Upload 2 files

live_streaming_flask.py

@@ -0,0 +1,151 @@
+from flask import Flask, render_template, Response, flash, redirect, url_for
+import cv2
+from unstructured.partition.pdf import partition_pdf
+import json, base64, io, os
+from PIL import Image
+from imutils.perspective import four_point_transform
+from dotenv import load_dotenv
+import pytesseract
+
+load_dotenv()
+
+app = Flask(__name__)
+app.secret_key = os.getenv("SECRET_KEY")
+pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
+poppler_path=r"C:\poppler-23.11.0\Library\bin"
+
+count = 0
+OUTPUT_FOLDER = "OUTPUTS"
+IMAGE_FOLDER_PATH = os.path.join(OUTPUT_FOLDER, "SCANNED_IMAGE")
+DETECTED_IMAGE_FOLDER_PATH = os.path.join(OUTPUT_FOLDER,"DETECTED_IMAGE")
+PDF_FOLDER_PATH = os.path.join(OUTPUT_FOLDER, "SCANNED_PDF")
+JSON_FOLDER_PATH = os.path.join(OUTPUT_FOLDER, "EXTRACTED_JSON")
+
+for path in [OUTPUT_FOLDER, IMAGE_FOLDER_PATH, DETECTED_IMAGE_FOLDER_PATH, PDF_FOLDER_PATH, JSON_FOLDER_PATH]:
+    os.makedirs(path, exist_ok=True)
+
+# camera = cv2.VideoCapture('rtsp://freja.hiof.no:1935/rtplive/_definst_/hessdalen03.stream')  # use 0 for web camera
+#  for cctv camera use rtsp://username:password@ip_address:554/user=username_password='password'_channel=channel_number_stream=0.sdp' instead of camera
+# for local webcam use 
+camera= cv2.VideoCapture(0)
+
+# Increase resolution if supported by the webcam
+camera.set(cv2.CAP_PROP_FRAME_WIDTH, 1280)
+camera.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)
+camera.set(cv2.CAP_PROP_FPS, 30)
+
+# --- FUNCTION: Detect document contour ---
+def detect_document_contour(image):
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    blur = cv2.GaussianBlur(gray, (5, 5), 0)
+    _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+
+    contours, _ = cv2.findContours(thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
+    contours = sorted(contours, key=cv2.contourArea, reverse=True)
+
+    for contour in contours:
+        area = cv2.contourArea(contour)
+        if area > 1000:
+            peri = cv2.arcLength(contour, True)
+            approx = cv2.approxPolyDP(contour, 0.02 * peri, True)
+            if len(approx) == 4:
+                return approx
+    return None
+
+# --- FUNCTION: Extract images from saved PDF ---
+def extract_images_from_pdf(pdf_path, output_json_path):
+    elements = partition_pdf(
+        filename=pdf_path,
+        strategy="hi_res",
+        extract_image_block_types=["Image"],  # or ["Image", "Table"]
+        extract_image_block_to_payload=True,  # Set to True to get base64 in output
+    )
+    with open(output_json_path, "w") as f:
+        json.dump([element.to_dict() for element in elements], f, indent=4)
+
+    # Display extracted images
+    with open(output_json_path, 'r') as file:
+        file_elements = json.load(file)
+        
+    extracted_images_dir = os.path.join(os.path.dirname(output_json_path), "extracted_images")
+    os.makedirs(extracted_images_dir, exist_ok=True)
+    
+    for i, element in enumerate(file_elements):
+        if "image_base64" in element["metadata"]:
+            image_data = base64.b64decode(element["metadata"]["image_base64"])
+            image = Image.open(io.BytesIO(image_data))
+            image.show(title=f"Extracted Image {i+1}")
+            # image.save(DETECTED_IMAGE_FOLDER_PATH, f"Extracted Image {i+1}.png")
+
+display = None 
+scale = 0.5
+contour = None
+
+def gen_frames():  # generate frame by frame from camera
+    global display 
+    
+    while True:
+        # Capture frame-by-frame
+        success, frame = camera.read()  # read the camera frame
+        if not success:
+            break
+        else:
+            display = frame.copy()
+            contour = detect_document_contour(display)
+
+            if contour is not None:
+                cv2.drawContours(display, [contour], -1, (0, 255, 0), 3)
+
+            resized = cv2.resize(display, (int(scale * display.shape[1]), int(scale * display.shape[0])))
+            cv2.imshow("📷 Scan Document - Press 's' to Save, ESC to Exit", resized)
+
+            ret, buffer = cv2.imencode('.jpg', resized)
+            
+            frame = buffer.tobytes()
+            yield (b'--frame\r\n'
+                   b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n')  # concat frame one by one and show result
+
+# --- Route: Scan Document ---
+@app.route("/capture", methods=['POST'])
+def capture_document():
+    global count, display 
+    
+    if display is None:
+        flash("❌ No frame captured!", "error")
+        return redirect(url_for("index"))
+    
+    frame = display.copy()
+    contour = detect_document_contour(frame)
+    
+    if contour is None:
+        flash("❌ No document contour found!", "error")
+        return redirect(url_for("index"))
+    
+    warped = four_point_transform(frame, contour.reshape(4, 2))
+    image_path = os.path.join(IMAGE_FOLDER_PATH, f"scanned_colored_{count}.jpg")
+    pdf_path = os.path.join(PDF_FOLDER_PATH, f"scanned_colored_{count}.pdf")
+    json_path = os.path.join(JSON_FOLDER_PATH, f"scanned_{count}.json")
+    # json_path = os.path.join(DETECTED_IMAGE_FOLDER_PATH, f"scanned_{count}.json")
+
+    cv2.imwrite(image_path, warped)
+    img = Image.open(image_path).convert("RGB")
+    img.save(pdf_path)
+    
+    extract_images_from_pdf(pdf_path, json_path)
+
+    flash("✅ Document scanned and saved!", "success")
+    count += 1
+    return redirect(url_for("index"))
+
+@app.route('/video_feed')
+def video_feed():
+    #Video streaming route. Put this in the src attribute of an img tag
+    return Response(gen_frames(), mimetype='multipart/x-mixed-replace; boundary=frame')
+
+@app.route('/')
+def index():
+    """Video streaming home page."""
+    return render_template('live_streaming_index.html')
+
+if __name__ == '__main__':
+    app.run(debug=True)

templates/live_streaming_index.html

@@ -0,0 +1,39 @@
+<!doctype html>
+<html lang="en">
+
+<head>
+    <!-- Required meta tags -->
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+
+    <!-- Bootstrap CSS -->
+    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css"
+        integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+
+    <title>Live Streaming Demonstration</title>
+</head>
+
+<body>
+    <div class="container">
+        <div class="row">
+            <div class="col-lg-8  offset-lg-2">
+                <h3 class="mt-3">Live Streaming</h3>
+                <img src="{{ url_for('video_feed') }}" width="100%" class="mb-3">
+                <form action="{{ url_for('capture_document') }}" method="post">
+                    <button type="submit" class="btn btn-success btn-lg">📸 Capture Image</button>
+                </form>
+                {% with messages = get_flashed_messages(with_categories=true) %}
+                {% for category, message in messages %}
+                {% if category == 'error' %}
+                <p style="color: red;">{{ message }}</p>
+                {% else %}
+                <p style="color: green;">{{ message }}</p>
+                {% endif %}
+                {% endfor %}
+                {% endwith %}
+            </div>
+        </div>
+    </div>
+</body>
+
+</html>