Commit graph

191 commits

Author SHA1 Message Date
vahidrezanezhad
1e7cecfcf9 updating ocr 2025-05-28 01:17:21 +02:00
vahidrezanezhad
03f52e7a46 updating ocr 2025-05-27 23:45:22 +02:00
vahidrezanezhad
31d9fa0c80 strings alignment function is added + new changes needed for prediction with both bin and rgb inputs is implemented 2025-05-25 21:44:36 +02:00
vahidrezanezhad
b18691f96a rnn ocr for all layout textregion types 2025-05-25 03:33:54 +02:00
vahidrezanezhad
ba3420b2d8 Drop capitals are written separately and are not attached to their corresponding text line. The OCR use case also supports single-image input. 2025-05-25 01:12:58 +02:00
vahidrezanezhad
0250a6d3d0 enhancing ocr 2025-05-23 18:06:53 +02:00
vahidrezanezhad
089029cec7 commit 21ec4fb is picked + rnn ocr at the same time with segmentation + enhancement of mb reading order 2025-05-23 15:55:03 +02:00
vahidrezanezhad
ee2c7e9013 enhancing curved lines OCR 2025-05-21 17:42:44 +02:00
vahidrezanezhad
14b70c2556 Implement hyphenated textline merging in OCR engine and a bug fixed for curved textline OCR 2025-05-21 14:39:31 +02:00
vahidrezanezhad
3ad621e956 ocr for curved lines 2025-05-20 19:01:52 +02:00
vahidrezanezhad
44ff51f5c1 mb reading order now can be done faster. Text regions are clustered using dilation, and mb reading order needs to be implemented for fewer regions 2025-05-20 16:51:08 +02:00
vahidrezanezhad
5016039cd7 enhancing marginal detection for light version 2025-05-18 02:48:05 +02:00
vahidrezanezhad
1cbc669d36 marginals detection enhanced for light version 2025-05-15 15:33:50 +02:00
vahidrezanezhad
1b229ba7ae enhancement for vertical textlines 2025-05-15 00:45:22 +02:00
vahidrezanezhad
ed46615f00 enhance ocr for vertical textlines 2025-05-14 18:34:58 +02:00
vahidrezanezhad
88e0315321 Accurately writing text line contours into xml file when the deskewing exceeds 45 degrees and the text line is in light mode 2025-05-13 15:53:05 +02:00
vahidrezanezhad
54088c6b04 The initial attempt at reading heavily deskewed or vertically aligned lines. 2025-05-13 14:40:57 +02:00
vahidrezanezhad
c12b09a868 I have tried to address the issues #163 and #161 . The changes have also improved marginal detection and enhanced the isolation of headers. 2025-05-12 00:10:18 +02:00
vahidrezanezhad
21ec4fbfb5 The text region coordinates are now correctly written into the XML output when using the skip layout and reading order option 2025-05-07 14:04:01 +02:00
vahidrezanezhad
83211ae684 In the case of skip_layout_and_reading_order, the confidence value was not set correctly, leading to an error while writing to the XML file. 2025-05-07 12:33:03 +02:00
vahidrezanezhad
89aa545049 let to add dataset abbrevation to extracted textline images and text 2025-05-03 02:59:16 +02:00
vahidrezanezhad
48e8dd4ab3 machine based model name changed to public one 2025-05-02 12:57:26 +02:00
vahidrezanezhad
a1a004b19d inference batch size for ocr is passed as an argument 2025-05-02 12:53:33 +02:00
vahidrezanezhad
5d8c864c08 adding space between splitted textline predicted text in the case of trocr 2025-05-02 01:02:32 +02:00
vahidrezanezhad
184af46664 displaying detexted text on an image is provided for trocr case 2025-05-02 00:30:36 +02:00
vahidrezanezhad
e2da7a6239 Fix model name to return the correct machine-based model name 2025-04-30 16:06:29 +02:00
vahidrezanezhad
b227736094 Fix OCR text cleaning to correctly handle 'U', 'K', and 'N' starting sentence; update text line splitting size 2025-04-30 16:04:34 +02:00
vahidrezanezhad
4cb4414740 Resolve remaining issue with #158 and resolving #124 2025-04-30 16:01:52 +02:00
vahidrezanezhad
208bde706f resolving issue #158 2025-04-30 13:55:09 +02:00
vahidrezanezhad
a22df11ebb Restoring the contour in the original image caused an error due to an empty tuple. This issue has been resolved, and as expected, the confidence score for this contour is set to zero 2025-04-14 00:42:08 +02:00
kba
8080bd823c 📦 v0.4.0 2025-04-07 16:48:57 +02:00
vahidrezanezhad
e2907f67e0 'from PIL.Image import Image' causes an error when using Image.new(), and since Image is already imported, this line can be safely commented out. 2025-04-06 00:33:36 +02:00
Robert Sachunsky
4339444e47 binarization CLI: fix option checks, simplify to asserts, fix dir_in mode 2025-04-05 01:21:08 +02:00
Robert Sachunsky
91a340f619 CLI: simplify option checks to asserts (also avoid stack trace) 2025-04-04 20:42:28 +02:00
Robert Sachunsky
e0a7fde537 logger: fix type hint 2025-04-04 20:27:15 +02:00
Robert Sachunsky
108ce1f5a1 Merge remote-tracking branch 'origin/main' into v3-api-release-foreal
(bad-ass difficult diff diffing)
2025-04-04 20:23:23 +02:00
vahidrezanezhad
2e3a29f66b In light mode: To determine whether a main region is a header, I adjusted the ratio to achieve better results. 2025-04-04 15:36:31 +02:00
vahidrezanezhad
38a2d60fa2 Confidence value for textregions and in the case of not light version is set to zero. This is done to let the pipeline go through. It will be updated to return the correct value in upcomming commits 2025-04-03 12:47:27 +02:00
vahidrezanezhad
6b52da227c docorating eynollah with textregion confidence score #135 2025-04-03 00:39:21 +02:00
Robert Sachunsky
559d001eef another fix to avoid frequent warnings 2025-04-02 05:45:34 +00:00
Robert Sachunsky
dd478279a4 CLI: also --overwrite in single-image mode 2025-04-02 05:40:21 +00:00
Robert Sachunsky
8159e6336a fix typo (preventing log messages) 2025-04-02 00:01:02 +00:00
Robert Sachunsky
2919538382 minor fixes to avoid frequent warnings 2025-04-01 23:33:26 +00:00
Robert Sachunsky
dcf2ed5e22 run: also write out XML in single filename mode 2025-04-01 23:13:24 +02:00
Robert Sachunsky
fe77171d45 run_single: reduce indentation 2025-04-01 22:47:33 +02:00
Robert Sachunsky
79003a083c CLI: ValueError instead of print+exit 2025-04-01 22:43:01 +02:00
Robert Sachunsky
e17d34fafa factor run_single() out of run(), simplify kwargs 2025-04-01 22:12:24 +02:00
Robert Sachunsky
1a0a1cb00b remove session methods and redundant model loaders 2025-04-01 21:15:41 +02:00
Robert Sachunsky
dd51f900b9 OCR-D: init Eynollah in 'setup', re-use instance for each page via non-public API 2025-04-01 13:02:30 +02:00
Robert Sachunsky
ffeb4a343d Eynollah: remove useless 'pcgts' attr 2025-04-01 13:00:41 +02:00