Python 如何选择六位数字组的正确轮廓
我有一批屏幕截图,如下所示: 我试着用六个数字来检测区域并识别它们。第二部分很有魅力。我在检测正确的区域时遇到问题,因为它可以根据屏幕尺寸进行移位。例如,裁剪图像如下所示: 看起来还可以,但我必须在代码中添加一些变通方法来选择正确的位置 我的代码:Python 如何选择六位数字组的正确轮廓,python,opencv,ocr,Python,Opencv,Ocr,我有一批屏幕截图,如下所示: 我试着用六个数字来检测区域并识别它们。第二部分很有魅力。我在检测正确的区域时遇到问题,因为它可以根据屏幕尺寸进行移位。例如,裁剪图像如下所示: 看起来还可以,但我必须在代码中添加一些变通方法来选择正确的位置 我的代码: import cv2 import numpy as np from matplotlib import pyplot as plt from PIL import Image rectKernel = cv2.getStructuringEle
import cv2
import numpy as np
from matplotlib import pyplot as plt
from PIL import Image
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15, 6))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (8, 8))
# Load and resize image to standard size
img0 = Image.open('./data/test.png')
img0.thumbnail((720, 1423))
img = np.array(img0)
# The magic from https://www.pyimagesearch.com/2017/07/17/credit-card-ocr-with-opencv-and-python/
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
thresh = cv2.threshold(gradX, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
cnts, _ = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
locs = []
for (i, c) in enumerate(cnts):
(x, y, w, h) = cv2.boundingRect(c)
ar = w / h
if x > 140 and x < 220 and w > 100 and h > 12 and h < 20 and ar >= 4 and ar <= 6:
locs.append((x, y, w, h))
# Calculate the crop rectangle
LEFT_TOP = (181, 316)
RIGHT_BOTTOM = (299, 346)
if len(locs) > 0:
(x, y, w, h) = locs[0]
LEFT_TOP = (x - 5, y - 5) # workaround place
RIGHT_BOTTOM = (x + w + 5, y + h) # workaround place
print(LEFT_TOP, RIGHT_BOTTOM)
img1 = img0.crop(LEFT_TOP + RIGHT_BOTTOM)
选定的轮廓看起来像:
它选择一个小于实际区域的轮廓。为什么?如何修复它
谢谢大家!
测试文件:
软件中没有魔法 不合适的过滤器会侵蚀你的部分手指 拆下tophat滤清器。 拆下索贝尔过滤器。 用cv2.THRESH_BINARY_INV替换cv2.THRESH_BINARY。 增加sqKernel的大小。 我建议您绘制等高线,并显示或保存中间结果以供测试 以下是修改后的代码:
import cv2
import numpy as np
#from matplotlib import pyplot as plt
from PIL import Image
#rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15, 6))
#sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (8, 8))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15, 11))
# Load and resize image to standard size
img0 = Image.open('./data/test.png')
img0.thumbnail((720, 1423))
img = np.array(img0)
# The magic from https://www.pyimagesearch.com/2017/07/17/credit-card-ocr-with-opencv-and-python/
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
#tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
#gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=-1)
#gradX = np.absolute(gradX)
#(minVal, maxVal) = (np.min(gradX), np.max(gradX))
#gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
#gradX = gradX.astype("uint8")
#gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
#thresh = cv2.threshold(gradX, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
cnts, _ = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
locs = []
# Draw contours for testing
tmp_im = cv2.cvtColor(img, cv2.COLOR_RGBA2BGR)
cv2.drawContours(tmp_im, cnts, -1, (0, 255, 0), 1) # Draw green line around the contour
cv2.imshow('tmp_im', tmp_im)
cv2.waitKey()
cv2.destroyAllWindows()
cv2.imwrite('./data/tmp_im.png', tmp_im)
for (i, c) in enumerate(cnts):
(x, y, w, h) = cv2.boundingRect(c)
ar = w / h
if x > 140 and x < 220 and w > 100 and h > 12 and h < 20 and ar >= 4 and ar <= 6:
locs.append((x, y, w, h))
# Calculate the crop rectangle
LEFT_TOP = (181, 316)
RIGHT_BOTTOM = (299, 346)
if len(locs) > 0:
(x, y, w, h) = locs[0]
#LEFT_TOP = (x - 5, y - 5) # workaround place
#RIGHT_BOTTOM = (x + w + 5, y + h) # workaround place
LEFT_TOP = (x, y) # workaround place
RIGHT_BOTTOM = (x + w, y + h) # workaround place
print(LEFT_TOP, RIGHT_BOTTOM)
img1 = img0.crop(LEFT_TOP + RIGHT_BOTTOM)
img1.show()
img1.save('./data/digits.png')
结果:
测试用tmp_img:
执行代码时,我得到LOC=[]。很可能您没有发布“./data/test.png”,而是发布了其他图像。请将导入语句添加到您发布的代码中。添加了导入行和测试图像。现在,在添加img1.save.'/data/digits.png'后,我得到了不错的数字。这是你的电话号码。好的,我看到了变通方法的位置是的,如果删除变通方法“+5”,结果裁剪文件将剪切部分数字。