透视变换 OMR Sheet - OpenCV Python
Perspective Transform OMR Sheet - OpenCV Python
我正在尝试在 python 中使用 OpenCV 进行透视变换。我想对齐图像并找到左上角右上角和左下角和右下角轮廓的坐标。到目前为止，这是我的代码，我可以在其中识别所有轮廓。
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(3,3),0)
edges = cv2.Canny(blur,50,100)
contours, hierarchy = cv2.findContours(edges,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) #find contours
cv2.drawContours(img,contours,-1,(0,255,0),2)
cv2.imshow('Contours',img)
cv2.waitKey(0)
这是我得到的图像。
如果你能帮我解决这个问题，我将不胜感激！
Original Image
演示输入：
Demo Inputs
演示输入 1：
Demo Input 1
演示输入 2：
Demo Input 2
演示输入 3：
Demo Input 3
演示输入 4：
Demo Input 4
期望的输出：
Desired Output
这是 Python/OpenCV 中的一种方法。
- 读取输入
- 阅读模板（针对其维度）
- 将输入转换为灰度和阈值
- 填充阈值（应用形态时保留角）
- 应用形态关闭
- 删除填充
- 获取最大外轮廓
- 获取其周长并近似为4个角作为变形的输入角
- 从模板的维度获取变形的输出角
- 获取透视变换矩阵
- 扭曲输入以匹配模板
- 保存结果
输入：
模板：
import cv2
import numpy as np
# read image
img = cv2.imread("omr_test.jpg")
hh, ww = img.shape[:2]
# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)
# remove padding
morph = morph[20:hh+20, 20:ww+20]
# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)
# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)
# Alternate: cv2.drawContours(page,[corners],0,(0,0,255),1)
# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)
# reformat input corners to x,y list
icorners = []
for corner in corners:
pt = [ corner[0][0],corner[0][1] ]
icorners.append(pt)
icorners = np.float32(icorners)
# get corresponding output corners form width and height
ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
ocorners = np.float32(ocorners)
# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)
# do perspective
warped = cv2.warpPerspective(img, M, (wd, ht))
# write results
cv2.imwrite("omr_test_thresh.jpg", thresh)
cv2.imwrite("omr_test_morph.jpg", morph)
cv2.imwrite("omr_test_polygon.jpg", polygon)
cv2.imwrite("omr_test_warped.jpg", warped)
# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)
阈值图像：
形态图像：
多边形图像：
扭曲的输入：
这里有一个修正，解决输入图像在Python/OpenCV中是顺时针旋转还是逆时针旋转。
- 读取输入
- 阅读模板（尺寸）
- 将输入转换为灰度和阈值
- 填充阈值（应用形态学时保留角）
- 应用形态关闭
- 删除填充
- 获取最大外轮廓
- 获取其周长并近似为4个角作为变形的输入角
- 按 Y 对角进行排序并测试 X 的前两个排序角。如果 diff=X2-X1 为负，则输出角需要以稍微不同的顺序列出。
- 根据模板的尺寸和排序角的差异获取变形的输出角。
- 获取透视变换矩阵
- 扭曲输入以匹配模板
- 保存结果
输入 1（顺时针旋转）：
:
输入 2（逆时针旋转）：
import cv2
import numpy as np
# read image
#img = cv2.imread("omr_test.jpg")
img = cv2.imread("omr_test2.jpg")
hh, ww = img.shape[:2]
# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)
# remove padding
morph = morph[20:hh+20, 20:ww+20]
# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)
# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)
# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)
# reformat input corners to x,y list
sortcorners = []
for corner in corners:
pt = [ corner[0][0],corner[0][1] ]
sortcorners.append(pt)
icorners = np.float32(sortcorners)
# sort corners on y
def takeSecond(elem):
return elem[1]
sortcorners.sort(key=takeSecond)
# check if second corner x is left or right of first corner x
x1 = sortcorners[0][0]
x2 = sortcorners[1][0]
diff = x2 - x1
print(x1, x2)
# get corresponding output corners from width and height
if diff >= 0:
ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
else:
ocorners = [ [wd,0], [0,0], [0,ht], [wd,ht]]
ocorners = np.float32(ocorners)
# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)
# do perspective
warped = cv2.warpPerspective(img, M, (wd, ht))
# write results
cv2.imwrite("omr_test2_thresh.jpg", thresh)
cv2.imwrite("omr_test2_morph.jpg", morph)
cv2.imwrite("omr_test2_polygon.jpg", polygon)
cv2.imwrite("omr_test2_warped.jpg", warped)
# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)
第一次输入的结果（顺时针旋转）：
第二个输入的结果（逆时针旋转）：
我正在尝试在 python 中使用 OpenCV 进行透视变换。我想对齐图像并找到左上角右上角和左下角和右下角轮廓的坐标。到目前为止，这是我的代码，我可以在其中识别所有轮廓。
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(3,3),0)
edges = cv2.Canny(blur,50,100)
contours, hierarchy = cv2.findContours(edges,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) #find contours
cv2.drawContours(img,contours,-1,(0,255,0),2)
cv2.imshow('Contours',img)
cv2.waitKey(0)
这是我得到的图像。
如果你能帮我解决这个问题，我将不胜感激！
Original Image
演示输入：
Demo Inputs
演示输入 1：
Demo Input 1
演示输入 2：
Demo Input 2
演示输入 3：
Demo Input 3
演示输入 4：
Demo Input 4
期望的输出：
Desired Output
这是 Python/OpenCV 中的一种方法。
- 读取输入
- 阅读模板（针对其维度）
- 将输入转换为灰度和阈值
- 填充阈值（应用形态时保留角）
- 应用形态关闭
- 删除填充
- 获取最大外轮廓
- 获取其周长并近似为4个角作为变形的输入角
- 从模板的维度获取变形的输出角
- 获取透视变换矩阵
- 扭曲输入以匹配模板
- 保存结果
输入：
模板：
import cv2
import numpy as np
# read image
img = cv2.imread("omr_test.jpg")
hh, ww = img.shape[:2]
# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)
# remove padding
morph = morph[20:hh+20, 20:ww+20]
# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)
# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)
# Alternate: cv2.drawContours(page,[corners],0,(0,0,255),1)
# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)
# reformat input corners to x,y list
icorners = []
for corner in corners:
pt = [ corner[0][0],corner[0][1] ]
icorners.append(pt)
icorners = np.float32(icorners)
# get corresponding output corners form width and height
ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
ocorners = np.float32(ocorners)
# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)
# do perspective
warped = cv2.warpPerspective(img, M, (wd, ht))
# write results
cv2.imwrite("omr_test_thresh.jpg", thresh)
cv2.imwrite("omr_test_morph.jpg", morph)
cv2.imwrite("omr_test_polygon.jpg", polygon)
cv2.imwrite("omr_test_warped.jpg", warped)
# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)
阈值图像：
形态图像：
多边形图像：
扭曲的输入：
这里有一个修正，解决输入图像在Python/OpenCV中是顺时针旋转还是逆时针旋转。
- 读取输入
- 阅读模板（尺寸）
- 将输入转换为灰度和阈值
- 填充阈值（应用形态学时保留角）
- 应用形态关闭
- 删除填充
- 获取最大外轮廓
- 获取其周长并近似为4个角作为变形的输入角
- 按 Y 对角进行排序并测试 X 的前两个排序角。如果 diff=X2-X1 为负，则输出角需要以稍微不同的顺序列出。
- 根据模板的尺寸和排序角的差异获取变形的输出角。
- 获取透视变换矩阵
- 扭曲输入以匹配模板
- 保存结果
输入 1（顺时针旋转）：
输入 2（逆时针旋转）：
import cv2
import numpy as np
# read image
#img = cv2.imread("omr_test.jpg")
img = cv2.imread("omr_test2.jpg")
hh, ww = img.shape[:2]
# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)
# remove padding
morph = morph[20:hh+20, 20:ww+20]
# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)
# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)
# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)
# reformat input corners to x,y list
sortcorners = []
for corner in corners:
pt = [ corner[0][0],corner[0][1] ]
sortcorners.append(pt)
icorners = np.float32(sortcorners)
# sort corners on y
def takeSecond(elem):
return elem[1]
sortcorners.sort(key=takeSecond)
# check if second corner x is left or right of first corner x
x1 = sortcorners[0][0]
x2 = sortcorners[1][0]
diff = x2 - x1
print(x1, x2)
# get corresponding output corners from width and height
if diff >= 0:
ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
else:
ocorners = [ [wd,0], [0,0], [0,ht], [wd,ht]]
ocorners = np.float32(ocorners)
# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)
# do perspective
warped = cv2.warpPerspective(img, M, (wd, ht))
# write results
cv2.imwrite("omr_test2_thresh.jpg", thresh)
cv2.imwrite("omr_test2_morph.jpg", morph)
cv2.imwrite("omr_test2_polygon.jpg", polygon)
cv2.imwrite("omr_test2_warped.jpg", warped)
# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)
第一次输入的结果（顺时针旋转）：
第二个输入的结果（逆时针旋转）：