OCR · Admin / QA

OCR Review

Unsichere Scans und offene Belege hier ruhig prüfen.

← QA Übersicht Pipelines Public OCR

Offen 26

Wartend 11

Nicht erkannt 0

Fehlgeschlagen 0

In Prüfung 0

Struktur 0

Fertig 0

Geparst 15

OCR Status

Backend: pytesseract+tesseract
Language: deu+eng
Tesseract: /usr/bin/tesseract
Available: yes
Python package: yes
tesseract found: yes
Pillow/preprocessing: yes
HEIF support: yes
Retry possible: yes

Supported formats: .heic, .heif, .jpeg, .jpg, .png

Letzter OCR-Check

Source file: imports/unknown/2026-05-27_123627_auto_img_3362.jpeg
Source identity: image · alnatura · receipt_photo
Source type / vendor: image / alnatura
Import method: upload
OCR variant: scaled_normalized
Suffix / Format: .jpeg / MPO
Mode: RGB → RGB
Preprocessing: True · Stage: normalized
Quality: good · Score: 100.0
Quality reasons: detected_total, detected_date, detected_vendor, likely_receipt, soft_image, rotation_corrected
Text / lines: 1733 / 51
Vendor / total / date: alnatura / True / True
Likely receipt: True
Image: 4284×5712 · small=False · rotation=True
Status: ocr_parsed
OCR status: ocr_parsed
Parse status: ocr_parsed
Parser: alnatura_receipt_parser · review · available=True
Line items: 41
Confidence: HIGH
Parser ready: True
Needs review: False
Generated: 2026-06-01T14:29:43.997929+00:00

OCR prüfen

synchroner lokaler Runner

Pending Images werden inklusive `imports/inbox/` und `imports/needs_review/` angezeigt.

Offene Bilder

Datei	Source	Status	Nächster Schritt	Hinweis
`2026-05-27_123619_auto_img_3361.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123619_auto_img_3361.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123627_auto_img_3362.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123634_auto_img_3363.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123634_auto_img_3363.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123641_auto_img_3364.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123641_auto_img_3364.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123648_auto_img_3365.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123648_auto_img_3365.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123654_auto_img_3366.jpeg`	`unknown`	pending	Run OCR	OCR audit missing
`2026-05-27_123654_auto_img_3366.jpeg`	`unknown`	pending	Run OCR	OCR audit missing

Problemfälle

Nicht erkannt

Keine unsupported Inputs.

Fehlgeschlagen

Keine OCR-Fehler.

Struktur / Prüfung

Keine Structure-/Review-Fälle.

Fertig / Geparst

Datei	Suffix	Format	Source	Mode	HEIF	Preproc	Source	OCR	Parse	Parser	Qualität	Backend
`2026-05-21_091415_auto_img_3351.jpeg`	`.jpeg`	`MPO`	`image · alnatura · receipt_photo`	`RGB→RGB`	yes	`True`	`alnatura`	ocr_parsed	`ocr_parsed`	`alnatura_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-21_091415_auto_img_3351.jpeg`	`.jpeg`	`MPO`	`image · alnatura · receipt_photo`	`RGB→RGB`	yes	`True`	`alnatura`	ocr_parsed	`ocr_parsed`	`alnatura_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-27_123627_auto_img_3362.jpeg`	`.jpeg`	`MPO`	`image · alnatura · receipt_photo`	`RGB→RGB`	yes	`True`	`alnatura`	ocr_parsed	`ocr_parsed`	`alnatura_receipt_parser` · `review`	`good` · `scaled_normalized`	`pytesseract+tesseract`
`2026-05-13_121809_auto_img_3342.png`	`.png`	`PNG`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-13_121809_auto_img_3342.png`	`.png`	`PNG`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131734_auto_img_3348.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131734_auto_img_3348.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131739_auto_img_3349.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131739_auto_img_3349.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-21_091259_auto_img_3349.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-21_091259_auto_img_3349.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-21_091405_auto_img_3350.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-21_091405_auto_img_3350.jpeg`	`.jpeg`	`MPO`	`image · dm · invoice`	`RGB→RGB`	yes	`True`	`dm`	ocr_parsed	`ocr_parsed`	`dm_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131727_auto_img_3347.jpeg`	`.jpeg`	`MPO`	`image · tegut · invoice`	`RGB→RGB`	yes	`True`	`tegut`	ocr_parsed	`ocr_parsed`	`tegut_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`
`2026-05-20_131727_auto_img_3347.jpeg`	`.jpeg`	`MPO`	`image · tegut · invoice`	`RGB→RGB`	yes	`True`	`tegut`	ocr_parsed	`ocr_parsed`	`tegut_receipt_parser` · `review`	`good` · `normalized_psm11`	`pytesseract+tesseract`