Marmelator/cv-analysis-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 37 Wiki Activity
72 Commits 19 Branches 190 Tags
Commit Graph

72 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Isaac Riley
4c06206445 merge minor changes before branching 2022-02-28 08:07:08 +01:00
Isaac Riley
44d4eb5a98 format and add functions in post_processing.py missing from merge 2022-02-25 12:34:34 +01:00
Isaac Riley
fc4789101f merge hugo into main; deskew already merged 2022-02-25 11:20:40 +01:00
Isaac Riley
596aa2d5a3 prepare for merge; minor edits 2022-02-25 09:46:20 +01:00
Isaac Riley
2180ff924a make full demo 2022-02-23 13:41:57 +01:00
Isaac Riley
a09fe65ed2 minor changes to demo script 2022-02-22 16:04:11 +01:00
Isaac Riley
8ff5147ee4 change default deskew function from hough-line-based to pixel-histogram-based; use scipy.ndimage.rotation 2022-02-22 10:18:41 +01:00
Isaac Riley
59e082379c fix angle detection to make more sensitive to small angles; format with black 2022-02-21 16:52:24 +01:00
Isaac Riley
08cce36940 add deskew.py to utils, also demo 2022-02-21 14:53:09 +01:00
llocarnini
2a68e1b221 kernel size for morphology ex set bit higher, so less non-table structure are detected. Reduced the kernel size of the directional motion blurr and increased the treshold a little bit so narrow cells wont be split up. 
Problem with the cell filtering for certain scanned pdfs detected.
 2022-02-18 16:36:25 +01:00
llocarnini
723c6606e1 kernel size for morphology ex set bit higher, so less non-table structure are detected. Reduced the kernel size of the directional motion blurr and increased the treshold a little bit so narrow cells wont be split up. 
Problem with the cell filtering for certain scanned pdfs detected.
 2022-02-18 16:35:50 +01:00
llocarnini
d70781f4aa changed tolerance in adjacent1 function in postprocessing.y from 2 to 4 
added function so vertical and horizontal components do not overlap the layout box of the table
 2022-02-17 16:45:55 +01:00
llocarnini
57ca47f38d different approaches to isolate line components of tables in scanned pdf files. 2022-02-16 12:37:17 +01:00
llocarnini
c2faf7d00b adjusted isolation of vertical and horizontal components to be more robust to scanned pages; work in progress 2022-02-14 11:04:04 +01:00
llocarnini
885fc22f9d added changes to parse scanned pdfs 2022-02-11 15:59:54 +01:00
llocarnini
07907d45dd some changes to fix some minor bugs in table_parsing.py and post_processing.py 2022-02-10 10:56:03 +01:00
llocarnini
4964c8f5a1 some changes to fix some minor bugs in table_parsing.py and post_processing.py 2022-02-10 10:22:22 +01:00
Matthias Bisping
f7d3e39692 nix dolles 2022-02-08 15:05:12 +01:00
Matthias Bisping
87cecadb44 applied black 2022-02-06 21:27:39 +01:00
Matthias Bisping
295666c28f added todo comments 2022-02-06 21:25:01 +01:00
Matthias Bisping
90b8613bf8 filtering non-tables by bounding rect check WIP 2022-02-06 21:03:40 +01:00
Matthias Bisping
36284f9a78 removed obsolete lines 2022-02-06 20:01:00 +01:00
Matthias Bisping
0fc6cf8008 fixed bug in adjaceny test 2022-02-06 20:00:38 +01:00
Matthias Bisping
106b333dca filtering for connected cells... but does not quite work yet 2022-02-06 16:44:07 +01:00
Matthias Bisping
c9b2f6bf29 Pull request #9: Refactoring 
Merge in RR/vidocp from refactoring to master

Squashed commit of the following:

commit 36a62a13e51148d2420cb12930e84d78629db6b0
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:54:53 2022 +0100

    refactoring

commit e652da1fa88a048f9a5211b4e8c0b96074fb5849
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:53:17 2022 +0100

    refactoring

commit d9567da428c81f9cd7971a657281df0a90166810
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:47:18 2022 +0100

    refactoring

commit 9d30009dceec0357db6499bfaffae8ce97718ee0
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:45:53 2022 +0100

    refactoring

commit e8863d67aaaff138fb088c4e496a91b6354cc059
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:42:45 2022 +0100

    refactoring

commit 89a99d3586db4fbafa743a45bdd02eaf0c1f341f
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:39:49 2022 +0100

    refactoring

commit aa66b6865b00b0490b9e7695a6bae386e6f96723
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:31:21 2022 +0100

    refactoring

commit 98d77cb522a08821c3a13ae2cffbe7239c654762
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:27:55 2022 +0100

    refactoring

commit fed3a7e4f1b8b7ca4e14f9e495459c26490fb50b
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:26:16 2022 +0100

    refactoring

commit 504cafbd5d4bba183d9943b36c60548aae34e402
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:25:44 2022 +0100

    renaming

commit c9780a57e5a048529d36958ba678eddb11759cef
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:24:41 2022 +0100

    removed obsolete import

commit d555e86475e82024f8e1a5fc5b0ac70faa091ee1
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 14:24:04 2022 +0100

    refactored figure detection once
 2022-02-06 14:55:38 +01:00
Matthias Bisping
36a62a13e5 refactoring 2022-02-06 14:54:53 +01:00
Matthias Bisping
e652da1fa8 refactoring 2022-02-06 14:53:17 +01:00
Matthias Bisping
d9567da428 refactoring 2022-02-06 14:47:18 +01:00
Matthias Bisping
9d30009dce refactoring 2022-02-06 14:45:53 +01:00
Matthias Bisping
e8863d67aa refactoring 2022-02-06 14:42:45 +01:00
Matthias Bisping
89a99d3586 refactoring 2022-02-06 14:39:49 +01:00
Matthias Bisping
aa66b6865b refactoring 2022-02-06 14:31:21 +01:00
Matthias Bisping
98d77cb522 refactoring 2022-02-06 14:27:55 +01:00
Matthias Bisping
fed3a7e4f1 refactoring 2022-02-06 14:26:16 +01:00
Matthias Bisping
504cafbd5d renaming 2022-02-06 14:25:44 +01:00
Matthias Bisping
c9780a57e5 removed obsolete import 2022-02-06 14:24:41 +01:00
Matthias Bisping
d555e86475 refactored figure detection once 2022-02-06 14:24:04 +01:00
Matthias Bisping
8432cfe514 Pull request #8: figure detection 
Merge in RR/vidocp from text_removal to master

Squashed commit of the following:

commit b65374c512ce9ba07fa522d591c83db3de5d7d55
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 01:03:12 2022 +0100

    readme updated

commit 1c1f7a395a00fa505cf19e1ad87d8c34faa6ef5b
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 01:00:46 2022 +0100

    figure detection version 1 completed

commit f257660823ef8682e9fedda9921ad946ef2ade76
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 00:37:03 2022 +0100

    wip

commit 2e89b28f4a69da80570597c823b3b7a591788d0a
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sun Feb 6 00:23:56 2022 +0100

    wip
 2022-02-06 01:04:15 +01:00
Matthias Bisping
b82a294610 Pull request #7: Layout detection version 3 
Merge in RR/vidocp from layout_detection_version_3 to master

Squashed commit of the following:

commit 262b1c14c0b8b164221d39fd286b20914d1a8e6a
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 22:56:10 2022 +0100

    comment

commit 975dcdaae2b0e9bfcb075fe1c87adc48175c0d93
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 22:50:41 2022 +0100

    applied black

commit 49ba3b5f318a1b5d6bb39c0b53de5e237a87da96
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 22:48:44 2022 +0100

    improved layout parsing logic: filtering of included rects

commit d78ac24c10793f72b569c3c827834400b730888a
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 22:36:49 2022 +0100

    improved layout parsing logic: filtering of overlaps, no sub-text regions
 2022-02-05 22:58:51 +01:00
Matthias Bisping
7ceb534fa2 readme updated 2022-02-05 20:31:13 +01:00
Matthias Bisping
8a9b493c94 readme updated 2022-02-05 20:29:23 +01:00
Matthias Bisping
e62a88ff9a fixed import 2022-02-05 20:27:29 +01:00
Matthias Bisping
bb5707dc89 Pull request #6: added layout parsing logic 
Merge in RR/vidocp from layout_detection_version_2 to master

Squashed commit of the following:

commit d443e95ad8143bed3efc74d9e38640498d8d16bf
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 20:16:13 2022 +0100

    readme updated

commit 953ad696932454ce851544ed016f9e64bcc12080
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 20:14:59 2022 +0100

    added layot parsing logic
 2022-02-05 20:17:14 +01:00
Matthias Bisping
00748a8ac0 Pull request #5: Table parsing version 2 
Merge in RR/vidocp from table_parsing_version_2 to master

Squashed commit of the following:

commit af136ca10cf96f99699e409000ff598ce90c192e
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:34:01 2022 +0100

    readme updated

commit 13ca7b1b03cb2bf7b3c8ef5821c1f8fa9ec532a0
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:32:11 2022 +0100

    drawing color standardized

commit 654e961c62ddc0f512074e8238d7fa88f0ea227e
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:22:57 2022 +0100

    refactoring

commit 964c17a36f7bbc1376dfe68f4ea90462d676e215
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:07:16 2022 +0100

    readme updated

commit 4470969b35bb76e68cc41947fa02e63100b30ce9
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:05:35 2022 +0100

    readme updated

commit a6c6bdb1e71a778a3c21a628cfb30acc5bc6086f
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:05:21 2022 +0100

    readme updated

commit e178793dd69b720adefe7533312314e4c405f975
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 18:03:45 2022 +0100

    readme updated

commit 443163864bab56930c2ef735c0aaafddd2561ead
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Sat Feb 5 17:59:03 2022 +0100

    implememted clean solution for parsing open tables. still needs final refactoring.
 2022-02-05 19:32:47 +01:00
Matthias Bisping
224360c823 readme updated 2022-02-05 16:23:42 +01:00
Matthias Bisping
9507bffd89 readme updated 2022-02-05 16:20:23 +01:00
Matthias Bisping
e454938c1e readme updated 2022-02-05 16:20:05 +01:00
Matthias Bisping
5491f511e2 readme updated 2022-02-05 16:19:27 +01:00
Matthias Bisping
5fec1db1e6 readme updated 2022-02-05 16:18:01 +01:00
Matthias Bisping
d5f445b5e1 readme updated 2022-02-05 16:17:39 +01:00