OpenCV快速入门——图像预处理(必看)

OpenCV预处理

      • 对图像特征提取前的预处理
        • 1.灰度化
        • 2.滤波处理
        • 3.轮廓检测
        • 4.透视变换
        • 5.二值化
        • 6.形态学
        • 7.图像绘制&添加文字

对图像特征提取前的预处理

1.灰度化

2.滤波处理

3.轮廓检测

4.透视变换

5.二值化

import numpy as np
import cv2


def order_points(pts):
	# 一共4个坐标点
	rect = np.zeros((4, 2), dtype="float32")

	# 按顺序找到对应坐标0123分别是 左上,右上,右下,左下
	# 计算左上,右下
	s = pts.sum(axis=1)
	rect[0] = pts[np.argmin(s)]
	rect[2] = pts[np.argmax(s)]

	# 计算右上和左下
	diff = np.diff(pts, axis=1)
	rect[1] = pts[np.argmin(diff)]
	rect[3] = pts[np.argmax(diff)]
	return rect


def four_point_transform(image, pts):
	# 获取输入坐标点
	rect = order_points(pts)
	(tl, tr, br, bl) = rect

	# 计算输入的w和h值
	widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
	widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
	maxWidth = max(int(widthA), int(widthB))

	heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
	heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
	maxHeight = max(int(heightA), int(heightB))

	# 变换后对应坐标位置
	dst = np.array([
		[0, 0],
		[maxWidth - 1, 0],
		[maxWidth - 1, maxHeight - 1],
		[0, maxHeight - 1]], dtype="float32")

	# 计算变换矩阵
	M = cv2.getPerspectiveTransform(rect, dst)
	warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

	# 返回变换后结果
	return warped


def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
	dim = None
	(h, w) = image.shape[:2]
	if width is None and height is None:
		return image
	if width is None:
		r = height / float(h)
		dim = (int(w * r), height)
	else:
		r = width / float(w)
		dim = (width, int(h * r))
	resized = cv2.resize(image, dim, interpolation=inter)
	return resized

# 读取输入
image = cv2.imread('aa.jpg')
#坐标也会相同变化
ratio = image.shape[0] / 500.0
orig = image.copy()


image = resize(orig, height=500)

# 预处理
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(gray, 75, 200)

# 展示预处理结果
print("STEP 1: 边缘检测")
cv2.imshow("Image", image)
cv2.imshow("Edged", edged)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 轮廓检测
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[1]
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5]

# 遍历轮廓
for c in cnts:
	# 计算轮廓近似
	peri = cv2.arcLength(c, True)
	# C表示输入的点集
	# epsilon表示从原始轮廓到近似轮廓的最大距离,它是一个准确度参数
	# True表示封闭的
	approx = cv2.approxPolyDP(c, 0.02 * peri, True)

	# 4个点的时候就拿出来
	if len(approx) == 4:
		screenCnt = approx
		break

# 展示结果
print("STEP 2: 获取轮廓")
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
cv2.imshow("Outline", image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 透视变换
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)

# 二值处理
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)
# 展示结果
print("STEP 3: 变换")
cv2.imshow("Original", resize(orig, height = 650))
cv2.imshow("Scanned", resize(ref, height = 650))
cv2.waitKey(0)
cv2.destroyAllWindows()

6.形态学

有时候也需要借助形态学,对图像进行处理


# kernel ==> element 算子
element = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
element2 = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
element3 = cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))
 
# 腐蚀、膨胀
erosion = cv2.erode(img, kernel, iterations=1)
dilation = cv2.dialte(img, kernel)
 
# 通用形态学操作
kernel = np.ones((5, 5), np.uint8)
dst = cv2.morphologyEx(src, cv2.MORPH_operation, kernel, iteration)
 
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel, 2)
 
# 形态学梯度 = dilation - erosion,用于提取物体轮廓
gradiet = cv2.morphologyEx(img, cv2.MORPH_GRADIENT, kernel)
 
# 顶帽 = src - open,用来分离比邻近点亮一些的斑块
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)
 
# 黑帽 = src - close,用来分离比邻近点暗一些的斑块
blackhat= cv2.morphologyEx(img, cv2.MORPH_BLACKHAT, kernel)

7.图像绘制&添加文字

cv2.line(img, (0, 0), (511, 511), (255, 0, 0), 3)            # pt1, pt2, color, thickness
cv2.rectangle(img, (384, 0), (511, 511), (255, 0, 0), 3)     # pt1, pt2, color, thickness
cv2.circle(img, (447, 63), 63, (0, 0, 255), -1)              # center, radius, color, shift
 
pts = np.array([[10, 5], [20, 30], [70, 20], [50, 10]], np.int32).reshape((-1, 2))
cv2.polylines(img, [pts], True, (0, 255, 255))               # pts, is_closed, color
 
font = cv2.FONT_HERSHEY_SIMPLEX        # text, start_pt, font, fontscale, color, thickness, linetype
cv2.putText(img, 'hello', (10, 500), font, 4, (255, 255, 0), 2, cv2.LINE_AA)

你可能感兴趣的