python - 有没有办法用 OpenCV 更好地加载图像
问题描述
我想加载图像并使用霍夫变换来捕获纸张内的黑色边界区域,然后在框内执行一些计数操作。当然,这要求我能够以相对较好的质量加载图像。
问题是当我使用 openCV 的 cv2.imread() 加载时,我得到了一个非常淡化的图片版本,我无法快速处理。更糟糕的是,我无法使用 cv2.imshow() 渲染图像,每次尝试查看它时我的 IDE 都会挂起。所以我只好用matplotlib来一步步的渲染和看图。
我不知道任何其他用于图像处理的软件包(也许是枕头,但我不知道它是否会做我需要做的事情)。
img = cv2.imread("img1-min.jpg")
因为 cv2.imshow() 方法会导致窗口崩溃,所以我求助于 matplotlib:
plt.imshow(img)
plt.title('my picture')
plt.show()
在那之后:
gray = cv2.cvtColor (img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 75, 150)
lines = cv2.HoughLinesP(edges, 1, np.pi/180, 50, 50, 5)
if lines is not None:
for line in lines:
x1, y1, x2, y2 = line[0]
cv2.line(img, (x1, y1), (x2, y2), (0, 255, 0), 5)
plt.imshow(img)
plt.title('my picture')
plt.show()
输出是:
如您所见,非常混乱。我的预感是这是因为原始图像的加载方式。有没有办法可以改进加载过程,以便更容易应用霍夫线?
解决方案
我相信图像加载得很好,cv2.imread()
但它的尺寸如此之大2976x3838
,您的 IDE 无法显示图像。我相信你申请cv2.HoughLinesP()
不正确。而不是使用cv2.HoughLinesP()
,这是一种检测线条的替代方法
这个想法是阈值然后找到板的边界框以创建掩码。从这个掩码中,我们执行透视变换以获得自上而下的图像。这将使我们能够更好地检测线条
一旦我们有了检测到的电路板,我们就可以提取 ROI
然后我们简单地检测垂直和水平线
结果
import cv2
import numpy as np
def perspective_transform(image, corners):
def order_corner_points(corners):
# Separate corners into individual points
# Index 0 - top-right
# 1 - top-left
# 2 - bottom-left
# 3 - bottom-right
corners = [(corner[0][0], corner[0][1]) for corner in corners]
top_r, top_l, bottom_l, bottom_r = corners[0], corners[1], corners[2], corners[3]
return (top_l, top_r, bottom_r, bottom_l)
# Order points in clockwise order
ordered_corners = order_corner_points(corners)
top_l, top_r, bottom_r, bottom_l = ordered_corners
# Determine width of new image which is the max distance between
# (bottom right and bottom left) or (top right and top left) x-coordinates
width_A = np.sqrt(((bottom_r[0] - bottom_l[0]) ** 2) + ((bottom_r[1] - bottom_l[1]) ** 2))
width_B = np.sqrt(((top_r[0] - top_l[0]) ** 2) + ((top_r[1] - top_l[1]) ** 2))
width = max(int(width_A), int(width_B))
# Determine height of new image which is the max distance between
# (top right and bottom right) or (top left and bottom left) y-coordinates
height_A = np.sqrt(((top_r[0] - bottom_r[0]) ** 2) + ((top_r[1] - bottom_r[1]) ** 2))
height_B = np.sqrt(((top_l[0] - bottom_l[0]) ** 2) + ((top_l[1] - bottom_l[1]) ** 2))
height = max(int(height_A), int(height_B))
# Construct new points to obtain top-down view of image in
# top_r, top_l, bottom_l, bottom_r order
dimensions = np.array([[0, 0], [width - 1, 0], [width - 1, height - 1],
[0, height - 1]], dtype = "float32")
# Convert to Numpy format
ordered_corners = np.array(ordered_corners, dtype="float32")
# Find perspective transform matrix
matrix = cv2.getPerspectiveTransform(ordered_corners, dimensions)
# Return the transformed image
return cv2.warpPerspective(image, matrix, (width, height))
image = cv2.imread('1.jpg')
original = image.copy()
blur = cv2.bilateralFilter(image,9,75,75)
gray = cv2.cvtColor(blur, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray,0,255, cv2.THRESH_OTSU + cv2.THRESH_BINARY_INV)[1]
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
mask = np.zeros(image.shape, dtype=np.uint8)
for c in cnts:
area = cv2.contourArea(c)
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.015 * peri, True)
if area > 150000 and len(approx) == 4:
cv2.drawContours(image,[c], 0, (36,255,12), 3)
cv2.drawContours(mask,[c], 0, (255,255,255), -1)
transformed = perspective_transform(original, approx)
mask = cv2.bitwise_and(mask, original)
# Remove horizontal lines
gray = cv2.cvtColor(transformed, cv2.COLOR_BGR2GRAY)
board_thresh = cv2.threshold(gray,0,255, cv2.THRESH_OTSU + cv2.THRESH_BINARY_INV)[1]
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (55,1))
detect_horizontal = cv2.morphologyEx(board_thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(transformed, [c], -1, (36,255,12), 9)
pass
# Remove vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,55))
detect_vertical = cv2.morphologyEx(board_thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(transformed, [c], -1, (36,255,12), 9)
cv2.imwrite('thresh.png', thresh)
cv2.imwrite('image.png', image)
cv2.imwrite('mask.png', mask)
cv2.imwrite('transformed.png', transformed)
cv2.waitKey()
推荐阅读
- memory - 双端口存储器
- excel - 用户窗体内的进度条
- c# - 使用 C# 在 Word Doc 中更改绝对图片大小
- sql - 前 10 名 - 多个表(联合) - SQL
- c++ - QT Gridlayout Item点击后不突出显示?
- reactjs - 如何使用 react-loadable 从库中导出各种组件
- javascript - 运行 Angular 应用程序时出错:“let-”仅支持 ng-template 元素
- c# - Xamarin Forms UWP - 无法使用 .NET Native 工具链编译 - 错误:ILT0032
- android - 当应用程序在设备中运行时,ConstraintLayout 中的视图未按预期放置
- c# - 使用 ISearchIndexClient 进行测试