mirror of
				https://github.com/qurator-spk/ocrd-galley.git
				synced 2025-10-31 19:24:12 +01:00 
			
		
		
		
	🧹 Modernize my_ocrd_workflow and use OCR-D's new --overwrite
This commit is contained in:
		
							parent
							
								
									3af3c6dd00
								
							
						
					
					
						commit
						efd955c04f
					
				
					 1 changed files with 7 additions and 16 deletions
				
			
		|  | @ -59,18 +59,14 @@ do_binarization() { | ||||||
|   ocrd_olena_binarize_parameters='{ |   ocrd_olena_binarize_parameters='{ | ||||||
|     "impl": "sauvola-ms-split" |     "impl": "sauvola-ms-split" | ||||||
|   }' |   }' | ||||||
|   ocrd workspace remove-group -rf OCR-D-IMG-BINPAGE |   ocrd-olena-binarize --overwrite -I $INPUT_FILE_GRP -O OCR-D-IMG-BINPAGE,OCR-D-IMG-BIN -p "$ocrd_olena_binarize_parameters" | ||||||
|   ocrd workspace remove-group -rf OCR-D-IMG-BIN |  | ||||||
|   ocrd-olena-binarize -I $INPUT_FILE_GRP -O OCR-D-IMG-BINPAGE,OCR-D-IMG-BIN -p "$ocrd_olena_binarize_parameters" |  | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| do_linesegmentation_tesserocr() { | do_linesegmentation_tesserocr() { | ||||||
|   # Segment the lines in the binarized images |   # Segment the lines in the binarized images | ||||||
| 
 | 
 | ||||||
|   ocrd workspace remove-group -rf OCR-D-SEG-REGION |   ocrd-tesserocr-segment-region --overwrite -I OCR-D-IMG-BINPAGE -O OCR-D-SEG-REGION | ||||||
|   ocrd workspace remove-group -rf OCR-D-SEG-LINE |   ocrd-tesserocr-segment-line --overwrite -I OCR-D-SEG-REGION -O OCR-D-SEG-LINE | ||||||
|   ocrd-tesserocr-segment-region -I OCR-D-IMG-BINPAGE -O OCR-D-SEG-REGION |  | ||||||
|   ocrd-tesserocr-segment-line -I OCR-D-SEG-REGION -O OCR-D-SEG-LINE |  | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| do_linesegmentation_sbb() { | do_linesegmentation_sbb() { | ||||||
|  | @ -79,9 +75,7 @@ do_linesegmentation_sbb() { | ||||||
|   ocrd_sbb_textline_detector_parameters='{ |   ocrd_sbb_textline_detector_parameters='{ | ||||||
|     "model": "/var/lib/textline_detection" |     "model": "/var/lib/textline_detection" | ||||||
|   }' |   }' | ||||||
|   ocrd workspace remove-group -rf OCR-D-SEG-REGION |   ocrd-sbb-textline-detector --overwrite -I OCR-D-IMG-BINPAGE -O OCR-D-SEG-LINE -p "$ocrd_sbb_textline_detector_parameters" | ||||||
|   ocrd workspace remove-group -rf OCR-D-SEG-LINE |  | ||||||
|   ocrd-sbb-textline-detector -I OCR-D-IMG-BINPAGE -O OCR-D-SEG-LINE -p "$ocrd_sbb_textline_detector_parameters" |  | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| do_ocr() { | do_ocr() { | ||||||
|  | @ -91,8 +85,7 @@ do_ocr() { | ||||||
|     "model": "GT4HistOCR_2000000", |     "model": "GT4HistOCR_2000000", | ||||||
|     "textequiv_level": "'$TEXTEQUIV_LEVEL'" |     "textequiv_level": "'$TEXTEQUIV_LEVEL'" | ||||||
|   }' |   }' | ||||||
|   ocrd workspace remove-group -rf OCR-D-OCR-TESS |   ocrd-tesserocr-recognize --overwrite -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS -p "$ocrd_tesserocr_recognize_parameters" | ||||||
|   ocrd-tesserocr-recognize -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS -p "$ocrd_tesserocr_recognize_parameters" |  | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| do_ocr_calamari() { | do_ocr_calamari() { | ||||||
|  | @ -102,8 +95,7 @@ do_ocr_calamari() { | ||||||
|     "checkpoint": "/var/lib/calamari-models/GT4HistOCR/2019-07-22T15:49+0200/*.ckpt.json", |     "checkpoint": "/var/lib/calamari-models/GT4HistOCR/2019-07-22T15:49+0200/*.ckpt.json", | ||||||
|     "textequiv_level": "'$TEXTEQUIV_LEVEL'" |     "textequiv_level": "'$TEXTEQUIV_LEVEL'" | ||||||
|   }' |   }' | ||||||
|   ocrd workspace remove-group -rf OCR-D-OCR-CALAMARI |   ocrd-calamari-recognize --overwrite -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI -p "$ocrd_calamari_recognize_parameters" | ||||||
|   ocrd-calamari-recognize -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI -p "$ocrd_calamari_recognize_parameters" |  | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| page_validate_xml() { | page_validate_xml() { | ||||||
|  | @ -159,8 +151,7 @@ main() { | ||||||
|     do_validate |     do_validate | ||||||
| 
 | 
 | ||||||
|     if ocrd workspace list-group | grep -q OCR-D-GT-PAGE; then |     if ocrd workspace list-group | grep -q OCR-D-GT-PAGE; then | ||||||
|       ocrd workspace remove-group -rf $ocr_filegrp-EVAL |       ocrd-dinglehopper --overwrite -I OCR-D-GT-PAGE,$ocr_filegrp -O $ocr_filegrp-EVAL | ||||||
|       ocrd-dinglehopper -I OCR-D-GT-PAGE,$ocr_filegrp -O $ocr_filegrp-EVAL |  | ||||||
|     fi |     fi | ||||||
| 
 | 
 | ||||||
|   done |   done | ||||||
|  |  | ||||||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue