Update app.py

app.py

@@ -11,7 +11,6 @@ import time
 # Initialize PaddleOCR once with improved settings
 ocr_model = PaddleOCR(use_angle_cls=True, lang='en', rec=True, det=True)
 
-# Function to analyze UV sterilization coverage (with morphological operations)
 def analyze_uv_coverage(img, brightness_threshold=150):
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
     
@@ -33,22 +32,18 @@ def analyze_uv_coverage(img, brightness_threshold=150):
     annotated_img = cv2.addWeighted(img, 0.6, overlay, 0.4, 0)
     return annotated_img, coverage_percent
 
-# Enhanced function to create a better PDF report
 def create_pdf_report(coverage_percent, extracted_texts, annotated_image_path, output_path):
     pdf = FPDF()
     pdf.add_page()
     
-    # Title and general info
     pdf.set_font("Arial", 'B', size=16)
     pdf.cell(200, 10, txt="UV Sterilization Report", ln=True, align='C')
     pdf.ln(10)
 
-    # Sterilization Coverage
     pdf.set_font("Arial", size=12)
     pdf.cell(0, 10, f"Sterilization Coverage: {coverage_percent:.2f}%", ln=True)
     pdf.ln(5)
 
-    # OCR Text extraction in a formatted way
     pdf.cell(0, 10, "Extracted Text from Image (OCR):", ln=True)
     pdf.set_font("Arial", size=10)
     if extracted_texts:
@@ -59,49 +54,41 @@ def create_pdf_report(coverage_percent, extracted_texts, annotated_image_path, o
 
     pdf.ln(10)
     
-    # Annotated Image Section
     pdf.cell(0, 10, "Annotated Image:", ln=True)
     pdf.image(annotated_image_path, x=10, y=pdf.get_y(), w=pdf.w - 20)
 
-    # Save the PDF to the specified path
     pdf.output(output_path)
 
 def process_image(input_img, brightness_threshold=150):
-    # Convert PIL image to OpenCV format
     img = cv2.cvtColor(np.array(input_img), cv2.COLOR_RGB2BGR)
 
-    # Run OCR using PaddleOCR
     start_time = time.time()
     ocr_result = ocr_model.ocr(np.array(input_img))
+    ocr_time = time.time() - start_time
+
     extracted_texts = []
     for line in ocr_result:
-        for word_info in line:
-            extracted_texts.append(word_info[1][0])
-    ocr_time = time.time() - start_time
+        if line:  # Skip None or empty
+            for word_info in line:
+                extracted_texts.append(word_info[1][0])
 
-    # Analyze UV coverage
     annotated_img, coverage_percent = analyze_uv_coverage(img, brightness_threshold)
 
-    # Save annotated image temporarily for PDF
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_img_file:
         cv2.imwrite(temp_img_file.name, annotated_img)
 
-        # Save PDF report temporarily
         temp_pdf_file = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
-        temp_pdf_file.close()  # Close so FPDF can write to it
+        temp_pdf_file.close()
         create_pdf_report(coverage_percent, extracted_texts, temp_img_file.name, temp_pdf_file.name)
 
-    # Convert annotated image back to RGB for display
     annotated_img_rgb = cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB)
 
     report_text = f"UV Sterilization Coverage: {coverage_percent:.2f}%\n\nExtracted Texts:\n"
     report_text += "\n".join(extracted_texts) if extracted_texts else "No text detected."
     report_text += f"\n\nOCR Processing Time: {ocr_time:.2f} seconds"
 
-    # Delete annotated image file to avoid temp buildup
     os.unlink(temp_img_file.name)
 
-    # Return annotated image, report text, and PDF file path
     return annotated_img_rgb, report_text, temp_pdf_file.name
 
 iface = gr.Interface(