OCR-D/ocrd_tesserocr

Issues

• Missing text with OCR-D

  #217 opened 5 months ago by jbarth-ubhd
  10

• ocrd resmgr same comment for 2 tesseract models

  #210 opened 6 months ago by jbarth-ubhd
  4

• Incorrect model path with current master

  #202 opened 7 months ago by mikegerber
  4

• crop: removes original image ref

  #201 opened 9 months ago by bertsky
  7

• recognize: split polygon failure

  #209 opened 7 months ago by bertsky
  1

• ocrd-tesserocr-recognise (and all other aliases) show help string (docstring) of segment

  #207 opened 7 months ago by bertsky
  0

• ocrd-tesserocr-crop: 22.5h processing time

  #206 opened 8 months ago by jbarth-ubhd
  3

• possibly an invalid tessdata path: AT_SYMLINK_NOFOLLOW ?

  #195 opened 9 months ago by jbarth-ubhd
  6

• Convert tests to pytest and fix `make coverage`

  #198 opened 9 months ago by kba
  1

• Side effects of running tesserocr-recognize as a worker

  #196 opened a year ago by MehmedGIT
  5

• Invalid parameter - not of type boolean

  #194 opened a year ago by MehmedGIT
  2

• ocrd-tesserocr-segment-region TypeError: __init__() got multiple values for argument 'workspace'

  #193 opened 2 years ago by mikegerber
  3

• ocrd-tesserocr-segment does not work

  #189 opened 2 years ago by jbarth-ubhd
  6

• A lot of ShapelyDeprecationWarning: The 'type' attribute is deprecated

  #192 opened 2 years ago by mikegerber
  2

• Use ocrd-tesserocr with caching for Processing Server not possible

  #190 opened 2 years ago by joschrew
  5

• list-resources not correct

  #174 opened 2 years ago by bertsky
  3

• reverse order of glyphs inside words in PAGE-File for RTL languages

  #185 opened 3 years ago by MihoMahi
  3

• ocrd-tesserocr-segment: segmentation fault

  #182 opened 3 years ago by jbarth-ubhd
  11

• incremental segmentation

  #183 opened 3 years ago by bertsky
  0

• montfaucon1719bd2_1, page 210, ocrd-tesserocr-segment -P find_tables false -P shrink_polygons true

  #181 opened 3 years ago by jbarth-ubhd
  0

• document model installation

  #173 opened 3 years ago by bertsky
  1

• Make it clearer which Tesseract engine is being used

  #168 opened 4 years ago by Witiko
  12

• resource_manager already causes initLogging

  #169 opened 4 years ago by bertsky
  1

• ocrd-tesserocr-recognize produces glyph segmentation that ocrd-fileformat-transform can't convert to ALTO

  #171 opened 4 years ago by mikegerber
  5

• ocrd_tesserocr processors waste CPU performance because of numpy blas threads

  #157 opened 4 years ago by stweil
  6

• segment-line: annotate polygon or clipped image

  #127 opened 5 years ago by bertsky
  3

• Problem with table recognition

  #134 opened 4 years ago by Shanksum
  9

• Floating regions

  #155 opened 4 years ago by beckstefan
  8

• ERROR processor.TesserocrCrop - Cannot find valid extent for page 'P_00001'

  #159 opened 4 years ago by jbarth-ubhd
  1

• shapely.errors.TopologicalError: The operation 'GEOSWithin_r' could not be performed. Likely cause is invalidity of the geometry <shapely.geometry.polygon.Polygon object at 0x7fb58a658b80>

  #160 opened 4 years ago by mikegerber
  3

• ocrd-tesserocr-recognize and docker

  #161 opened 4 years ago by gpetz
  3

• Processor tesserocr-segment-line terminates with exception (TopologyException: Input geom 1 is invalid)

  #149 opened 4 years ago by stweil
  23

• tesseract-recognize creates negative word coordinates

  #153 opened 4 years ago by stweil
  8

• ocrd-tesserocr-segment-region fails with AttributeError: 'LineString' object has no attribute 'exterior'

  #151 opened 4 years ago by stweil
  3

• Exception: File with ID=... already exists

  #147 opened 4 years ago by beckstefan
  5

• Processor terminates with exception: ocrd-tesserocr-segment-region exited with non-zero

  #139 opened 4 years ago by stweil
  7

• Processor terminates with exception: 'TesserocrDeskew' object has no attribute 'image_grp'

  #142 opened 4 years ago by stweil
  0

• CI fails

  #137 opened 4 years ago by bertsky
  0

• Does not set pcGtsId

  #135 opened 4 years ago by mikegerber
  0

• TESSDATA_PREFIX is interpreted incorrectly

  #129 opened 4 years ago by kba
  2

• PAGE helper functions in recognize to generateDS API?

  #131 opened 4 years ago by kba
  1

• segment-line: Self-intersection at or near point ...

  #123 opened 5 years ago by jbarth-ubhd
  9

• "segment-line" produces "GeometryCollection" (which has no coords)

  #119 opened 5 years ago by wrznr
  2

• RFC: Harmonize parameters for similar processors

  #118 opened 5 years ago by stweil
  1

• pip install ocrd_tesserocr error

  #117 opened 5 years ago by WeiHin
  2

• bug: segment-region produce empty OrderedGroup

  #115 opened 5 years ago by tboenig
  5

• TypeError: object of type 'list_reverseiterator' has no len()

  #112 opened 5 years ago by mikegerber
  4

• recognize: expose character white/blacklisting parameters

  #107 opened 5 years ago by bertsky
  0

• Memory leaks

  #105 opened 5 years ago by stweil
  31

• Why does 'ocrd-tesserocr-deskew' need 'osd.traineddata' as a model?

  #106 opened 5 years ago by VolkerHartmann
  5