mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-09 21:28:17 +00:00
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>
This commit is contained in:
@@ -1390,7 +1390,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 134.9199981689453,
|
||||
"l": 134.9200439453125,
|
||||
"t": 304.890625,
|
||||
"r": 475.6635437011719,
|
||||
"b": 510.21826171875,
|
||||
@@ -2174,7 +2174,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 134.9199981689453,
|
||||
"l": 134.9200439453125,
|
||||
"t": 304.890625,
|
||||
"r": 475.6635437011719,
|
||||
"b": 510.21826171875,
|
||||
@@ -2909,7 +2909,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 134.9199981689453,
|
||||
"l": 134.9200439453125,
|
||||
"t": 304.890625,
|
||||
"r": 475.6635437011719,
|
||||
"b": 510.21826171875,
|
||||
@@ -3623,7 +3623,7 @@
|
||||
"b": 268.20489999999995,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.987092912197113,
|
||||
"confidence": 0.9870928525924683,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@@ -3938,7 +3938,7 @@
|
||||
"b": 532.05774,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9494234323501587,
|
||||
"confidence": 0.9494236707687378,
|
||||
"cells": [
|
||||
{
|
||||
"index": 12,
|
||||
@@ -4302,7 +4302,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 218.81556701660156,
|
||||
"l": 218.8155517578125,
|
||||
"t": 278.0153503417969,
|
||||
"r": 391.96246337890625,
|
||||
"b": 508.89410400390625,
|
||||
@@ -4337,7 +4337,7 @@
|
||||
"b": 268.20489999999995,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.987092912197113,
|
||||
"confidence": 0.9870928525924683,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@@ -4658,7 +4658,7 @@
|
||||
"b": 532.05774,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9494234323501587,
|
||||
"confidence": 0.9494236707687378,
|
||||
"cells": [
|
||||
{
|
||||
"index": 12,
|
||||
@@ -5040,7 +5040,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 218.81556701660156,
|
||||
"l": 218.8155517578125,
|
||||
"t": 278.0153503417969,
|
||||
"r": 391.96246337890625,
|
||||
"b": 508.89410400390625,
|
||||
@@ -5072,7 +5072,7 @@
|
||||
"b": 268.20489999999995,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.987092912197113,
|
||||
"confidence": 0.9870928525924683,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@@ -5393,7 +5393,7 @@
|
||||
"b": 532.05774,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9494234323501587,
|
||||
"confidence": 0.9494236707687378,
|
||||
"cells": [
|
||||
{
|
||||
"index": 12,
|
||||
@@ -5729,7 +5729,7 @@
|
||||
"id": 2,
|
||||
"label": "picture",
|
||||
"bbox": {
|
||||
"l": 218.81556701660156,
|
||||
"l": 218.8155517578125,
|
||||
"t": 278.0153503417969,
|
||||
"r": 391.96246337890625,
|
||||
"b": 508.89410400390625,
|
||||
|
||||
Reference in New Issue
Block a user