Editing Ai Accessibility (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''AI image description for screen readers:'''
<syntaxhighlight lang="python">
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import requests
import pyttsx3  # Text-to-speech for screen reader output

# BLIP-2 image captioning model for accessibility
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained(
    "Salesforce/blip-image-captioning-large"
).to("cuda")

def describe_image_for_accessibility(image_path: str) -> str:
    """Generate detailed image description for blind users."""
    image = Image.open(image_path).convert("RGB")
    # Unconditional captioning
    inputs = processor(image, return_tensors="pt").to("cuda")
    out = model.generate(**inputs, max_new_tokens=200, num_beams=5)
    base_description = processor.decode(out[0], skip_special_tokens=True)
    # Conditional probing for specific attributes
    questions = [
        ("How many people are in this image?", "people count"),
        ("What colors are prominent?", "colors"),
        ("Is there any text visible in the image?", "text"),
    ]
    details = []
    for question, aspect in questions:
        q_input = processor(image, question, return_tensors="pt").to("cuda")
        out = model.generate(**q_input, max_new_tokens=50)
        answer = processor.decode(out[0], skip_special_tokens=True)
        details.append(f"{aspect}: {answer}")
    return f"{base_description}. Details: {', '.join(details)}"

# Screen reader output
tts = pyttsx3.init()
description = describe_image_for_accessibility("photo.jpg")
tts.say(description)
tts.runAndWait()
</syntaxhighlight>
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">