পাইথনে বাংলা OCR – ইমেজ টু টেক্সট

pip install pytesseract

python -c "import pytesseract; print('pytesseract installed successfully!')"

tesseract --list-langs

import pytesseract
from PIL import Image

# Load the image
image_path = "bangla.png"  # Path to your image file
image = Image.open(image_path)

# Perform OCR on the image
text = pytesseract.image_to_string(image, lang="ben")  # 'ben' is the code for Bangla

# Print the extracted text
print("Extracted Text:")
print(text)

# Save the extracted text to a file
with open("extracted_bangla_text.txt", "w", encoding="utf-8") as file:
    file.write(text)

import os
import pytesseract
from PIL import Image

# Directory containing the images
image_dir = "path_to_your_directory"  # Replace with the path to your image directory

# Output text file to save OCR results
output_txt_file = "ocr_results.txt"

# Language for OCR (Bangla in this case)
ocr_language = "ben"  # Change to your desired language

# Open the output file in write mode
with open(output_txt_file, "w", encoding="utf-8") as output_file:
    # Iterate through all files in the directory
    for filename in os.listdir(image_dir):
        if filename.lower().endswith((".png", ".jpg", ".jpeg", ".tiff", ".bmp")):  # Supported image formats
            # Full path to the image
            image_path = os.path.join(image_dir, filename)

            # Load the image
            image = Image.open(image_path)

            # Perform OCR on the image
            extracted_text = pytesseract.image_to_string(image, lang=ocr_language)

            # Write the filename and extracted text to the output file
            output_file.write(f"File: {filename}\n")
            output_file.write(extracted_text)
            output_file.write("\n" + "=" * 50 + "\n")  # Separator for readability

            print(f"Processed: {filename}")  # Optional: Print progress

print(f"All OCR results saved to {output_txt_file}")

ocr_languages = "ben+eng"

pip install pdf2image

import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path("bangla.pdf")

# OCR with Bangla language
for i, image in enumerate(images):
    text = pytesseract.image_to_string(image, lang="ben")
    print(f"Page {i + 1}:\n{text}\n")

import pytesseract
from pdf2image import convert_from_path

# Path to your PDF file
pdf_path = "bangla.pdf"

# Output text file path
output_txt_path = "output.txt"

# Convert the PDF to images
images = convert_from_path(pdf_path)

# Open a text file for writing in Unicode format
with open(output_txt_path, "w", encoding="utf-8") as file:
    for i, image in enumerate(images):
        # Perform OCR on each page
        text = pytesseract.image_to_string(image, lang="ben")  # 'ben' for Bangla language
        # Write the page number and extracted text to the file
        file.write(f"Page {i + 1}:\n")
        file.write(text)
        file.write("\n" + "="*50 + "\n")  # Separator between pages

print(f"Bangla text extracted and saved to {output_txt_path}")

conda create -n orc python=3.12

conda activate ocr

conda install -c conda-forge pytesseract

import pytesseract
from PIL import Image

# Load the image
image_path = "bangla.png"  # Path to your image file
image = Image.open(image_path)

# Perform OCR on the image
text = pytesseract.image_to_string(image, lang="ben")  # 'ben' is the code for Bangla

# Print the extracted text
print("Extracted Text:")
print(text)

conda install -c conda-forge tesseract-data-ben