Create app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+from transformers import pipeline
+import pytesseract
+import cv2
+from PIL import Image
+import numpy as np
+
+# -------------------------------------------------------------
+#  Load Model
+# -------------------------------------------------------------
+# Replace with your fine-tuned model on Hugging Face Hub
+MODEL_ID = "google/vit-base-patch16-224-in21k"
+
+classifier = pipeline("image-classification", model=MODEL_ID)
+
+# -------------------------------------------------------------
+#  Certificate Verification Function
+# -------------------------------------------------------------
+def verify_certificate(image):
+    # Convert to RGB if needed
+    if not isinstance(image, Image.Image):
+        image = Image.fromarray(image)
+    image = image.convert("RGB")
+
+    # 1️⃣ Model prediction
+    preds = classifier(image)
+    top_pred = preds[0]
+    label = top_pred["label"]
+    score = float(top_pred["score"])
+
+    # 2️⃣ OCR text extraction (optional but helpful)
+    img_np = np.array(image)
+    img_cv = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
+    gray = cv2.cvtColor(img_cv, cv2.COLOR_BGR2GRAY)
+    text = pytesseract.image_to_string(gray)
+
+    # 3️⃣ Combine result
+    result = {
+        "prediction": label,
+        "confidence": round(score, 4),
+        "text_preview": text[:300]
+    }
+    return result
+
+# -------------------------------------------------------------
+#  Gradio Interface
+# -------------------------------------------------------------
+demo = gr.Interface(
+    fn=verify_certificate,
+    inputs=gr.Image(type="numpy", label="Upload Certificate Image"),
+    outputs=gr.JSON(label="Verification Result"),
+    title="Fake Certificate Verification API 🧠",
+    description="Uploads a certificate image, runs an ML model to detect forgery, and extracts text for review.",
+)
+
+if __name__ == "__main__":
+    demo.launch()