I am not sure what you mean by "I have tried setting the Region of Interest
(ROI) ", but when I cut region and pre-processed it as described in the
documentation I got the correct results:
tesseract frame_1-ROI1_preprocessed.png - --psm 7
GOH SCE YUAN
tesseract frame_1-ROI2_preprocessed.png - --psm 4
0197782267
073351668
0197732267
Zdenko
st 28. 6. 2023 o 4:26 Lee Kar Yee <leekarye...@gmail.com> napísal(a):
> Hi,
>
> Apologies. Kindly refer to the following.
>
> With the following code, I managed to draw rectangle on the region that
> are processed by Tesseract OCR.
>
> pytesseract.pytesseract.tesseract_cmd = r"C:\Program
> Files\Tesseract-OCR\tesseract.exe"
>
> video = r"C:\Users\User\Downloads\FATHER\test.mp4"
> cap = cv2.VideoCapture(video)
> frame_count = 0
>
> while cap.isOpened() and frame_count < 2:
> ret, frame = cap.read()
>
> if not ret:
> break
>
> # Perform OCR on the entire frame without dictionaries
> text = pytesseract.image_to_string(frame, config='--psm 1 -l eng --oem
> 1')
>
> print(text)
>
> # Get the bounding box coordinates of the detected text regions
> boxes = pytesseract.image_to_boxes(frame, config='--psm 1 -l eng --oem
> 1')
>
> # Draw bounding box rectangles on the frame
> for box in boxes.splitlines():
> _, x, y, w, h, _ = box.split(' ')
> x, y, w, h = int(x), int(y), int(w), int(h)
> # Draw rectangles on the frame
> cv2.rectangle(frame, (x, y), (w, h), (0, 0, 255), 1)
>
> # Save the frame as an image
> cv2.imwrite(f"frame_{frame_count}.jpg", frame)
>
> frame_count += 1
>
> cap.release()
> cv2.destroyAllWindows()
>
> And the results are as below.
>
> ntes F-Farm Annlicatinns Service Reiest 9 Oar
>
> individual Name IDK
>
> GOH SCE YUAN 600
>
>
> nten F-Farm Annlicatinns Service Request «9 [or
>
> Individual Name IDK
>
> GOH SCE YUAN 600
>
> Kindly refer to the objective.jpg for what I actually intend to capture.
>
> Thanks,
>
> Lee
>
> On Tuesday, June 27, 2023 at 6:25:50 PM UTC+8 zdenop wrote:
>
>> without an example image nobody can help you.
>>
>> Zdenko
>>
>>
>> ut 27. 6. 2023 o 12:01 Lee Kar Yee <leeka...@gmail.com> napísal(a):
>>
>>> Hi all,
>>>
>>> I am new to Tesseract OCR. I am trying to achieve extracting alphabets
>>> and numbers from images.
>>> These images are being converted from a mp4 video into frames as JPG.
>>>
>>> While using Page segmentation method 3, it is working wonders on
>>> extracting alphabets, but it failed to extract numbers.
>>>
>>> I have tried setting the Region of Interest (ROI) but yet it still
>>> failed.
>>>
>>> Any thoughts or direction that can point me to so that I can improve it?
>>>
>>> Thanks,
>>>
>>> Lee
>>>
>>> --
>>> You received this message because you are subscribed to the Google
>>> Groups "tesseract-ocr" group.
>>> To unsubscribe from this group and stop receiving emails from it, send
>>> an email to tesseract-oc...@googlegroups.com.
>>> To view this discussion on the web visit
>>> https://groups.google.com/d/msgid/tesseract-ocr/67b453f2-7781-44a5-be05-05676d3ee5fan%40googlegroups.com
>>> <https://groups.google.com/d/msgid/tesseract-ocr/67b453f2-7781-44a5-be05-05676d3ee5fan%40googlegroups.com?utm_medium=email&utm_source=footer>
>>> .
>>>
>> --
> You received this message because you are subscribed to the Google Groups
> "tesseract-ocr" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to tesseract-ocr+unsubscr...@googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/tesseract-ocr/be985e79-79d0-41f9-8b14-139af74e94e9n%40googlegroups.com
> <https://groups.google.com/d/msgid/tesseract-ocr/be985e79-79d0-41f9-8b14-139af74e94e9n%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8yT%3Dr3g4USx0aP8LDMGCys%3DGTEak9TWo02_sPSszMEsJA%40mail.gmail.com.
