Search found 22 matches

by BruceRobertson
May 22nd, 2014, 8:40 pm
Forum: Polytonic Greek OCR
Topic: Primary vs. Secondary Resources
Replies: 7
Views: 2317

Re: Primary vs. Secondary Resources

Did you mean Schenkl's Dissertationes ab Arriano digestae? I ran it here: http://heml.mta.ca/lace/sidebysideview2/11956040 from a rather poor copy. I'm interested in other desiderata, both within and outside biblical materials, since it's better that we focus on what people need, rather than specifi...
by BruceRobertson
May 22nd, 2014, 1:18 pm
Forum: Polytonic Greek OCR
Topic: Assignment 2: PG 93 col. 1571-2
Replies: 11
Views: 3325

Re: Assignment 2: PG 93 col. 1571-2

Hi, all --

Using the Internet Archive link above, you should find a '+' and '-' button on the bottom of the browser window. This will zoom you into an image of a better resolution. I find I can solve just about any problem with this feature.
by BruceRobertson
May 22nd, 2014, 12:06 pm
Forum: Polytonic Greek OCR
Topic: Assignment 2: PG 93 col. 1571-2
Replies: 11
Views: 3325

Re: Assignment 2: PG 93 col. 1571-2

Are you using the image supplied above or the Internet Archive one? You should be able to zoom into IA very far so as to be able to resolve these ambiguities.
by BruceRobertson
May 21st, 2014, 8:29 pm
Forum: Polytonic Greek OCR
Topic: Assignment 3: PG 94 col. 1593-4
Replies: 17
Views: 4476

Re: Assignment 3: PG 94 col. 1593-4

Yes, please use the ligated forms.
by BruceRobertson
May 21st, 2014, 11:48 am
Forum: Polytonic Greek OCR
Topic: Assignment 2: PG 93 col. 1571-2
Replies: 11
Views: 3325

Re: Assignment 2: PG 93 col. 1571-2

Well, the old joke is that if you create a number of pages of ground truth = to the number of pages in the target corpus, you should get pretty close to perfect results :-) However, if my calculations are correct, the existing classifier is trained on 8 whole pages of ground truth. So any additional...
by BruceRobertson
May 21st, 2014, 8:06 am
Forum: Polytonic Greek OCR
Topic: Assignment 3: PG 94 col. 1593-4
Replies: 17
Views: 4476

Assignment 3: PG 94 col. 1593-4

Image for reference: http://heml.mta.ca/lace/static/Images/Color/patrologiaecursu93mignuoft_color/patrologiaecursu93mignuoft_0805.jpg Link to high-res image: https://archive.org/stream/patrologiaecursu93mignuoft#page/n802/mode/1up Another thought: if people are comfortable only with Greek, we could ...
by BruceRobertson
May 21st, 2014, 7:49 am
Forum: Polytonic Greek OCR
Topic: Assignment 2: PG 93 col. 1571-2
Replies: 11
Views: 3325

Assignment 2: PG 93 col. 1571-2

We've run the 9 volumes of PG that are in colour in the IA. We need training generally, but especially on reasonably dark pages (the very pale ones are not worth training to, since other sources do not share this fault) and italics, both Latin script and Greek. Once again, please do not alter the li...
by BruceRobertson
May 19th, 2014, 7:40 am
Forum: Polytonic Greek OCR
Topic: Identifying the fonts used in a scanned image
Replies: 1
Views: 1350

Re: Identifying the fonts used in a scanned image

I should make a field guide to this. For OCR purposes, what matters is the performance of a given engine/classifier combination. Ocropus/Ciaconna, e.g., appears to be more comprehensive, allowing various types of Porson fonts to be classified together, which is a really good thing for commentaries. ...
by BruceRobertson
May 18th, 2014, 2:18 pm
Forum: Polytonic Greek OCR
Topic: Assignment 1: Polytonic Greek OCR
Replies: 4
Views: 1679

Re: Assignment 1: Polytonic Greek OCR

This is a one-person task, I think, since it should only take about 10 - 30 minutes, depending on keyboarding skills. Why don't we just have people claim them on the forum here, and then others will know they're tied up?
by BruceRobertson
May 17th, 2014, 2:45 pm
Forum: Polytonic Greek OCR
Topic: Assignment 1: Polytonic Greek OCR
Replies: 4
Views: 1679

Assignment 1: Polytonic Greek OCR

For our experiment in crowd-sourcing the generation of ground-truth for OCR improvement, here's an example I'll hand off to whoever would like to try it on. The page image is: http://heml.org/lace/static/Images/Color/shortgrammarofgr00robeuoft_color/shortgrammarofgr00robeuoft_0150.jpg Text is the fo...

Go to advanced search