initial commit

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+# Load the trained model
+model = tf.keras.models.load_model("prescription_model.h5")
+
+# Function to preprocess the uploaded image
+def preprocess_image(image):
+    image = image.convert("L")  # Convert to grayscale
+    image = image.resize((128, 128))  # Resize to match model input
+    image = np.array(image) / 255.0  # Normalize
+    image = np.expand_dims(image, axis=0)  # Add batch dimension
+    return image
+
+# Function to predict text from handwritten prescription
+def predict_text(image):
+    processed_image = preprocess_image(image)
+    prediction = model.predict(processed_image)
+    predicted_text = decode_prediction(prediction)  # Implement your decoding logic
+    return predicted_text
+
+# Placeholder function for decoding (depends on model architecture)
+def decode_prediction(prediction):
+    return "Decoded text (implement OCR logic)"
+
+# Gradio UI
+interface = gr.Interface(
+    fn=predict_text,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Handwritten Prescription OCR",
+    description="Upload a prescription image, and the model will return the recognized text."
+)
+
+if __name__ == "__main__":
+    interface.launch()

prescription_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd2afd1b1907c2397ae740a099d509e9332c98be069df3f3cc53f05eba972da
+size 29964376

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow
+gradio
+numpy
+pillow