Create app.py

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+import easyocr
+import torch
+from transformers import pipeline
+import numpy as np
+
+# Load OCR model (English, Arabic, French, Chinese)
+reader = easyocr.Reader(['en', 'ar', 'fr', 'zh'])
+
+# Load YOLOv5 model (small model for faster performance)
+model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
+
+# Load translation model (multilingual to English)
+translator = pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en")
+
+def process_image(image):
+    # Convert PIL Image to numpy array if needed
+    if not isinstance(image, np.ndarray):
+        image = np.array(image)
+    
+    # Step 1: OCR - Text Extraction
+    text_results = reader.readtext(image)
+    extracted_texts = [res[1] for res in text_results]
+    extracted_text = " ".join(extracted_texts)
+
+    # Step 2: Translate Text
+    if extracted_text:
+        translation = translator(extracted_text)[0]['translation_text']
+    else:
+        translation = "No text detected."
+
+    # Step 3: Object Detection - Bounding Boxes
+    results = model(image)
+    detected_img = results.render()[0]  # returns a list, take first image
+
+    return detected_img, extracted_text, translation
+
+# Define Gradio Interface
+iface = gr.Interface(
+    fn=process_image,
+    inputs=gr.Image(type="pil", label="Upload Image (Signs, ID, License Plate)"),
+    outputs=[
+        gr.Image(label="Detected Objects in Image"),
+        gr.Textbox(label="Extracted Text"),
+        gr.Textbox(label="Translated Text to English")
+    ],
+    title="🚨 Police Smart Glasses AI Demo",
+    description="Upload an image to simulate smart glasses detecting text, translating it, and recognizing objects."
+)
+
+if __name__ == "__main__":
+    iface.launch()