering
- supervised learning
- object segmentation
- computer vision
- image regions
- dimensionality reduction
- principal component analysis
- automatic extraction
- high dimensional
- weakly supervised
- pattern recognition
- keywords