How to keep Only Black color text in the image using OpenCV Python?

Question

I have the following image:

.

I want to keep only the black colored text 0790 and remove all from the picture. This stackoverflow question teaches to remove the color. However, I need to keep the color, not remove it.

Answer 1

You can simply use a threshold to filter out colored parts:

from PIL import Image

image = Image.open("xyz.jpeg")
image_data = image.load()
height, width = image.size
# Define a threshold for blackness
threshold = 60
for x in range(height):
    for y in range(width):
        r, g, b = image_data[x, y]
        # Check if the pixel is close to black
        if r < threshold and g < threshold and b < threshold:
            image_data[x, y] = (0, 0, 0)  # Keep it black
        else:
            image_data[x, y] = (255, 255, 255)  # Change to white or any background color

After removing color:

from paddleocr import PaddleOCR
numpydata = np.asarray(image)
recognition_result = ocr_engine.ocr(numpydata, cls=True)
recognition_text = get_ocr_text(recognition_result)

You can also use PaddleOCR to extract text if you: recognition_result = 0790

# helper function 
def get_ocr_text(recognition_result):
    txts = []    
    for result in recognition_result:
        if result is not None:
            txts.extend(line[1][0] for line in result)
    return " ".join(txts).strip()