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_scanned/groundtruth/docling_v2/ocr_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": 595.201171875,
"height": 841.9216918945312
},
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"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": 70.90211866351085,
"r_y0": 124.83139551297342,
"r_x1": 504.8720079864275,
"r_y1": 124.83139551297342,
"r_x2": 504.8720079864275,
"r_y2": 102.66666671251768,
"r_x3": 70.90211866351085,
"r_y3": 102.66666671251768,
"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": 73.10852522817731,
"r_y0": 152.70503335218433,
"r_x1": 153.04479435252625,
"r_y1": 152.70503335218433,
"r_x2": 153.04479435252625,
"r_y2": 130.00136157890958,
"r_x3": 73.10852522817731,
"r_y3": 130.00136157890958,
"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": 70.90211866351085,
"t": 76.99999977896756,
"r": 504.8720079864275,
"b": 152.70503335218433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9715733528137207,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"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": 70.90211866351085,
"r_y0": 124.83139551297342,
"r_x1": 504.8720079864275,
"r_y1": 124.83139551297342,
"r_x2": 504.8720079864275,
"r_y2": 102.66666671251768,
"r_x3": 70.90211866351085,
"r_y3": 102.66666671251768,
"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": 73.10852522817731,
"r_y0": 152.70503335218433,
"r_x1": 153.04479435252625,
"r_y1": 152.70503335218433,
"r_x2": 153.04479435252625,
"r_y2": 130.00136157890958,
"r_x3": 73.10852522817731,
"r_y3": 130.00136157890958,
"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": 70.90211866351085,
"t": 76.99999977896756,
"r": 504.8720079864275,
"b": 152.70503335218433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9715733528137207,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"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": 70.90211866351085,
"r_y0": 124.83139551297342,
"r_x1": 504.8720079864275,
"r_y1": 124.83139551297342,
"r_x2": 504.8720079864275,
"r_y2": 102.66666671251768,
"r_x3": 70.90211866351085,
"r_y3": 102.66666671251768,
"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": 73.10852522817731,
"r_y0": 152.70503335218433,
"r_x1": 153.04479435252625,
"r_y1": 152.70503335218433,
"r_x2": 153.04479435252625,
"r_y2": 130.00136157890958,
"r_x3": 73.10852522817731,
"r_y3": 130.00136157890958,
"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": 70.90211866351085,
"t": 76.99999977896756,
"r": 504.8720079864275,
"b": 152.70503335218433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9715733528137207,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"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": 70.90211866351085,
"r_y0": 124.83139551297342,
"r_x1": 504.8720079864275,
"r_y1": 124.83139551297342,
"r_x2": 504.8720079864275,
"r_y2": 102.66666671251768,
"r_x3": 70.90211866351085,
"r_y3": 102.66666671251768,
"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": 73.10852522817731,
"r_y0": 152.70503335218433,
"r_x1": 153.04479435252625,
"r_y1": 152.70503335218433,
"r_x2": 153.04479435252625,
"r_y2": 130.00136157890958,
"r_x3": 73.10852522817731,
"r_y3": 130.00136157890958,
"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