v0.7.0

Added:

• segment-table: new processor that adds table cells as text regions, #104
• raw_lines option, #104
• interprete overwrite_regions more consistently, #104
• annotate @orientation (independent of dedicated deskewing processor) for vertical and @type for all other text blocks, #104
• no separators and noise regions in reading order, #104

Changed:

• docker image built on Ubuntu 18.04, #94, #97
• Consistent setup of docker, #97

v0.6.0

Changed:

• Depend on OCR-D/core v2.0.0

v0.5.1

Fixed:

• Correct version in ocrd-tool.json, #76

v0.4.1

• Adapt to feature selection/filtering mechanism for derived images in core
• Fixes for image-feature-related corner cases in crop and deskew
• Use explicit (second) output fileGrp when producing derived images
• Upgrade to upstream tesserocr 2.4.1
• Use OCR core >= stable 1.0.0

v0.5.0

• Adapt to new core image API, #80
• Use OCR core >= unstable 2.0.0a1

v0.4.0

Changed:

• 🔥 common.py is now part of OCR-D/core's ocrd_utils, OCR-D/core#268, #49
• many fixes and improvements to crop, deskew, binarize
• proper handling of orientaton on page level
• updated requirements

v0.3.0: implement AlternativeImage-based processing:

Changed:

• Use basename of input file for output name
• Use .xml filename extension for PAGE output
• Warn about existing border or regions in crop
• Use PSM.SPARSE_TEXT without tables in crop
• Filter unreliable regions in crop
• Add padding around border in crop
• Delete existing regions in segment_region
• Cover vertical text and tables in segment_region
• Add parameter find_tables in segment_region
• Add parameter crop_polygons in segment_region
• Add parameter overwrite_regions in segment_region
• Add parameter overwrite_lines in segment_line
• Add parameter overwrite_words in segment_word
• Add page/region-level processor deskew
• Add page/region/line-level processor binarize
• Respect AlternativeImage on all levels

v0.2.2

Changed:

• Add simple page cropping processor crop
• Respect border cropping in segment_word
• Add parameter overwrite_words in recognize
• Make higher TextEquivs consistent after recognize

Fixed:

• Remove invalid @externalRef from MetadataItem
• Retain pageId in output (i.e. link to structMap)

v0.1.2

Fixed:

• arithmetic average (not product) for line conf, #22

v0.1.1

Fixed:

• robust conf calculation (when no result), #21