alessandrocorradini/blood-examination-text-extraction-from-image

Text from complex image with Tesseract OCR

blood-examination-text-extraction-from-image's Issues

Example output using `tabulate`

Notify me using: @WK-GiHu

---

Note: Line RDW has a ocr failure *

Emocromo         con         con             formula
---------------  ----------  --------------  ----------------
Globuli Bianchi  7.50        migl./mme       ( 4.00 - 10.90 )
Globuli Rossi    4.75        mil./mmc        ( 4.50 — 5.90 )
Emoglobina       14.7        g/dl            ( 13,5 © 17,5)
Ematocrito       43.1        %               ( 41.0 - 53.0 )
MCV              90.6        fl              ( 80.0 - 99.0 )
MCH              30.9        pg              ( 26.0 - 36.0 )
MCHC             34.1        g/dl            ( 31.0 - 37.0 )
RDW              12.4 * cv%  (12.6 - 15.8 )
Piastrine        263         migl./mme       ( 150 - 450 )
MPV              8.8         fl              ( 6.3 - 12.5 )
Gr.Neutrofili    44.9        %
Linfociti        44.3        %
Monociti         7.8         %
Gr.Eosinofili    2.3         %
Gr.Basofili      0.7         %
Gr.Neutrofili    3.37        migl./mme       ( 1.80 - 7.70 )
Linfociti        3.32        migl./mmc       (1.00 - 4.50 )
Monociti         0.59        migl./mmc       ( 0.10 - 1.00 )
Gr.Eosinofili    0.17        migl./mmce      ( 0.04 - 0.40 )
Gr.Basofili      0.05        migl./mmc       (0 - 0.10 )

test.pdf

@AlessandroCorradini

https://github.com/AlessandroCorradini/Blood-Examination-Text-Extraction-from-Image/blob/master/test.pdf

This PDF does only embed the image referto-1.jpg into a PDF page. No OCR or converting at all, takes place.