如何解决如何在python中绘制低对比度对象的轮廓?
我很难勾勒出这种类型的低对比度对象:
我希望输出诸如以下内容的
在上面的示例中,我将cv2.findContours
与下面的代码一起使用,但是使用的阈值为105 ret,thresh = cv.threshold(blur,105,255,0)
。但是,如果我为低对比度图像重现它,则找不到最佳阈值:
import numpy as np
from PIL import Image
import requests
from io import BytesIO
import cv2 as cv
url = 'https://i.stack.imgur.com/OeZJ9.jpg'
response = requests.get(url)
img = Image.open(BytesIO(response.content)).convert('RGB')
img = np.array(img)
imgray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
blur = cv.GaussianBlur(imgray,(105,105),0)
ret,205,0)
im2,cnts,hierarchy = cv.findContours(thresh,cv.RETR_TREE,cv.CHAIN_APPROX_SIMPLE)
cv.drawContours(img,-1,(0,255),5)
plt.imshow(img,cmap = 'gray')
我知道问题在于背景和物体的强度重叠,但是我找不到其他成功的方法。我尝试过的其他事情包括:
- 阈值,in
skimage
和skimage.measure.find_contours
。 - 分水岭算法,in
opencv
。 - 腐蚀和扩张in
opencv
,这会大大降低轮廓分辨率。
我希望能以尽可能高的分辨率对与背景对比度较低的对象进行轮廓绘制。
解决方法
这里提出了什么
通过颜色渐变变化检测轮廓(见 Antonino 的回复)
对背景对比度低的对象进行轮廓绘制并非易事。尽管 Antonino 的片段接近轮廓,但对于轮廓检测还不够:
-
为了找到可能的最佳参数,我使用了下面的伪代码,它输出了数千张经过视觉分类的图像(参见输出图像)。然而,所有可能参数的组合都没有成功,即输出了所需的轮廓:
for scale_percent in range(30,51,5): for threshold1 in range(5,21): for threshold2 in range(10,31): for gauss_kernel in range(1,11,2): for std in [0,1,2]: for kernel_size in range(2,6): for iterations_dialation in [2,3]: for iterations_erosion in [2,3]: for img in images: name = img[3:] img = cv2.imread('my/img/dir'+img) original_height,original_width,color = img.shape width = int(original_width * scale_percent / 100) height = int(original_height * scale_percent / 100) dim = (width,height) resized = cv2.resize(img,dim,interpolation = cv2.INTER_AREA) imgBlur = cv2.GaussianBlur(resized,(gauss_kernel,gauss_kernel),std) imgGray = cv2.cvtColor(imgBlur,cv2.COLOR_BGR2GRAY) imgCanny = cv2.Canny(imgGray,threshold1,threshold2) plt.subplot(231),plt.imshow(resized),plt.axis('off') plt.title('Original '+ str(name)) plt.subplot(232),plt.imshow(imgCanny,cmap = 'gray') plt.title('Canny Edge-detector\n thr1 = {},thr2 = {}'.format(threshold1,threshold2)),plt.axis('off') kernel_s = (kernel_size,kernel_size) kernel = np.ones(kernel_s) imgDil = cv2.dilate(imgCanny,kernel,iterations = iterations_dialation) plt.subplot(233),plt.imshow(imgDil,cmap = 'gray'),plt.axis('off') plt.title("Dilated\n({},{}) iterations = {}".format(kernel_size,kernel_size,iterations_dialation)) kernel_erosion = np.ones(()) imgThre = cv2.erode(imgDil,iterations = iterations_erosion) plt.subplot(234),plt.imshow(imgThre,plt.axis('off') plt.title('Eroded\n({},{}) iterations = {}'.format(kernel_size,iterations_erosion)) imgFinalContours,finalContours = getContours(imgThre,resized) plt.subplot(235),plt.axis('off') plt.title("Contours") plt.subplot(236),plt.axis('off') plt.title('Contours') plt.tight_layout(pad = 0.1) plt.imshow(imgFinalContours) plt.savefig("my/results/" +name[:6]+"_scale_percent({})".format(scale_percent)+ "_threshold1({})".format(threshold1) +"_threshold2({})".format(threshold2) +"_gauss_kernel({})".format(gauss_kernel) +"_std({})".format(std) +"_kernel_size({})".format(kernel_size) +"_iterations_dialation({})".format(iterations_dialation) +"_iterations_erosion({})".format(iterations_erosion) +".jpg") plt.title(name) images = ["b_36_2.jpg","b_78_2.jpg","b_51_2.jpg","b_72_2.jpg","a_78_2.jpg","a_70_2.jpg"] process_images_1(images)
解决办法
使用预训练的深度学习模型
一个初步的想法是使用grabcut来训练模型,但这在时间上会非常昂贵。因此,预训练的深度学习模型是第一枪。虽然有些工具 failed,但此 other tool 的性能优于之前尝试过的任何其他方法(见下图)。因此,将所有功劳归功于 GitHub 存储库的创建者,扩展到操作模型(U^2-NET、BASNet)的创建者。 https://github.com/OPHoperHPO/image-background-remove-tool 不需要任何图像预处理,包含关于如何部署它的非常简单的文档,甚至是一个可执行的 google colab notebook。输出图像是具有透明背景的 png 图像:
因此,找到轮廓所需要的只是隔离 alpha 通道:
import cv2
import matplotlib.pyplot as plt,numpy as np
filename = '/a_58_2_pg_0.png'
image_4channel = cv2.imread(filename,cv2.IMREAD_UNCHANGED)
alpha_channel = image_4channel[...,-1]
contours,hier = cv2.findContours(alpha_channel,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
for idx,contour in enumerate(contours):
# create mask
# zeros with same shape
mask = np.zeros(alpha_channel.shape,np.uint8)
# draw contour
mask = cv2.drawContours(mask,[contour],-1,(255,255,255),-1) # -1 to fill the mask
cv2.imwrite('/contImage.jpg',mask)
plt.imshow(mask)
,
Ciao
为了解决您的问题,我将使用该片段来检测轮廓,并在其区域上对其进行过滤,仅保留大于给定尺寸的轮廓。在您的情况下,我假设您仅在搜索对象,但我准备将代码扩展为包含多个对象的图片
import cv2
import numpy as np
# input image
path = "16.jpg"
# finding contours
def getContours(img,imgContour):
contours,hierarchy = cv2.findContours(img,cv2.CHAIN_APPROX_SIMPLE)
finalContours = []
# for each contour found
for cnt in contours:
# find its area in pixel^2
area = cv2.contourArea(cnt)
print("Contour area: ",area)
# fixed assuming you are searching for the biggest object
# value can be found via previous print
minArea = 18000
if (area > minArea):
perimeter = cv2.arcLength(cnt,False)
# smaller epsilon -> more vertices detected [= more precision]
# improving bounding box precision - original value 0.02 * perimeter
epsilon = 0.002*perimeter
# check how many vertices
approx = cv2.approxPolyDP(cnt,epsilon,True)
print(len(approx))
finalContours.append([len(approx),area,approx,cnt])
# leaving this part if you have more objects to detect
# not needed when minArea has been chosen to detect only one object
# sorting the final results in descending order depending on the area
finalContours = sorted(finalContours,key = lambda x:x[1],reverse=True)
print("Final Contours number: ",len(finalContours))
for con in finalContours:
cv2.drawContours(imgContour,con[3],(0,3)
return imgContour,finalContours
# sourcing the input image
img = cv2.imread(path)
# img.shape gives back height,width,color in this order
original_height,color = img.shape
print('Original Dimensions : ',original_height)
# resizing to see the entire image
scale_percent = 30
width = int(original_width * scale_percent / 100)
height = int(original_height * scale_percent / 100)
print('Resized Dimensions : ',height)
dim = (width,height)
# resize image
resized = cv2.resize(img,interpolation = cv2.INTER_AREA)
cv2.imshow("Starting image",resized)
cv2.waitKey()
# blurring
imgBlur = cv2.GaussianBlur(resized,(7,7),1)
# graying
imgGray = cv2.cvtColor(imgBlur,cv2.COLOR_BGR2GRAY)
# inizialing thresholds
threshold1 = 14
threshold2 = 17
# canny
imgCanny = cv2.Canny(imgGray,threshold2)
# showing the last produced result
cv2.imshow("Canny",imgCanny)
cv2.waitKey()
kernel = np.ones((2,2))
imgDil = cv2.dilate(imgCanny,iterations = 3)
imgThre = cv2.erode(imgDil,iterations = 3)
imgFinalContours,resized)
# show the contours on the unfiltered resized image
cv2.imshow("Final Contours",imgFinalContours)
cv2.waitKey()
cv2.destroyAllWindows()
使用选定的值运行此命令的最终输出如下:
祝你有美好的一天
安东诺
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。