Spaces:
Sleeping
Sleeping
File size: 4,322 Bytes
d5841ad |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
"""
Text Detection Demo with Gradio
Extract text from images using OCR
"""
import gradio as gr
import cv2
import pytesseract
import numpy as np
from PIL import Image
import os
# Set Tesseract path (will be overridden in cloud deployment)
if os.path.exists(r'C:\Program Files\Tesseract-OCR\tesseract.exe'):
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
def extract_text_from_image(image):
"""
Extract text from an uploaded image
Args:
image: PIL Image or numpy array
Returns:
tuple: (processed_image, extracted_text)
"""
try:
# Convert PIL Image to numpy array if needed
if isinstance(image, Image.Image):
image = np.array(image)
# Convert RGB to BGR for OpenCV
if len(image.shape) == 3 and image.shape[2] == 3:
img = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
else:
img = image
# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Apply thresholding for better OCR
_, threshold = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# Extract text using Tesseract
text = pytesseract.image_to_string(threshold)
# Clean up the text
text = text.strip()
if not text:
text = "⚠️ No text detected in the image.\n\nTips:\n- Make sure the image contains clear text\n- Try an image with higher resolution\n- Ensure good contrast between text and background"
# Convert processed image back to RGB for display
processed_display = cv2.cvtColor(threshold, cv2.COLOR_GRAY2RGB)
return processed_display, text
except Exception as e:
error_msg = f"❌ Error processing image: {str(e)}\n\nPlease try another image."
return image, error_msg
# Create Gradio interface
with gr.Blocks(theme=gr.themes.Soft(), title="Text Detection Demo") as demo:
gr.Markdown(
"""
# 📝 Text Detection Demo
### Extract text from any image using OCR
Upload an image containing text, and the AI will extract all readable text from it.
Perfect for documents, screenshots, photos of signs, and more!
"""
)
with gr.Row():
with gr.Column():
input_image = gr.Image(
label="Upload Image",
type="pil",
height=400
)
extract_btn = gr.Button(
"🔍 Extract Text",
variant="primary",
size="lg"
)
gr.Markdown(
"""
### 💡 Tips for best results:
- Use clear, high-resolution images
- Ensure good lighting and contrast
- Avoid blurry or distorted text
- Works with printed and digital text
"""
)
with gr.Column():
output_image = gr.Image(
label="Processed Image (Thresholded)",
height=400
)
output_text = gr.Textbox(
label="Extracted Text",
lines=10,
placeholder="Extracted text will appear here...",
show_copy_button=True
)
# Example images section
gr.Markdown("### 📸 Try these examples:")
gr.Examples(
examples=[
["inputs/test1.jpg"] if os.path.exists("inputs/test1.jpg") else None,
["inputs/test2.jpg"] if os.path.exists("inputs/test2.jpg") else None,
],
inputs=input_image,
label="Sample Images"
)
# Connect the button to the function
extract_btn.click(
fn=extract_text_from_image,
inputs=input_image,
outputs=[output_image, output_text]
)
# Footer
gr.Markdown(
"""
---
Made with ❤️ using Gradio and Tesseract OCR
"""
)
# Launch the app
if __name__ == "__main__":
demo.launch(
share=True, # Creates a public shareable link
server_name="0.0.0.0", # Allow external connections
server_port=7860
)
|