Update app.py

app.py

@@ -9,18 +9,18 @@ import pytz
 import numpy as np
 import logging
 
-# Set up logging
+# Set up logging for better debugging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
-# Configure Tesseract path
+# Configure Tesseract path (ensure it's correctly set to your Tesseract installation)
 try:
-    pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract'  # Adjust path if needed
+    pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract'  # Change this to your tesseract path
     pytesseract.get_tesseract_version()  # Test Tesseract availability
     logging.info("Tesseract is available")
 except Exception as e:
     logging.error(f"Tesseract not found or misconfigured: {str(e)}")
 
-# Preprocessing function
+# Image Preprocessing to improve OCR accuracy
 def preprocess_image(img_cv):
     """Preprocess image for OCR: enhance contrast, reduce noise, and apply adaptive thresholding."""
     try:
@@ -40,33 +40,33 @@ def preprocess_image(img_cv):
         logging.error(f"Image preprocessing failed: {str(e)}")
         return img_cv
 
-# Function to extract weight using OCR
+# Function to extract weight from the image using Tesseract OCR
 def extract_weight(img):
-    """Extract weight from image using Tesseract OCR with improved configuration."""
+    """Extract weight from image using Tesseract OCR."""
     try:
         if img is None:
             logging.error("No image provided for OCR")
             return "Not detected", 0.0, None
         
-        # Convert PIL image to OpenCV format
+        # Convert PIL image to OpenCV format for processing
         img_cv = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
-        # Preprocess the image
+        # Preprocess the image (contrast, noise reduction, etc.)
         processed_img = preprocess_image(img_cv)
         
-        # OCR configuration for digit extraction
+        # OCR configuration to focus on digits and decimals
         custom_config = r'--oem 3 --psm 6 -c tessedit_char_whitelist=0123456789.'
         
-        # Run OCR
+        # Run OCR on the processed image
         text = pytesseract.image_to_string(processed_img, config=custom_config)
         logging.info(f"OCR result: '{text}'")
         
-        # Extract valid weight from OCR result (strip unwanted characters)
+        # Extract valid weight (only digits and decimals)
         weight = ''.join(filter(lambda x: x in '0123456789.', text.strip()))
         if weight:
             try:
                 weight_float = float(weight)
-                if weight_float >= 0:  # Only accept valid weights
-                    confidence = 95.0  # Assume high confidence if we have a valid weight
+                if weight_float >= 0:  # Ensure valid weight value
+                    confidence = 95.0  # High confidence if weight is valid
                     logging.info(f"Weight detected: {weight} (Confidence: {confidence:.2f}%)")
                     return weight, confidence, processed_img
             except ValueError:
@@ -78,7 +78,7 @@ def extract_weight(img):
         logging.error(f"OCR processing failed: {str(e)}")
         return "Not detected", 0.0, None
 
-# Main function to process image and display results
+# Main function to process the image and return results
 def process_image(img):
     """Process uploaded or captured image and extract weight."""
     if img is None:
@@ -91,11 +91,12 @@ def process_image(img):
     # Extract weight and confidence from the image
     weight, confidence, processed_img = extract_weight(img)
     
+    # If no weight detected, display the failure message
     if weight == "Not detected" or confidence < 95.0:
         logging.warning(f"Weight detection failed: {weight} (Confidence: {confidence:.2f}%)")
         return f"{weight} (Confidence: {confidence:.2f}%)", ist_time, gr.update(visible=True), gr.update(visible=False)
     
-    # Convert processed image to base64 for display
+    # Convert processed image to base64 for displaying it as a snapshot
     pil_image = Image.fromarray(processed_img)
     buffered = io.BytesIO()
     pil_image.save(buffered, format="PNG")
@@ -103,7 +104,7 @@ def process_image(img):
     
     return f"{weight} kg (Confidence: {confidence:.2f}%)", ist_time, img_base64, gr.update(visible=True)
 
-# Gradio Interface
+# Gradio Interface for user input and displaying results
 with gr.Blocks(title="⚖️ Auto Weight Logger") as demo:
     gr.Markdown("## ⚖️ Auto Weight Logger")
     gr.Markdown("📷 Upload or capture an image of a digital weight scale (max 5MB).")