Initial commit

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+import pytesseract
+from PIL import Image
+from paddleocr import PaddleOCR
+
+# Initialize PaddleOCR
+ocr = PaddleOCR(use_angle_cls=True, lang='en')
+
+def extract_text(image_path):
+    # Open the image file
+    image = Image.open(image_path).convert('L')
+
+    # Extract text using Tesseract OCR
+    tesseract_text = pytesseract.image_to_string(image)
+
+    # Extract text using PaddleOCR
+    paddle_results = ocr.ocr(image_path, cls=True)
+    paddle_text = "\n".join([line[1][0] for result in paddle_results for line in result])
+
+    # Return extracted text from both OCR engines
+    return f"📝 **Tesseract OCR Output:**\n{tesseract_text}\n\n🔍 **PaddleOCR Output:**\n{paddle_text}"
+
+# Create Gradio Interface
+demo = gr.Interface(
+    fn=extract_text,
+    inputs=gr.Image(type="filepath"),
+    outputs="text",
+    title="AI-Powered Image Text Extractor",
+    description="Upload an image containing text, and the AI will extract and display the text using both Tesseract and PaddleOCR.",
+)
+
+# Launch Gradio App
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+pytesseract
+pillow
+paddleocr
+paddlepaddle