Python Implementation of HED
We will use a pre-trained HED model to detect the edge of our input image
Input Image:
Input image for HED
Python3
import cv2 img = cv2.imread("input.webp") (H, W) = img.shape[:2] blob = cv2.dnn.blobFromImage(img, scalefactor=1.0, size=(W, H), swapRB=False, crop=False) net = cv2.dnn.readNetFromCaffe("deploy.prototxt", "hed_pretrained_bsds.caffemodel") net.setInput(blob) hed = net.forward() hed = cv2.resize(hed[0, 0], (W, H)) hed = (255 * hed).astype("uint8") cv2.imshow("Input", img) cv2.imshow("HED", hed) cv2.waitKey(0) |
Output:
Output
Using Different Input image
Input image:
Input image for HED
Python3
import cv2 img = cv2.imread("pexels-ylanite-koppens-2343170(1).jpg") (H, W) = img.shape[:2] blob = cv2.dnn.blobFromImage(img, scalefactor=1.0, size=(W, H), swapRB=False, crop=False) net = cv2.dnn.readNetFromCaffe("deploy.prototxt", "hed_pretrained_bsds.caffemodel") net.setInput(blob) hed = net.forward() hed = cv2.resize(hed[0, 0], (W, H)) hed = (255 * hed).astype("uint8") cv2.imshow("Input", img) cv2.imshow("HED", hed) cv2.waitKey(0) |
Output
Output
Holistically-Nested Edge Detection with OpenCV and Deep Learning
Holistically-nested edge detection (HED) is a deep learning model that uses fully convolutional neural networks and deeply-supervised nets to do image-to-image prediction. HED develops rich hierarchical representations automatically (directed by deep supervision on side replies) that are critical for resolving ambiguity in edge and object boundary detection.
Contact Us