Update app.py

app.py

@@ -6,14 +6,22 @@ import tempfile
 import os
 from PIL import Image
 from paddleocr import PaddleOCR
+import time
 
-# Initialize PaddleOCR once
-ocr_model = PaddleOCR(use_angle_cls=True, lang='en')
+# 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)
+    
+    # Apply threshold to identify sterilized vs unsterilized zones
     _, binary_mask = cv2.threshold(gray, brightness_threshold, 255, cv2.THRESH_BINARY)
 
+    # Apply morphological operations for better segmentation
+    kernel = np.ones((5, 5), np.uint8)
+    binary_mask = cv2.dilate(binary_mask, kernel, iterations=1)  # Dilation to fill gaps
+    
     total_pixels = binary_mask.size
     sterilized_pixels = cv2.countNonZero(binary_mask)
     coverage_percent = (sterilized_pixels / total_pixels) * 100
@@ -25,18 +33,23 @@ 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()
-    pdf.set_font("Arial", size=14)
+    
+    # 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)
 
-    pdf.cell(0, 10, "Extracted Texts from Image (OCR):", ln=True)
+    # 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:
         for text in extracted_texts:
@@ -45,8 +58,12 @@ def create_pdf_report(coverage_percent, extracted_texts, annotated_image_path, o
         pdf.cell(0, 8, "No text detected.", ln=True)
 
     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):
@@ -54,11 +71,13 @@ def process_image(input_img, brightness_threshold=150):
     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))
     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
 
     # Analyze UV coverage
     annotated_img, coverage_percent = analyze_uv_coverage(img, brightness_threshold)
@@ -77,6 +96,7 @@ def process_image(input_img, brightness_threshold=150):
 
     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)