Update app.py

app.py

@@ -1,4 +1,4 @@
-import gradio as gr
+import gradio as gr 
 import cv2
 import numpy as np
 from fpdf import FPDF
@@ -11,7 +11,6 @@ from datetime import datetime
 import base64
 import io
 import logging
-from PIL import Image
 
 # Set up logging to debug file writing issues
 logging.basicConfig(level=logging.INFO)
@@ -180,42 +179,19 @@ def save_record_to_salesforce(annotated_image_url, coverage_percent, original_im
     })
 
 def process_image(input_img, brightness_threshold=150):
-    logger.info(f"Input image type: {type(input_img)}, Shape: {input_img.size if isinstance(input_img, Image.Image) else 'N/A'}")
-    
-    # Validate input image
-    if input_img is None:
-        raise ValueError("No image provided")
-
-    if isinstance(input_img, Image.Image):
-        img = np.array(input_img)
-    else:
-        raise ValueError(f"Unsupported image type: {type(input_img)}")
+    img = np.array(input_img)  # Convert PIL Image to NumPy array
+    img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)  # Convert from RGB to BGR
 
-    if len(img.shape) != 3 or img.shape[2] != 3:
-        raise ValueError("Invalid image format: Expected a 3-channel color image")
-
-    img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
-
-    # Resize large images
+    # Resize large images for faster processing, preserving aspect ratio
     max_dim = 640
     h, w = img.shape[:2]
-    if h < 10 or w < 10 or h > 4096 or w > 4096:
-        raise ValueError(f"Invalid image dimensions: {w}x{h}")
-    if img.size == 0:
-        raise ValueError("Empty image provided")
-    
     if max(h, w) > max_dim:
         scale = max_dim / max(h, w)
         img = cv2.resize(img, (int(w * scale), int(h * scale)))
 
-    # OCR processing
-    try:
-        start_time = time.time()
-        ocr_result = ocr_model.predict(img)
-        ocr_time = time.time() - start_time
-    except Exception as e:
-        logger.error(f"PaddleOCR failed: {str(e)}", exc_info=True)
-        raise RuntimeError(f"PaddleOCR processing failed: {str(e)}")
+    start_time = time.time()
+    ocr_result = ocr_model.predict(img)  # Use the `predict` method here instead of `ocr`
+    ocr_time = time.time() - start_time
 
     extracted_texts = []
     for line in ocr_result:
@@ -235,31 +211,33 @@ def process_image(input_img, brightness_threshold=150):
     temp_pdf_file.close()
     create_pdf_report(coverage_percent, extracted_texts, annotated_img_path, temp_pdf_file.name)
 
+    # Upload annotated image and get URL
     annotated_image_url = upload_image_and_get_url(annotated_img_path)
+
+    # Save record in Salesforce
     save_record_to_salesforce(annotated_image_url, coverage_percent, input_img)
 
     annotated_img_rgb = cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB)
+
     report_text = f"UV Sterilization Coverage: {coverage_percent:.2f}%"
+
+    # Clean up temp image file after PDF generation
     os.unlink(annotated_img_path)
 
     return annotated_img_rgb, report_text, temp_pdf_file.name
 
 iface = gr.Interface(
     fn=process_image,
-    inputs=[
-        gr.Image(type="pil", label="Upload Post-UV Sterilization Image"),
-        gr.Slider(50, 255, value=150, step=1, label="Brightness Threshold")
-    ],
-    outputs=[
-        gr.Image(type="numpy", label="Annotated Image"),
-        gr.Textbox(label="UV Sterilization Report", lines=5),
-        gr.File(label="Download PDF Report")
-    ],
+    inputs=[gr.Image(type="pil", label="Upload Post-UV Sterilization Image"),
+            gr.Slider(50, 255, value=150, step=1, label="Brightness Threshold")],
+    outputs=[gr.Image(type="numpy", label="Annotated Image"),
+             gr.Textbox(label="UV Sterilization Report", lines=5),
+             gr.File(label="Download PDF Report")],
     title="UV Sterilization Coverage Analyzer",
     description="Upload a post-UV sterilization image to analyze surface coverage and generate a compliance report."
 )
 
-iface.queue(max_size=10, concurrency_count=1)  # Limit to 1 concurrent request
+iface.queue()  # Enable request queuing to improve UX on heavy processing
 
 if __name__ == "__main__":
     iface.launch()