Update app.py

app.py

@@ -1,40 +1,47 @@
 import gradio as gr
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 from PIL import Image
-import pytesseract  # Install using `pip install pytesseract` and ensure Tesseract is installed
+import pytesseract  # Install via `pip install pytesseract` and ensure Tesseract OCR is installed on your system
 
 # Load your fine-tuned model and tokenizer
 model_name = "quadranttechnologies/Receipt_Image_Analyzer"
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Define a function to preprocess the image and predict
-def analyze_receipt(image):
-    # Perform OCR to extract text from the image
-    extracted_text = pytesseract.image_to_string(image)
-    
-    # Tokenize the extracted text
-    inputs = tokenizer(extracted_text, return_tensors="pt", truncation=True, padding=True)
-    
-    # Get model predictions
+# Function to preprocess image and extract text using OCR
+def ocr_extract_text(image):
+    # Convert image to grayscale for better OCR accuracy
+    gray_image = image.convert("L")
+    # Use Tesseract OCR to extract text
+    extracted_text = pytesseract.image_to_string(gray_image)
+    return extracted_text
+
+# Define a function to analyze the receipt image
+def analyze_receipt_image(receipt_image):
+    # Extract text from the image
+    receipt_text = ocr_extract_text(receipt_image)
+    if not receipt_text.strip():
+        return {"error": "No text detected in the image."}
+
+    # Use the fine-tuned model to analyze the extracted text
+    inputs = tokenizer(receipt_text, return_tensors="pt", truncation=True, padding=True)
     outputs = model(**inputs)
     logits = outputs.logits
     predicted_class = logits.argmax(-1).item()
-    
-    # Optionally return extracted text and prediction as JSON
-    result = {
-        "extracted_text": extracted_text,
+
+    # Return the extracted text and predicted class as JSON
+    return {
+        "extracted_text": receipt_text,
         "predicted_class": predicted_class
     }
-    return result
 
 # Create a Gradio interface
 interface = gr.Interface(
-    fn=analyze_receipt,
-    inputs=gr.inputs.Image(type="pil"),  # Accept image input
-    outputs="json",  # Return JSON output
+    fn=analyze_receipt_image,
+    inputs=gr.Image(type="pil"),  # Updated to use gr.Image
+    outputs="json",  # Output will be displayed as JSON
     title="Receipt Image Analyzer",
-    description="Upload a receipt image to analyze and classify its contents.",
+    description="Upload an image of a receipt. The app extracts text and analyzes it using a fine-tuned LLM model.",
 )
 
 # Launch the Gradio app