mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 03:55:00 +00:00
Code Issues Packages Projects Releases Wiki Activity
45265bf8b1
docling/tests/data/webp/groundtruth/docling_v2/webp-test.pages.json
Clément Doumouro 45265bf8b1
feat(ocr): auto-detect rotated pages in Tesseract (#1167) 
* fix(ocr): tesseract support mis-oriented documents

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): update missing test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): rotate image to the natural orientation before layout prediction

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): move bounding bow rotation util to orientation.py

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): refactor rotation utilities

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): avoid to swallow tesseract errors causing orientation detection failures

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrCliModel`

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrModel`

* chore(ocr): default `TesseractOcrCliModel._is_auto` to `False`

* fix(ocr): fix `TesseractOcrCliModel._is_auto` computation

* chore(ocr): improve logging in case of OSD failure in `TesseractOcrCliModel` and `TesseractOcrModel`

---------

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
2025-05-21 18:12:33 +02:00

388 lines
12 KiB
JSON
Raw Blame History

[
{
"page_no": 0,
"size": {
"width": 2000.0,
"height": 2829.0
},
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 246.4065456254215,
"r_y0": 329.06770715202435,
"r_x1": 1691.991797818404,
"r_y1": 329.06770715202435,
"r_x2": 1691.991797818404,
"r_y2": 258.9040166758338,
"r_x3": 246.4065456254215,
"r_y3": 258.9040166758338,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 238.19302423176944,
"r_y0": 415.36904822716525,
"r_x1": 1696.0985546594009,
"r_y1": 415.36904822716525,
"r_x2": 1696.0985546594009,
"r_y2": 345.20535775097477,
"r_x3": 238.19302423176944,
"r_y3": 345.20535775097477,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 245.43122061153045,
"r_y0": 513.795726112558,
"r_x1": 514.3223724413002,
"r_y1": 513.795726112558,
"r_x2": 514.3223724413002,
"r_y2": 436.0574704074058,
"r_x3": 245.43122061153045,
"r_y3": 436.0574704074058,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
}
],
"parsed_page": null,
"predictions": {
"layout": {
"clusters": [
{
"id": 0,
"label": "text",
"bbox": {
"l": 238.19302423176944,
"t": 258.9040166758338,
"r": 1696.0985546594009,
"b": 513.795726112558,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9721010327339172,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 246.4065456254215,
"r_y0": 329.06770715202435,
"r_x1": 1691.991797818404,
"r_y1": 329.06770715202435,
"r_x2": 1691.991797818404,
"r_y2": 258.9040166758338,
"r_x3": 246.4065456254215,
"r_y3": 258.9040166758338,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 238.19302423176944,
"r_y0": 415.36904822716525,
"r_x1": 1696.0985546594009,
"r_y1": 415.36904822716525,
"r_x2": 1696.0985546594009,
"r_y2": 345.20535775097477,
"r_x3": 238.19302423176944,
"r_y3": 345.20535775097477,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 245.43122061153045,
"r_y0": 513.795726112558,
"r_x1": 514.3223724413002,
"r_y1": 513.795726112558,
"r_x2": 514.3223724413002,
"r_y2": 436.0574704074058,
"r_x3": 245.43122061153045,
"r_y3": 436.0574704074058,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
}
],
"children": []
}
]
},
"tablestructure": {
"table_map": {}
},
"figures_classification": null,
"equations_prediction": null,
"vlm_response": null
},
"assembled": {
"elements": [
{
"label": "text",
"id": 0,
"page_no": 0,
"cluster": {
"id": 0,
"label": "text",
"bbox": {
"l": 238.19302423176944,
"t": 258.9040166758338,
"r": 1696.0985546594009,
"b": 513.795726112558,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9721010327339172,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 246.4065456254215,
"r_y0": 329.06770715202435,
"r_x1": 1691.991797818404,
"r_y1": 329.06770715202435,
"r_x2": 1691.991797818404,
"r_y2": 258.9040166758338,
"r_x3": 246.4065456254215,
"r_y3": 258.9040166758338,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 238.19302423176944,
"r_y0": 415.36904822716525,
"r_x1": 1696.0985546594009,
"r_y1": 415.36904822716525,
"r_x2": 1696.0985546594009,
"r_y2": 345.20535775097477,
"r_x3": 238.19302423176944,
"r_y3": 345.20535775097477,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 245.43122061153045,
"r_y0": 513.795726112558,
"r_x1": 514.3223724413002,
"r_y1": 513.795726112558,
"r_x2": 514.3223724413002,
"r_y2": 436.0574704074058,
"r_x3": 245.43122061153045,
"r_y3": 436.0574704074058,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
}
],
"children": []
},
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
}
],
"body": [
{
"label": "text",
"id": 0,
"page_no": 0,
"cluster": {
"id": 0,
"label": "text",
"bbox": {
"l": 238.19302423176944,
"t": 258.9040166758338,
"r": 1696.0985546594009,
"b": 513.795726112558,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9721010327339172,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 246.4065456254215,
"r_y0": 329.06770715202435,
"r_x1": 1691.991797818404,
"r_y1": 329.06770715202435,
"r_x2": 1691.991797818404,
"r_y2": 258.9040166758338,
"r_x3": 246.4065456254215,
"r_y3": 258.9040166758338,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 238.19302423176944,
"r_y0": 415.36904822716525,
"r_x1": 1696.0985546594009,
"r_y1": 415.36904822716525,
"r_x2": 1696.0985546594009,
"r_y2": 345.20535775097477,
"r_x3": 238.19302423176944,
"r_y3": 345.20535775097477,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 245.43122061153045,
"r_y0": 513.795726112558,
"r_x1": 514.3223724413002,
"r_y1": 513.795726112558,
"r_x2": 514.3223724413002,
"r_y2": 436.0574704074058,
"r_x3": 245.43122061153045,
"r_y3": 436.0574704074058,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
}
],
"children": []
},
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
}
],
"headers": []
}
}
]
Reference in New Issue View Git Blame Copy Permalink