Update app.py

app.py

@@ -1,56 +1,28 @@
+import streamlit as st
 import cv2
 import numpy as np
-from paddleocr import PaddleOCR
-import matplotlib.pyplot as plt
 from fpdf import FPDF
+import tempfile
 import os
+from PIL import Image
+import io
 
-# Initialize PaddleOCR
-ocr = PaddleOCR(use_angle_cls=True, lang='en')
-
-def run_ocr(image_path):
-    result = ocr.ocr(image_path, cls=True)
-    texts = []
-    for line in result:
-        for word_info in line:
-            texts.append(word_info[1][0])
-    return texts
-
-def analyze_uv_coverage(image_path, brightness_threshold=150):
-    # Load image
-    img = cv2.imread(image_path)
+def analyze_uv_coverage(img, brightness_threshold=150):
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-
-    # Threshold image to segment sterilized zones
     _, binary_mask = cv2.threshold(gray, brightness_threshold, 255, cv2.THRESH_BINARY)
 
-    # Calculate coverage
     total_pixels = binary_mask.size
     sterilized_pixels = cv2.countNonZero(binary_mask)
     coverage_percent = (sterilized_pixels / total_pixels) * 100
 
-    # Create color overlay: sterilized in green, unsterilized in red
     overlay = img.copy()
-    overlay[binary_mask == 255] = [0, 255, 0]        # Green zones: sterilized
-    overlay[binary_mask == 0] = [0, 0, 255]          # Red zones: unsterilized
+    overlay[binary_mask == 255] = [0, 255, 0]  # Green sterilized
+    overlay[binary_mask == 0] = [0, 0, 255]    # Red unsterilized
 
-    # Blend overlay with original image
     annotated_img = cv2.addWeighted(img, 0.6, overlay, 0.4, 0)
-
     return annotated_img, coverage_percent
 
-def save_report(image_path, coverage_percent, extracted_texts, output_folder='output'):
-    if not os.path.exists(output_folder):
-        os.makedirs(output_folder)
-
-    report_file = os.path.join(output_folder, 'UV_Sterilization_Report.pdf')
-    annotated_image_file = os.path.join(output_folder, 'annotated_image.jpg')
-
-    # Generate annotated image and save
-    annotated_img, coverage = analyze_uv_coverage(image_path)
-    cv2.imwrite(annotated_image_file, annotated_img)
-
-    # Create 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)
@@ -67,37 +39,56 @@ def save_report(image_path, coverage_percent, extracted_texts, output_folder='ou
         pdf.multi_cell(0, 8, f"- {text}")
 
     pdf.ln(10)
-    pdf.cell(0, 10, "Annotated Image is saved alongside this report.", ln=True)
-
-    # Insert annotated image (resize for PDF)
-    pdf.image(annotated_image_file, x=10, y=pdf.get_y(), w=pdf.w - 20)
-
-    pdf.output(report_file)
-    print(f"Report saved at: {report_file}")
-    print(f"Annotated image saved at: {annotated_image_file}")
-
-def main(image_path):
-    print("Running OCR...")
-    extracted_texts = run_ocr(image_path)
-    print("Extracted Texts:", extracted_texts)
-
-    print("Analyzing UV sterilization coverage...")
-    annotated_img, coverage_percent = analyze_uv_coverage(image_path)
-
-    # Show annotated image using matplotlib
-    plt.imshow(cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB))
-    plt.title(f"UV Sterilization Coverage: {coverage_percent:.2f}%")
-    plt.axis('off')
-    plt.show()
-
-    # Save report and annotated image
-    save_report(image_path, coverage_percent, extracted_texts)
-
-if __name__ == '__main__':
-    import argparse
-
-    parser = argparse.ArgumentParser(description="UV Sterilization Analysis App")
-    parser.add_argument('image_path', type=str, help='Path to post-UV sterilization image')
-    args = parser.parse_args()
-
-    main(args.image_path)
+    pdf.cell(0, 10, "Annotated Image:", ln=True)
+    pdf.image(annotated_image_path, x=10, y=pdf.get_y(), w=pdf.w - 20)
+    pdf.output(output_path)
+
+def main():
+    st.title("UV Sterilization Coverage Analyzer")
+
+    uploaded_file = st.file_uploader("Upload post-UV sterilization image", type=['png','jpg','jpeg'])
+    brightness_threshold = st.slider("Brightness Threshold (for sterilized zone detection)", 50, 255, 150)
+
+    if uploaded_file is not None:
+        # Read image
+        file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
+        img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+
+        # Run OCR with Streamlit experimental API (uses Tesseract)
+        pil_image = Image.open(uploaded_file)
+        ocr_result = st.experimental_text_ocr(pil_image)
+        extracted_texts = [item['text'] for item in ocr_result if item['text'].strip() != ""]
+
+        # Analyze UV coverage
+        annotated_img, coverage_percent = analyze_uv_coverage(img, brightness_threshold)
+
+        # Show results
+        st.subheader("Extracted Text from Image:")
+        if extracted_texts:
+            for txt in extracted_texts:
+                st.write(f"- {txt}")
+        else:
+            st.write("No text detected.")
+
+        st.subheader(f"UV Sterilization Coverage: {coverage_percent:.2f}%")
+        st.image(cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB), caption="Annotated Image (Green = Sterilized, Red = Unsterilized)")
+
+        # Save annotated image temporarily
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_img_file:
+            cv2.imwrite(temp_img_file.name, annotated_img)
+
+            # Create PDF report
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf_file:
+                create_pdf_report(coverage_percent, extracted_texts, temp_img_file.name, temp_pdf_file.name)
+
+                # Provide download link for PDF
+                with open(temp_pdf_file.name, "rb") as f:
+                    pdf_bytes = f.read()
+                st.download_button(label="Download UV Sterilization Report (PDF)", data=pdf_bytes, file_name="UV_Sterilization_Report.pdf")
+
+                # Cleanup temp files on app rerun
+                os.unlink(temp_img_file.name)
+                os.unlink(temp_pdf_file.name)
+
+if __name__ == "__main__":
+    main()