import gradio as gr import numpy as np import pytesseract from PIL import Image, ImageEnhance, ImageFilter import pandas as pd import re import json import os import random import datetime import matplotlib.pyplot as plt import seaborn as sns import cv2 import requests from io import BytesIO # Load nutrition database with expanded items def load_nutrition_data(): # Enhanced food database with more items and categories food_data = { # Fast food and restaurant items "pizza": {"calories": 285, "fat": 10, "carbs": 36, "protein": 12, "category": "junk"}, "burger": {"calories": 354, "fat": 17, "carbs": 40, "protein": 15, "category": "junk"}, "cheeseburger": {"calories": 400, "fat": 20, "carbs": 40, "protein": 15, "category": "junk"}, "hamburger": {"calories": 350, "fat": 15, "carbs": 40, "protein": 15, "category": "junk"}, "fries": {"calories": 312, "fat": 15, "carbs": 41, "protein": 3, "category": "junk"}, "french fries": {"calories": 312, "fat": 15, "carbs": 41, "protein": 3, "category": "junk"}, "salad": {"calories": 100, "fat": 7, "carbs": 5, "protein": 2, "category": "healthy"}, "caesar salad": {"calories": 150, "fat": 10, "carbs": 5, "protein": 3, "category": "healthy"}, "garden salad": {"calories": 80, "fat": 5, "carbs": 5, "protein": 2, "category": "healthy"}, "soda": {"calories": 140, "fat": 0, "carbs": 39, "protein": 0, "category": "junk"}, "coke": {"calories": 140, "fat": 0, "carbs": 39, "protein": 0, "category": "junk"}, "pepsi": {"calories": 150, "fat": 0, "carbs": 41, "protein": 0, "category": "junk"}, "sprite": {"calories": 140, "fat": 0, "carbs": 38, "protein": 0, "category": "junk"}, "cola": {"calories": 140, "fat": 0, "carbs": 39, "protein": 0, "category": "junk"}, "diet coke": {"calories": 0, "fat": 0, "carbs": 0, "protein": 0, "category": "neutral"}, "juice": {"calories": 110, "fat": 0, "carbs": 26, "protein": 0, "category": "neutral"}, "orange juice": {"calories": 110, "fat": 0, "carbs": 26, "protein": 0, "category": "neutral"}, "apple juice": {"calories": 115, "fat": 0, "carbs": 28, "protein": 0, "category": "neutral"}, "water": {"calories": 0, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, "sparkling water": {"calories": 0, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, "pasta": {"calories": 200, "fat": 2, "carbs": 42, "protein": 7, "category": "neutral"}, "spaghetti": {"calories": 220, "fat": 2, "carbs": 43, "protein": 8, "category": "neutral"}, "pasta carbonara": {"calories": 380, "fat": 18, "carbs": 43, "protein": 14, "category": "neutral"}, "fettuccine": {"calories": 220, "fat": 2, "carbs": 43, "protein": 8, "category": "neutral"}, "lasagna": {"calories": 360, "fat": 12, "carbs": 37, "protein": 25, "category": "neutral"}, "mac and cheese": {"calories": 350, "fat": 15, "carbs": 45, "protein": 15, "category": "neutral"}, "macaroni": {"calories": 200, "fat": 2, "carbs": 42, "protein": 7, "category": "neutral"}, "steak": {"calories": 300, "fat": 15, "carbs": 0, "protein": 30, "category": "protein"}, "ribeye": {"calories": 330, "fat": 25, "carbs": 0, "protein": 30, "category": "protein"}, "filet mignon": {"calories": 320, "fat": 20, "carbs": 0, "protein": 35, "category": "protein"}, "sirloin": {"calories": 270, "fat": 12, "carbs": 0, "protein": 32, "category": "protein"}, "chicken": {"calories": 220, "fat": 8, "carbs": 0, "protein": 40, "category": "protein"}, "chicken wings": {"calories": 350, "fat": 18, "carbs": 5, "protein": 33, "category": "protein"}, "chicken tenders": {"calories": 380, "fat": 20, "carbs": 20, "protein": 30, "category": "protein"}, "grilled chicken": {"calories": 220, "fat": 8, "carbs": 0, "protein": 40, "category": "protein"}, "fried chicken": {"calories": 320, "fat": 16, "carbs": 12, "protein": 28, "category": "protein"}, "fish": {"calories": 180, "fat": 5, "carbs": 0, "protein": 30, "category": "healthy"}, "salmon": {"calories": 200, "fat": 10, "carbs": 0, "protein": 25, "category": "healthy"}, "tuna": {"calories": 160, "fat": 3, "carbs": 0, "protein": 33, "category": "healthy"}, "cod": {"calories": 150, "fat": 2, "carbs": 0, "protein": 28, "category": "healthy"}, "rice": {"calories": 130, "fat": 0, "carbs": 28, "protein": 3, "category": "neutral"}, "brown rice": {"calories": 110, "fat": 1, "carbs": 22, "protein": 3, "category": "healthy"}, "white rice": {"calories": 130, "fat": 0, "carbs": 28, "protein": 3, "category": "neutral"}, "fried rice": {"calories": 230, "fat": 10, "carbs": 28, "protein": 8, "category": "neutral"}, #Indian Food Items "butter chicken": {"calories": 450, "fat": 28, "carbs": 14, "protein": 32, "category": "protein"}, "chole bhature": {"calories": 550, "fat": 30, "carbs": 50, "protein": 14, "category": "junk"}, "dal makhani": {"calories": 320, "fat": 18, "carbs": 24, "protein": 14, "category": "neutral"}, "rajma chawal": {"calories": 410, "fat": 10, "carbs": 60, "protein": 15, "category": "neutral"}, "paneer butter masala": {"calories": 430, "fat": 30, "carbs": 20, "protein": 18, "category": "protein"}, "tandoori chicken": {"calories": 290, "fat": 13, "carbs": 4, "protein": 35, "category": "protein"}, "biryani": {"calories": 480, "fat": 20, "carbs": 55, "protein": 18, "category": "neutral"}, "veg biryani": {"calories": 400, "fat": 15, "carbs": 50, "protein": 10, "category": "neutral"}, "chicken biryani": {"calories": 500, "fat": 20, "carbs": 55, "protein": 22, "category": "protein"}, "aloo paratha": {"calories": 300, "fat": 12, "carbs": 40, "protein": 7, "category": "neutral"}, "samosa": {"calories": 260, "fat": 15, "carbs": 25, "protein": 5, "category": "junk"}, "masala dosa": {"calories": 390, "fat": 15, "carbs": 50, "protein": 8, "category": "neutral"}, "idli sambar": {"calories": 270, "fat": 6, "carbs": 45, "protein": 10, "category": "healthy"}, "pav bhaji": {"calories": 420, "fat": 22, "carbs": 40, "protein": 8, "category": "junk"}, "poha": {"calories": 250, "fat": 10, "carbs": 35, "protein": 5, "category": "healthy"}, "upma": {"calories": 240, "fat": 8, "carbs": 34, "protein": 6, "category": "healthy"}, "chana masala": {"calories": 280, "fat": 12, "carbs": 30, "protein": 12, "category": "protein"}, "fish curry": {"calories": 310, "fat": 18, "carbs": 12, "protein": 25, "category": "protein"}, "mutton curry": {"calories": 500, "fat": 35, "carbs": 10, "protein": 30, "category": "protein"}, "kadai paneer": {"calories": 380, "fat": 25, "carbs": 18, "protein": 15, "category": "protein"}, "malai kofta": {"calories": 440, "fat": 30, "carbs": 25, "protein": 12, "category": "junk"}, "dal tadka": {"calories": 280, "fat": 10, "carbs": 30, "protein": 12, "category": "healthy"}, "aloo methi": {"calories": 200, "fat": 10, "carbs": 18, "protein": 6, "category": "healthy"}, "phulka": {"calories": 90, "fat": 2, "carbs": 18, "protein": 3, "category": "healthy"}, "butter naan": {"calories": 300, "fat": 10, "carbs": 40, "protein": 6, "category": "junk"}, "tandoori roti": {"calories": 120, "fat": 2, "carbs": 22, "protein": 4, "category": "healthy"}, "mineral water": {"calories": 0, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, "Chicken Tikka Masala": {"calories": 480, "fat": 28, "carbs": 16, "protein": 35, "category": "protein"}, "mutton biryani": {"calories": 550, "fat": 25, "carbs": 50, "protein": 30, "category": "protein"}, "garlic naan": {"calories": 160, "fat": 5, "carbs": 28, "protein": 4, "category": "neutral"}, "garlic naan (2 pcs)": {"calories": 320, "fat": 10, "carbs": 56, "protein": 8, "category": "neutral"}, "butter naan (2 pcs)": {"calories": 600, "fat": 20, "carbs": 80, "protein": 12, "category": "junk"}, "jeera rice": {"calories": 210, "fat": 5, "carbs": 35, "protein": 4, "category": "neutral"}, "papadum": {"calories": 40, "fat": 2, "carbs": 4, "protein": 1, "category": "neutral"}, "papadum": {"calories": 160, "fat": 8, "carbs": 16, "protein": 4, "category": "neutral"}, "mixed raita": {"calories": 100, "fat": 5, "carbs": 10, "protein": 3, "category": "healthy"}, "gulab jamun": {"calories": 150, "fat": 7, "carbs": 25, "protein": 3, "category": "junk"}, "gulab jamun 4 pcs": {"calories": 600, "fat": 28, "carbs": 100, "protein": 12, "category": "junk"}, "masala chai": {"calories": 80, "fat": 3, "carbs": 10, "protein": 2, "category": "neutral"}, "masala chai 4 cups": {"calories": 320, "fat": 12, "carbs": 40, "protein": 8, "category": "neutral"}, "pongal": {"calories": 320, "fat": 12, "carbs": 40, "protein": 7, "category": "neutral"}, "medu vadai": {"calories": 150, "fat": 8, "carbs": 15, "protein": 4, "category": "junk"}, "sambhar idly": {"calories": 270, "fat": 6, "carbs": 40, "protein": 10, "category": "healthy"}, "poori": {"calories": 150, "fat": 8, "carbs": 18, "protein": 3, "category": "junk"}, "ghee roast": {"calories": 450, "fat": 25, "carbs": 45, "protein": 7, "category": "junk"}, "tea": {"calories": 50, "fat": 2, "carbs": 5, "protein": 1, "category": "neutral"}, "dal makhani": {"calories": 320, "fat": 18, "carbs": 24, "protein": 14, "category": "neutral"}, "mixed raita": {"calories": 100, "fat": 5, "carbs": 10, "protein": 3, "category": "healthy"}, "gulab jamun": {"calories": 150, "fat": 7, "carbs": 25, "protein": 3, "category": "junk"}, "masala chai": {"calories": 80, "fat": 3, "carbs": 10, "protein": 2, "category": "neutral"}, "mutton biryani": {"calories": 550, "fat": 25, "carbs": 50, "protein": 30, "category": "protein"}, # Drinks "beer": {"calories": 154, "fat": 0, "carbs": 13, "protein": 1, "category": "junk"}, "wine": {"calories": 125, "fat": 0, "carbs": 4, "protein": 0, "category": "neutral"}, "red wine": {"calories": 125, "fat": 0, "carbs": 4, "protein": 0, "category": "neutral"}, "white wine": {"calories": 120, "fat": 0, "carbs": 4, "protein": 0, "category": "neutral"}, "cocktail": {"calories": 180, "fat": 0, "carbs": 20, "protein": 0, "category": "junk"}, "margarita": {"calories": 200, "fat": 0, "carbs": 25, "protein": 0, "category": "junk"}, "daiquiri": {"calories": 180, "fat": 0, "carbs": 20, "protein": 0, "category": "junk"}, "mojito": {"calories": 160, "fat": 0, "carbs": 18, "protein": 0, "category": "junk"}, "martini": {"calories": 120, "fat": 0, "carbs": 3, "protein": 0, "category": "neutral"}, "coffee": {"calories": 5, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, "latte": {"calories": 120, "fat": 4, "carbs": 10, "protein": 8, "category": "neutral"}, "cappuccino": {"calories": 110, "fat": 4, "carbs": 8, "protein": 6, "category": "neutral"}, "espresso": {"calories": 5, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, # Desserts "ice cream": {"calories": 207, "fat": 11, "carbs": 24, "protein": 4, "category": "junk"}, "cake": {"calories": 350, "fat": 18, "carbs": 45, "protein": 4, "category": "junk"}, "chocolate cake": {"calories": 370, "fat": 19, "carbs": 48, "protein": 5, "category": "junk"}, "cheesecake": {"calories": 400, "fat": 25, "carbs": 35, "protein": 7, "category": "junk"}, "tiramisu": {"calories": 380, "fat": 20, "carbs": 40, "protein": 5, "category": "junk"}, "brownie": {"calories": 300, "fat": 15, "carbs": 40, "protein": 3, "category": "junk"}, "cookie": {"calories": 180, "fat": 9, "carbs": 22, "protein": 2, "category": "junk"}, "chocolate": {"calories": 200, "fat": 12, "carbs": 20, "protein": 2, "category": "junk"}, "pie": {"calories": 300, "fat": 14, "carbs": 38, "protein": 3, "category": "junk"}, "apple pie": {"calories": 290, "fat": 14, "carbs": 40, "protein": 3, "category": "junk"}, "pudding": {"calories": 150, "fat": 4, "carbs": 25, "protein": 3, "category": "junk"}, # Other common items "sandwich": {"calories": 250, "fat": 8, "carbs": 30, "protein": 15, "category": "neutral"}, "wrap": {"calories": 220, "fat": 5, "carbs": 30, "protein": 13, "category": "neutral"}, "soup": {"calories": 120, "fat": 3, "carbs": 12, "protein": 10, "category": "healthy"}, "bread": {"calories": 80, "fat": 1, "carbs": 15, "protein": 3, "category": "neutral"}, "garlic bread": {"calories": 150, "fat": 6, "carbs": 18, "protein": 4, "category": "neutral"}, "roll": {"calories": 80, "fat": 1, "carbs": 15, "protein": 3, "category": "neutral"}, "milkshake": {"calories": 300, "fat": 10, "carbs": 50, "protein": 9, "category": "junk"}, "dessert": {"calories": 280, "fat": 14, "carbs": 35, "protein": 5, "category": "junk"}, "smoothie": {"calories": 170, "fat": 2, "carbs": 35, "protein": 5, "category": "neutral"}, "tea": {"calories": 2, "fat": 0, "carbs": 0, "protein": 0, "category": "healthy"}, "appetizer": {"calories": 200, "fat": 12, "carbs": 15, "protein": 8, "category": "neutral"}, "noodles": {"calories": 190, "fat": 2, "carbs": 40, "protein": 7, "category": "neutral"}, "taco": {"calories": 210, "fat": 10, "carbs": 22, "protein": 12, "category": "neutral"}, "burrito": {"calories": 350, "fat": 12, "carbs": 50, "protein": 15, "category": "neutral"}, "nachos": {"calories": 600, "fat": 35, "carbs": 58, "protein": 20, "category": "junk"}, "fajitas": {"calories": 290, "fat": 10, "carbs": 30, "protein": 25, "category": "neutral"}, "quesadilla": {"calories": 400, "fat": 22, "carbs": 35, "protein": 18, "category": "neutral"}, "eggs": {"calories": 140, "fat": 10, "carbs": 1, "protein": 12, "category": "protein"}, "omelette": {"calories": 220, "fat": 16, "carbs": 2, "protein": 16, "category": "protein"}, "pancakes": {"calories": 380, "fat": 12, "carbs": 60, "protein": 10, "category": "neutral"}, "waffles": {"calories": 370, "fat": 14, "carbs": 55, "protein": 8, "category": "neutral"}, "toast": {"calories": 80, "fat": 1, "carbs": 15, "protein": 3, "category": "neutral"}, "muffin": {"calories": 210, "fat": 10, "carbs": 30, "protein": 3, "category": "junk"}, "croissant": {"calories": 230, "fat": 12, "carbs": 26, "protein": 5, "category": "neutral"}, "doughnut": {"calories": 250, "fat": 12, "carbs": 30, "protein": 4, "category": "junk"}, "donut": {"calories": 250, "fat": 12, "carbs": 30, "protein": 4, "category": "junk"}, "bagel": {"calories": 245, "fat": 1, "carbs": 48, "protein": 10, "category": "neutral"}, "scone": {"calories": 230, "fat": 12, "carbs": 28, "protein": 4, "category": "neutral"}, # Side dishes "onion rings": {"calories": 320, "fat": 18, "carbs": 35, "protein": 5, "category": "junk"}, "mashed potatoes": {"calories": 150, "fat": 4, "carbs": 25, "protein": 3, "category": "neutral"}, "baked potato": {"calories": 130, "fat": 0, "carbs": 30, "protein": 3, "category": "neutral"}, "coleslaw": {"calories": 120, "fat": 8, "carbs": 10, "protein": 1, "category": "neutral"}, "corn": {"calories": 90, "fat": 1, "carbs": 20, "protein": 3, "category": "healthy"}, "broccoli": {"calories": 40, "fat": 0, "carbs": 8, "protein": 4, "category": "healthy"}, "veggies": {"calories": 50, "fat": 0, "carbs": 10, "protein": 2, "category": "healthy"}, "vegetables": {"calories": 50, "fat": 0, "carbs": 10, "protein": 2, "category": "healthy"}, "chips": {"calories": 300, "fat": 15, "carbs": 35, "protein": 3, "category": "junk"}, } return food_data # Load nutrition database nutrition_data = load_nutrition_data() # Load motivational quotes based on health score ranges def load_motivational_quotes(): quotes = { "excellent": [ "You're making excellent food choices! Your body thanks you for the premium fuel.", "Fantastic choices! You're investing in your long-term health with every bite.", "Your healthy eating habits today are building your stronger body for tomorrow.", "Impressive meal choices! You're mastering the art of nutritious eating.", "You're a nutrition champion! These balanced choices will energize your day." ], "good": [ "Good job balancing nutrition! Small improvements can take you to the next level.", "You're on the right track with your food choices. Keep building those healthy habits!", "Nice work choosing a fairly balanced meal. Your body appreciates the consideration.", "Your meal choices show you care about your health. Keep that momentum going!", "Good balance of nutrients in this meal. Remember: consistency is key to health." ], "moderate": [ "This meal has some nutritional bright spots. Consider adding more protein next time.", "Balance is a journey. Try adding more vegetables to your next meal.", "Everyone indulges sometimes. Tomorrow is a new opportunity for nourishing choices.", "Consider this meal a starting point. Small improvements add up to big health benefits.", "Moderation is key. Try balancing this meal with healthier choices later today." ], "poor": [ "Your body deserves premium fuel. Consider more nutrient-dense options next time.", "One meal doesn't define your health journey. Your next choice can be a healthier one.", "We all have indulgences. Balance this meal with nutritious choices for your next one.", "Small steps lead to big changes. Consider adding vegetables to your next meal.", "Remember: food is fuel. Choose options that will energize rather than drain you." ] } return quotes # Initialize motivational quotes motivational_quotes = load_motivational_quotes() # Helper function to preprocess the image for better OCR results def preprocess_image(image): # Convert to numpy array if needed if not isinstance(image, np.ndarray): image = np.array(image) try: # Ensure the image is in RGB format (3 channels) if len(image.shape) == 2: # Grayscale image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB) elif len(image.shape) == 3 and image.shape[2] == 4: # RGBA image = cv2.cvtColor(image, cv2.COLOR_RGBA2RGB) # Convert to grayscale gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # Apply multiple preprocessing techniques and keep the best result results = [] # Technique 1: Adaptive thresholding thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2) results.append(thresh) # Technique 2: Otsu's thresholding after Gaussian filtering blur = cv2.GaussianBlur(gray, (5, 5), 0) _, otsu = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) results.append(otsu) # Technique 3: Histogram equalization equalized = cv2.equalizeHist(gray) results.append(equalized) # Technique 4: Original grayscale results.append(gray) # Convert all results to PIL images pil_images = [Image.fromarray(img) for img in results] return pil_images except Exception as e: print(f"Error preprocessing image: {e}") # If preprocessing fails, return the original image as a list return [Image.fromarray(image) if isinstance(image, np.ndarray) else image] # OCR function to extract text from bill image with enhanced image processing def extract_text_from_image(image): try: # If image is a URL, download it if isinstance(image, str) and (image.startswith('http://') or image.startswith('https://')): response = requests.get(image) img = Image.open(BytesIO(response.content)) else: img = Image.fromarray(image) if isinstance(image, np.ndarray) else image # Create a copy for display display_img = img.copy() if hasattr(img, 'copy') else img # Preprocess the image to get multiple versions preprocessed_images = preprocess_image(img) # Try OCR on each preprocessed image best_text = "" # Custom configs to try configs = [ r'--oem 3 --psm 6 -l eng', # Assume a single uniform block of text r'--oem 3 --psm 4 -l eng', # Assume a single column of text r'--oem 3 --psm 3 -l eng', # Fully automatic page segmentation r'--oem 3 --psm 11 -l eng', # Sparse text - no specific structure r'--oem 3 --psm 12 -l eng', # Sparse text with OSD ] for img_version in preprocessed_images: for config in configs: try: text = pytesseract.image_to_string(img_version, config=config) # Keep the longest text as it likely contains more information if len(text.strip()) > len(best_text.strip()): best_text = text except Exception as e: print(f"OCR error with specific config: {str(e)}") continue # If all attempts failed or returned very little text if len(best_text.strip()) < 10: # Try one last attempt with default settings try: best_text = pytesseract.image_to_string(img) except Exception as e: print(f"Final OCR attempt error: {str(e)}") # Debug output print(f"OCR extracted text of length: {len(best_text)}") return best_text except Exception as e: print(f"Error extracting text: {str(e)}") return f"Error extracting text: {str(e)}" # Extract food items from the OCR text with improved pattern recognition def extract_food_items(text): # Improved algorithm to detect food items in bill text lines = text.split('\n') food_items = [] # Debug info print(f"Processing {len(lines)} lines of text") # Clean and normalize all lines first cleaned_lines = [] for line in lines: # Remove common non-food text line = re.sub(r'thank you|receipt|invoice|order|table|server', '', line.lower(), flags=re.IGNORECASE) cleaned_lines.append(line.strip()) # Regular patterns for food items in bills # More comprehensive price pattern to catch various formats price_pattern = r'(\$?\d+\.\d{2}|\$?\d+\,\d{2}|\$?\d+)' for line in cleaned_lines: if not line: continue # Skip lines that look like totals or headers skip_keywords = [ 'total', 'subtotal', 'tax', 'gratuity', 'tip', 'service', 'amount', 'due', 'change', 'cash', 'credit', 'card', 'payment', 'date', 'time', 'check', 'table', 'guest', 'invoice', 'receipt', 'bill', 'order', 'tel', 'phone', 'address', 'thank you', 'restaurant', 'cafe', 'bar', 'grill', 'kitchen', 'www', 'http' ] if any(keyword in line.lower() for keyword in skip_keywords): continue # Debug line print(f"Processing line: '{line}'") # If line contains a price, extract the item name (everything before the price) if re.search(price_pattern, line): # Split based on number patterns (likely price) item_parts = re.split(price_pattern, line) if item_parts and len(item_parts) > 1: item_match = item_parts[0].strip() if item_match and len(item_match) > 1: # Ensure it's not just whitespace # Clean up the item name (remove quantities, etc.) cleaned_item = re.sub(r'^\d+\s*[xX]?\s*', '', item_match) # Remove quantities like "2 x" or "2" cleaned_item = re.sub(r'\d+\s*oz\s*', '', cleaned_item) # Remove sizes like "12oz" cleaned_item = re.sub(r'\(\w+\)', '', cleaned_item) # Remove parentheses # Filter out very short items that are likely not food if len(cleaned_item.strip()) > 2: food_items.append(cleaned_item.strip().lower()) print(f"Found item with price: '{cleaned_item.strip().lower()}'") # If not enough items found, try alternate methods if len(food_items) < 2: # Look for menu-like patterns for line in cleaned_lines: # Try to find numbered items (e.g., "1. Burger" or "#1 Burger") numbered_pattern = r'(?:^|\s)(?:\d+\.|\#\d+)\s+(.+?)(?:\s+\$|\s+\d|\s*$)' match = re.search(numbered_pattern, line) if match: item = match.group(1).strip().lower() if len(item) > 2 and item not in food_items: food_items.append(item) print(f"Found numbered item: '{item}'") # Simple heuristic: look for capitalized words that might be menu items # This is a fallback when we're struggling to find items if len(line) > 3 and not any(char.isdigit() for char in line) and not any(skip in line for skip in skip_keywords): potential_item = re.sub(r'\W+', ' ', line).strip().lower() # Check if the line contains any known food items for food in nutrition_data.keys(): if food in potential_item: if potential_item not in food_items: food_items.append(potential_item) print(f"Found potential food item: '{potential_item}'") break # If we still have no items, use a more aggressive approach to find any words # that match our food database if len(food_items) < 2: print("Using aggressive food item detection...") # Flatten all text and clean it all_text = ' '.join(cleaned_lines).lower() # Filter out non-alphanumeric characters all_text = re.sub(r'[^\w\s]', ' ', all_text) # Get all words words = all_text.split() # Look for any word or pair of words that matches our food database for i in range(len(words)): # Single word match if words[i] in nutrition_data: food_items.append(words[i]) print(f"Found direct food match: '{words[i]}'") # Two-word match if i < len(words) - 1: two_words = words[i] + ' ' + words[i+1] if two_words in nutrition_data: food_items.append(two_words) print(f"Found direct two-word food match: '{two_words}'") # If we've exhausted all options but still have no items, try to find words # that are similar to our food database if len(food_items) < 2: print("Using similarity-based food item detection...") all_text = ' '.join(cleaned_lines).lower() words = re.findall(r'\b[a-z]{3,}\b', all_text) # Find all words with at least 3 letters for word in words: # Skip very common words if word in ['the', 'and', 'for', 'with', 'that', 'have', 'this', 'from']: continue # Check if the word is a substring of any food in our database for food in nutrition_data.keys(): if word in food: food_items.append(food) print(f"Found similar food item: '{food}' from '{word}'") break # Remove duplicates and limit to reasonable number food_items = list(set(food_items))[:10] print(f"Final food items extracted: {food_items}") return food_items # Match extracted food items to our nutrition database with improved fuzzy matching def match_food_to_nutrition(food_items): matched_items = [] for item in food_items: # Direct match if item in nutrition_data: matched_items.append({"name": item, "nutrition": nutrition_data[item]}) continue # Improved matching logic - word-based matching and ngram similarity best_match = None max_score = 0 # Split the item into words for better matching item_words = set(item.split()) for db_food in nutrition_data: # Calculate word overlap db_food_words = set(db_food.split()) if item_words and db_food_words: overlap = len(item_words.intersection(db_food_words)) score = overlap / max(len(item_words), len(db_food_words)) # Boost score if one string contains the other if db_food in item or item in db_food: score += 0.3 if score > max_score: max_score = score best_match = db_food # Only match if the score is reasonably high if best_match and max_score > 0.3: matched_items.append({"name": item, "matched_as": best_match, "nutrition": nutrition_data[best_match]}) # Remove duplicates (based on matched_as) unique_matches = [] seen_matches = set() for item in matched_items: match_key = item.get("matched_as", item["name"]) if match_key not in seen_matches: unique_matches.append(item) seen_matches.add(match_key) return unique_matches # Calculate nutritional totals and health # Calculate nutritional totals and health score def calculate_meal_health(matched_items): if not matched_items: return None, None, "No food items detected" # Calculate total nutrition total_calories = sum(item["nutrition"]["calories"] for item in matched_items) total_fat = sum(item["nutrition"]["fat"] for item in matched_items) total_carbs = sum(item["nutrition"]["carbs"] for item in matched_items) total_protein = sum(item["nutrition"]["protein"] for item in matched_items) # Count items by category category_counts = {"healthy": 0, "neutral": 0, "protein": 0, "junk": 0} for item in matched_items: category = item["nutrition"]["category"] category_counts[category] = category_counts.get(category, 0) + 1 # Calculate health score (0-100) total_items = len(matched_items) health_score = 0 # Point system: # - Healthy items: +25 points each # - Protein items: +15 points each # - Neutral items: +5 points each # - Junk items: -10 points each # Base score of 50 health_score = 50 health_score += category_counts["healthy"] * 25 health_score += category_counts["protein"] * 15 health_score += category_counts["neutral"] * 5 health_score -= category_counts["junk"] * 10 # Adjust based on macros if total_calories > 0: # Protein is good protein_ratio = (total_protein * 4) / total_calories if protein_ratio > 0.25: # >25% protein is good health_score += 10 # Too much fat is not ideal fat_ratio = (total_fat * 9) / total_calories if fat_ratio > 0.4: # >40% calories from fat health_score -= 10 # Clamp score between 0-100 health_score = max(0, min(100, health_score)) # Determine feedback category if health_score >= 80: category = "excellent" elif health_score >= 60: category = "good" elif health_score >= 40: category = "moderate" else: category = "poor" # Get a random motivational quote for the category quote = random.choice(motivational_quotes[category]) # Create nutrition data nutrition_data = { "calories": total_calories, "fat": total_fat, "carbs": total_carbs, "protein": total_protein, "health_score": health_score, "category": category, "message": quote } # Create summary dominant_macro = "" if total_calories > 0: fat_percentage = (total_fat * 9) / total_calories * 100 carbs_percentage = (total_carbs * 4) / total_calories * 100 protein_percentage = (total_protein * 4) / total_calories * 100 if max(fat_percentage, carbs_percentage, protein_percentage) == fat_percentage: dominant_macro = "fat" elif max(fat_percentage, carbs_percentage, protein_percentage) == carbs_percentage: dominant_macro = "carbs" else: dominant_macro = "protein" summary = f"You consumed approximately {total_calories} calories — mostly {dominant_macro}." if health_score >= 70: summary += " Great choices today!" elif health_score >= 50: summary += " Consider more balanced options next time." else: summary += " Try to make healthier choices next time." return nutrition_data, summary, "" # Generate detailed analysis with visualization def generate_analysis(matched_items, nutrition_data): if not matched_items or not nutrition_data: return None # Create DataFrame for the items items_data = [] for item in matched_items: name = item["name"] if "matched_as" in item: name = f"{name} (matched as {item['matched_as']})" items_data.append({ "Item": name, "Calories": item["nutrition"]["calories"], "Fat (g)": item["nutrition"]["fat"], "Carbs (g)": item["nutrition"]["carbs"], "Protein (g)": item["nutrition"]["protein"], "Category": item["nutrition"]["category"].capitalize() }) df = pd.DataFrame(items_data) # Get the current date and time now = datetime.datetime.now() date_str = now.strftime("%Y-%m-%d") time_str = now.strftime("%H:%M:%S") # Create visualization plots fig, axs = plt.subplots(2, 2, figsize=(12, 10)) # Plot 1: Calories by item (horizontal bar) df_sorted = df.sort_values('Calories', ascending=True) sns.barplot(x='Calories', y='Item', data=df_sorted, ax=axs[0, 0], palette='viridis') axs[0, 0].set_title('Calories by Item') axs[0, 0].set_xlabel('Calories') axs[0, 0].set_ylabel('Food Item') # Plot 2: Macronutrient breakdown (pie chart) total_calories = nutrition_data["calories"] if total_calories > 0: fat_cals = nutrition_data["fat"] * 9 carb_cals = nutrition_data["carbs"] * 4 protein_cals = nutrition_data["protein"] * 4 macro_data = [fat_cals, carb_cals, protein_cals] macro_labels = [f'Fat ({fat_cals:.0f} cal)', f'Carbs ({carb_cals:.0f} cal)', f'Protein ({protein_cals:.0f} cal)'] colors = ['#FF9999', '#66B2FF', '#99FF99'] axs[0, 1].pie(macro_data, labels=macro_labels, colors=colors, autopct='%1.1f%%', startangle=90) axs[0, 1].set_title('Calorie Sources') else: axs[0, 1].text(0.5, 0.5, 'No calorie data available', ha='center', va='center') axs[0, 1].axis('off') # Plot 3: Health score gauge health_score = nutrition_data["health_score"] # Create a gauge chart using a pie chart size = 0.3 vals = [health_score, 100-health_score] # Create color based on score if health_score >= 80: color = '#00CC66' # Green elif health_score >= 60: color = '#CCCC00' # Yellow elif health_score >= 40: color = '#FF9900' # Orange else: color = '#FF3333' # Red cmap = [color, '#f0f0f0'] axs[1, 0].pie(vals, radius=1, colors=cmap, startangle=90, counterclock=False) axs[1, 0].pie([1], radius=1-size, colors=['white']) axs[1, 0].text(0, 0, f"{health_score:.0f}", fontsize=32, ha='center', va='center') axs[1, 0].text(0, -0.2, "Health Score", fontsize=12, ha='center', va='center') axs[1, 0].set_title('Meal Health Score') # Plot 4: Food category breakdown category_counts = df['Category'].value_counts() sns.barplot(x=category_counts.index, y=category_counts.values, ax=axs[1, 1], palette='viridis') axs[1, 1].set_title('Food Categories') axs[1, 1].set_xlabel('Category') axs[1, 1].set_ylabel('Count') plt.tight_layout() # Save the plots to a file analysis_img_path = "analysis_temp.png" plt.savefig(analysis_img_path, dpi=150, bbox_inches='tight') plt.close() # Create a table of the analyzed items items_table = df.to_html(index=False, classes='table table-striped') # Create analysis summary total_fat = nutrition_data["fat"] total_carbs = nutrition_data["carbs"] total_protein = nutrition_data["protein"] analysis_summary = f"""

Meal Nutrition Analysis

Date: {date_str}   Time: {time_str}

Summary

Total Calories: {total_calories:.0f}
Total Fat: {total_fat:.1f}g ({(total_fat * 9 / total_calories * 100):.1f}% of calories)
Total Carbs: {total_carbs:.1f}g ({(total_carbs * 4 / total_calories * 100):.1f}% of calories)
Total Protein: {total_protein:.1f}g ({(total_protein * 4 / total_calories * 100):.1f}% of calories)
Health Score: {health_score:.0f}/100 ({nutrition_data["category"].capitalize()})

Feedback

{nutrition_data["message"]}

Analyzed Items

{items_table}

Recommendations

""" # Add custom recommendations based on the nutritional analysis if total_protein < 20: analysis_summary += "

✅ Add more protein to your meals. Good sources include lean meats, fish, eggs, tofu, or legumes.

" if (total_fat * 9 / total_calories) > 0.4: analysis_summary += "

✅ Consider reducing fat intake, especially from fried foods and processed items.

" category_counts_dict = df['Category'].value_counts().to_dict() junk_count = category_counts_dict.get('Junk', 0) healthy_count = category_counts_dict.get('Healthy', 0) if junk_count > healthy_count: analysis_summary += "

✅ Try to include more fruits and vegetables in your meals for better nutrition.

" if health_score < 50: analysis_summary += "

✅ Balance your plate with 1/2 vegetables, 1/4 protein, and 1/4 whole grains for improved nutrition.

" return analysis_img_path, analysis_summary # Function to process the bill image with enhanced error handling def process_bill_image(image): try: display_img = None ocr_text = "" food_items = [] matched_items = [] nutrition_data = None summary = "" error_message = "" # Process the image if it's valid if image is not None: # Extract text using OCR ocr_text = extract_text_from_image(image) if ocr_text: # Extract food items from the OCR text food_items = extract_food_items(ocr_text) if food_items: # Match food items to nutrition database matched_items = match_food_to_nutrition(food_items) if matched_items: # Calculate health score and nutrition data nutrition_data, summary, error_message = calculate_meal_health(matched_items) else: error_message = "No matching food items found in our database. Please try another image." else: error_message = "No food items detected. Please try another image or check the image clarity." else: error_message = "No text could be extracted from the image. Please try a clearer image." else: error_message = "Please upload an image to analyze." # Generate the food items section food_items_html = "

No food items detected

" if matched_items: food_items_html = "" # Generate detailed analysis if we have data analysis_img = None analysis_html = "

No analysis available

" if matched_items and nutrition_data: try: analysis_img, analysis_html = generate_analysis(matched_items, nutrition_data) except Exception as e: print(f"Error generating analysis: {str(e)}") analysis_html = f"

Error generating analysis: {str(e)}

" # Return the results return ( ocr_text, food_items_html, summary if summary else error_message, analysis_img if analysis_img else None, analysis_html ) except Exception as e: error_msg = f"An error occurred: {str(e)}" print(error_msg) return ( "", "

No food items detected

", error_msg, None, "

Analysis not available due to an error

" ) # Function to process direct text input (instead of an image) def process_text_input(text_input): try: if not text_input: return "

No text provided

", "Please enter some text to analyze", None, "

Analysis not available

" # Extract food items from the text food_items = extract_food_items(text_input) if not food_items: return "

No food items detected in your text

", "No food items found. Try being more specific about what you ate.", None, "

Analysis not available

" # Match food items to nutrition database matched_items = match_food_to_nutrition(food_items) if not matched_items: return "

No matching food items found in our database

", "Your food items couldn't be matched to our database. Try different foods or descriptions.", None, "

Analysis not available

" # Calculate health score and nutrition data nutrition_data, summary, error_message = calculate_meal_health(matched_items) if error_message: return "

No food items detected

", error_message, None, "

Analysis not available

" # Generate the food items section food_items_html = "" # Generate detailed analysis analysis_img, analysis_html = generate_analysis(matched_items, nutrition_data) return food_items_html, summary, analysis_img, analysis_html except Exception as e: error_msg = f"An error occurred: {str(e)}" print(error_msg) return "

No food items detected

", error_msg, None, "

Analysis not available due to an error

" # Create the Gradio interface def create_gradio_interface(): # Define CSS for the interface custom_css = """ body { font-family: 'Arial', sans-serif; } h1 { color: #4a4a4a; text-align: center; } .footer { text-align: center; margin-top: 20px; font-size: 0.8em; color: #666; } .container { margin: 0 auto; max-width: 1200px; } .tab-content { padding: 15px; border: 1px solid #ddd; border-top: none; border-radius: 0 0 5px 5px; } .nutrition-summary { background-color: #f9f9f9; padding: 15px; border-radius: 5px; margin-top: 15px; } .footer-note { font-size: 0.9em; font-style: italic; margin-top: 30px; text-align: center; color: #777; } table.table-striped { width: 100%; border-collapse: collapse; } table.table-striped th, table.table-striped td { border: 1px solid #ddd; padding: 8px; text-align: left; } table.table-striped tr:nth-child(even) { background-color: #f2f2f2; } table.table-striped th { padding-top: 12px; padding-bottom: 12px; background-color: #4CAF50; color: white; } """ # Define theme theme = gr.themes.Soft( primary_hue="green", secondary_hue="blue", ).set( body_text_color="#333333", block_title_text_weight="600", block_border_width="1px", block_shadow="0px 5px 10px rgba(0, 0, 0, 0.1)", button_primary_background_fill="#4CAF50", button_primary_background_fill_hover="#45a049", ) # Create Gradio blocks with gr.Blocks(css=custom_css, theme=theme) as demo: # Header gr.HTML("""

🧾 Restaurant Bill Nutritional Analyzer 🍔

Upload a photo of your restaurant bill or receipt, and this tool will analyze what you ate, estimate the nutritional content, and provide a health score.

Note: This tool works best with clear images of English-language bills and menus.

""") # Main content with gr.Tabs(): # Image upload tab with gr.TabItem("Upload Receipt Image"): with gr.Row(): with gr.Column(scale=1): # Input components image_input = gr.Image(label="Upload a photo of your restaurant bill") analyze_btn = gr.Button("Analyze Receipt", variant="primary") with gr.Column(scale=1): # Output components ocr_output = gr.Textbox(label="Extracted Text (OCR)", lines=5) with gr.Row(): with gr.Column(scale=1): food_items_output = gr.HTML(label="Detected Food Items") with gr.Column(scale=1): nutrition_summary = gr.Textbox(label="Nutrition Summary", lines=4) with gr.Row(): gr.HTML("

Detailed Nutritional Analysis

") with gr.Row(): with gr.Column(scale=1): analysis_chart = gr.Image(label="Analysis Chart") with gr.Column(scale=1): analysis_details = gr.HTML(label="Analysis Details") # Set up the button click event analyze_btn.click( fn=process_bill_image, inputs=[image_input], outputs=[ocr_output, food_items_output, nutrition_summary, analysis_chart, analysis_details] ) # Manual text input tab with gr.TabItem("Enter Food Items Manually"): with gr.Row(): with gr.Column(scale=1): text_input = gr.Textbox( label="Enter what you ate (e.g., 'burger, fries, and a soda')", lines=3, placeholder="Example: I had a cheeseburger with fries and a coke for lunch." ) analyze_text_btn = gr.Button("Analyze Food Items", variant="primary") with gr.Row(): with gr.Column(scale=1): text_food_items = gr.HTML(label="Detected Food Items") with gr.Column(scale=1): text_summary = gr.Textbox(label="Nutrition Summary", lines=4) with gr.Row(): with gr.Column(scale=1): text_analysis_chart = gr.Image(label="Analysis Chart") with gr.Column(scale=1): text_analysis_details = gr.HTML(label="Analysis Details") # Examples for text input gr.Examples( examples=[ "I had a burger, fries and a coke", "For dinner I ordered pizza and ice cream", "Grilled chicken salad with water", "Steak, baked potato and broccoli with red wine" ], inputs=text_input ) # Set up the button click event analyze_text_btn.click( fn=process_text_input, inputs=[text_input], outputs=[text_food_items, text_summary, text_analysis_chart, text_analysis_details] ) # About tab with gr.TabItem("About"): gr.HTML("""

About This Tool

This nutritional analyzer uses OCR (Optical Character Recognition) to extract text from restaurant bills and receipts. It then uses natural language processing techniques to identify food items and match them to a nutrition database.

How It Works

  1. Image Processing: Your uploaded image is enhanced for better text recognition
  2. Text Extraction: OCR technology reads the text from the image
  3. Food Detection: NLP algorithms identify food items in the text
  4. Nutrition Matching: Food items are matched to a nutrition database
  5. Analysis: Nutritional totals are calculated and a health score is assigned

Limitations

Please note the following limitations:

Privacy Notice

Images uploaded to this tool are processed for the sole purpose of extracting food information. Images and extracted data are not permanently stored.

This tool is intended for informational purposes only and is not a substitute for professional nutritional or medical advice.

""") # Footer gr.HTML("""

🍽️ Restaurant Bill Nutritional Analyzer | Built with Gradio and Hugging Face | 2023

""") return demo # Create and launch the app demo = create_gradio_interface() # Run the app if __name__ == "__main__": demo.launch()