Re: [tesseract-ocr] Cannt extract number from image screenshot

2024-04-29 Thread Master - Event
i try invert color, white to black, try enchance image sharpness, contracst, convert color grb, gray, config pytesseract lang, page segmentation method, OCR engine mode but it not work :( Vào lúc 21:19:34 UTC+2 ngày Thứ Hai, 29 tháng 4, 2024, zdenop đã viết: > First, show us that you tried

Re: [tesseract-ocr] Re: Textbook-like format. Correcting improperly recognized text

2024-04-29 Thread Misti Hamon
"Regarding proofreading with Scribe OCR, it is definitely possible to zoom in. The controls are virtually identical to popular document viewer programs like Acrobat. You can zoom in on the current location of the mouse using Control + Mouse Wheel, scroll using the mouse wheel, and pan in all

Re: [tesseract-ocr] Cannt extract number from image screenshot

2024-04-29 Thread Zdenko Podobny
First, show us that you tried everything from the documentation. Zdenko po 29. 4. 2024 o 21:16 Master - Event napísal(a): > i try extract number from screenshot but i cannt. someone help me why. > my code ``` > img_data = base64.b64decode(screenshot) > image_pil =

[tesseract-ocr] Cannt extract number from image screenshot

2024-04-29 Thread Master - Event
i try extract number from screenshot but i cannt. someone help me why. my code ``` img_data = base64.b64decode(screenshot) image_pil = Image.open(BytesIO(img_data)) box = (0, 222, 80, 240) cropped_img = image_pil.crop(box) image_cv2 = np.array(cropped_img) image_cv2 = cv2.cvtColor(image_cv2,

[tesseract-ocr] Re: Textbook-like format. Correcting improperly recognized text

2024-04-29 Thread Jeremiah
Regarding proofreading with Scribe OCR , it is definitely possible to zoom in. The controls are virtually identical to popular document viewer programs like Acrobat. You can zoom in on the current location of the mouse using Control + Mouse Wheel, scroll using the

[tesseract-ocr] Textbook-like format. Correcting improperly recognized text

2024-04-29 Thread Misti Hamon
Forgive me, I have lots of questions and will be trying to separate out one question per conversation (so that those searching later may more easily find the answers). I'm working with scanned images of a textbook like layout - occasional drop-caps, text in 2 or occasionally 3 columns that

Re: [tesseract-ocr] hOCR verification and editing plus non-word characters

2024-04-29 Thread Misti Hamon
Thank you for your reply, and please forgive my delay, it took me much longer to finish preprocessing my images than I anticipated (actually, was lead to believe it would take - but probably because I'm working with a textbook type layout and not a novel type layout right now). To confirm, you