实战 | 基于OpenCV的钢材表面划痕检测(步骤 + 源码)

Color Space

发布于 2023-12-20 19:30:01

2.2K0

文章被收录于专栏：OpenCV与AI深度学习OpenCV与AI深度学习

视觉/图像重磅干货，第一时间送达

导读

本文主要介绍基于OpenCV实现钢材表面划痕检测，并给详细步骤和代码。

背景介绍

实例图片来源于网络，目标是提取图中的划痕。

本文实现效果如下：

实现步骤

【1】灰度转换 +自适应二值化

# load image
img = cv2.imread('src.jpg')

# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# adaptive threshold 
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, -35)
cv2.imwrite('thres.jpg',thresh)

【2】形态学闭运算 + 开运算，去除噪点干扰（注意核大小）

# apply morphology
kernel = np.ones((3,30),np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
kernel = np.ones((3,35),np.uint8)
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)

【3】霍夫直线检测 + 绘制结果

# get hough line segments
threshold = 25
minLineLength = 10
maxLineGap = 20
lines = cv2.HoughLinesP(morph, 1, 30*np.pi/360, threshold, minLineLength, maxLineGap)

# draw lines
linear1 = np.zeros_like(thresh)
linear2 = img.copy()
for [line] in lines:
    x1 = line[0]
    y1 = line[1]
    x2 = line[2]
    y2 = line[3]
    cv2.line(linear1, (x1,y1), (x2,y2), 255, 1)
    cv2.line(linear2, (x1,y1), (x2,y2), (0,0,255), 1)