邊緣偵測是電腦視覺的基礎,使我們能夠辨識影像中的物件邊界。在本教程中,我們將使用 Sobel 算子和 Canny 邊緣偵測器以及 Python 和 OpenCV 來實作邊緣偵測。然後,我們將使用 Flask 創建一個簡單的 Web 應用程序,並使用 Bootstrap 進行樣式設計,以允許用戶上傳圖像並查看結果。
示範連結:邊緣偵測示範
開啟終端機或命令提示字元並執行:
pip install opencv-python numpy Flask
mkdir edge_detection_app cd edge_detection_app
Sobel 算子計算影像強度的梯度,強調邊緣。
程式碼實作:
import cv2 # Load the image in grayscale image = cv2.imread('input_image.jpg', cv2.IMREAD_GRAYSCALE) if image is None: print("Error loading image") exit() # Apply Sobel operator sobelx = cv2.Sobel(image, cv2.CV_64F, 1, 0, ksize=5) # Horizontal edges sobely = cv2.Sobel(image, cv2.CV_64F, 0, 1, ksize=5) # Vertical edges
Canny 邊緣偵測器是一種用於偵測邊緣的多層演算法。
程式碼實作:
# Apply Canny edge detector edges = cv2.Canny(image, threshold1=100, threshold2=200)
建立一個名為app.py的檔案:
from flask import Flask, request, render_template, redirect, url_for import cv2 import os app = Flask(__name__) UPLOAD_FOLDER = 'static/uploads/' OUTPUT_FOLDER = 'static/outputs/' app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER app.config['OUTPUT_FOLDER'] = OUTPUT_FOLDER # Create directories if they don't exist os.makedirs(UPLOAD_FOLDER, exist_ok=True) os.makedirs(OUTPUT_FOLDER, exist_ok=True)
上傳路線:
@app.route('/', methods=['GET', 'POST']) def upload_image(): if request.method == 'POST': file = request.files.get('file') if not file or file.filename == '': return 'No file selected', 400 filepath = os.path.join(app.config['UPLOAD_FOLDER'], file.filename) file.save(filepath) process_image(file.filename) return redirect(url_for('display_result', filename=file.filename)) return render_template('upload.html')
處理影像函數:
def process_image(filename): image_path = os.path.join(app.config['UPLOAD_FOLDER'], filename) image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE) # Apply edge detection sobelx = cv2.Sobel(image, cv2.CV_64F, 1, 0, ksize=5) edges = cv2.Canny(image, 100, 200) # Save outputs cv2.imwrite(os.path.join(app.config['OUTPUT_FOLDER'], 'sobelx_' + filename), sobelx) cv2.imwrite(os.path.join(app.config['OUTPUT_FOLDER'], 'edges_' + filename), edges)
結果路線:
@app.route('/result/<filename>') def display_result(filename): return render_template('result.html', original_image='uploads/' + filename, sobelx_image='outputs/sobelx_' + filename, edges_image='outputs/edges_' + filename)
if __name__ == '__main__': app.run(debug=True)
在 HTML 範本中包含 Bootstrap CDN 以進行樣式設定。
建立templates目錄並加入upload.html:
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Edge Detection App</title> <!-- Bootstrap CSS CDN --> <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css"> </head> <body> <div class="container mt-5"> <h1 class="text-center mb-4">Upload an Image for Edge Detection</h1> <div class="row justify-content-center"> <div class="col-md-6"> <form method="post" enctype="multipart/form-data" class="border p-4"> <div class="form-group"> <label for="file">Choose an image:</label> <input type="file" name="file" accept="image/*" required class="form-control-file" id="file"> </div> <button type="submit" class="btn btn-primary btn-block">Upload and Process</button> </form> </div> </div> </div> </body> </html>
在templates目錄下建立result.html:
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Edge Detection Results</title> <!-- Bootstrap CSS CDN --> <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css"> </head> <body> <div class="container mt-5"> <h1 class="text-center mb-5">Edge Detection Results</h1> <div class="row"> <div class="col-md-6 mb-4"> <h4 class="text-center">Original Image</h4> <img src="{{ url_for('static', filename=original_image) }}" alt="Original Image" class="img-fluid rounded mx-auto d-block"> </div> <div class="col-md-6 mb-4"> <h4 class="text-center">Sobel X</h4> <img src="{{ url_for('static', filename=sobelx_image) }}" alt="Sobel X" class="img-fluid rounded mx-auto d-block"> </div> <div class="col-md-6 mb-4"> <h4 class="text-center">Canny Edges</h4> <img src="{{ url_for('static', filename=edges_image) }}" alt="Canny Edges" class="img-fluid rounded mx-auto d-block"> </div> </div> <div class="text-center mt-4"> <a href="{{ url_for('upload_image') }}" class="btn btn-secondary">Process Another Image</a> </div> </div> </body> </html>
python app.py
開啟網頁瀏覽器並導航至 http://localhost:5000。
我們建立了一個簡單的 Web 應用程序,使用 Sobel 算子和 Canny 邊緣偵測器執行邊緣偵測。透過整合 Python、OpenCV、Flask 和 Bootstrap,我們創建了一個互動式工具,讓用戶上傳圖像並查看邊緣檢測結果。
後續步驟
GitHub 儲存庫:邊緣偵測應用程式
以上是使用 Python 和 OpenCV 實現邊緣檢測:逐步指南的詳細內容。更多資訊請關注PHP中文網其他相關文章!