Open petermr opened 5 years ago
The ami20190418b can extract text from images in cTrees . This needs testing on the stata and `spss corpora.
ami20190418b
cTree
stata
`spss
run these by: cd to parent directory of spss corpus (e.g. $(HOME)/ContentMine/Projects/forestplots/ then
cd
spss
$(HOME)/ContentMine/Projects/forestplots/
ami-ocr -p spss
Notes: $PATH will have to be set to point toami-ocr`
$PATH will have to be set to point to
Also Tesseract must be installed locally, and the path set in AmiOCRTool parameters.
AmiOCRTool
The ami20190419 version has now been uploaded and supersedes the previous.
ami20190419
Builds y-lines of text.
The
ami20190418b
can extract text from images incTree
s . This needs testing on thestata
and`spss
corpora.run these by:
cd
to parent directory ofspss
corpus (e.g.$(HOME)/ContentMine/Projects/forestplots/
thenNotes:
$PATH will have to be set to point to
ami-ocr`Also Tesseract must be installed locally, and the path set in
AmiOCRTool
parameters.