python - 如何旋转图像以对齐文本以进行提取?
问题描述
我正在使用 pytessearct 从图像中提取文本。但它不适用于倾斜的图像。考虑下面给出的图像:
这是提取文本的代码,它在不倾斜的图像上运行良好。
img = cv2.imread(<path_to_image>)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5),0)
ret3, thresh = cv2.threshold(blur,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
def findSignificantContours (img, edgeImg):
contours, heirarchy = cv2.findContours(edgeImg, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
# Find level 1 contours
level1 = []
for i, tupl in enumerate(heirarchy[0]):
# Each array is in format (Next, Prev, First child, Parent)
# Filter the ones without parent
if tupl[3] == -1:
tupl = np.insert(tupl, 0, [i])
level1.append(tupl)
significant = []
tooSmall = edgeImg.size * 5 / 100 # If contour isn't covering 5% of total area of image then it probably is too small
for tupl in level1:
contour = contours[tupl[0]];
area = cv2.contourArea(contour)
if area > tooSmall:
significant.append([contour, area])
# Draw the contour on the original image
cv2.drawContours(img, [contour], 0, (0,255,0),2, cv2.LINE_AA, maxLevel=1)
significant.sort(key=lambda x: x[1])
#print ([x[1] for x in significant]);
mx = (0,0,0,0) # biggest bounding box so far
mx_area = 0
for cont in contours:
x,y,w,h = cv2.boundingRect(cont)
area = w*h
if area > mx_area:
mx = x,y,w,h
mx_area = area
x,y,w,h = mx
# Output to files
roi = img[y:y+h,x:x+w]
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5),0)
ret3, thresh = cv2.threshold(blur,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2_imshow(thresh)
text = pytesseract.image_to_string(roi);
print(text); print("\n"); print(pytesseract.image_to_string(thresh));
print("\n")
return [x[0] for x in significant];
edgeImg_8u = np.asarray(thresh, np.uint8)
# Find contours
significant = findSignificantContours(img, edgeImg_8u)
mask = thresh.copy()
mask[mask > 0] = 0
cv2.fillPoly(mask, significant, 255)
# Invert mask
mask = np.logical_not(mask)
#Finally remove the background
img[mask] = 0;
Tesseract 无法从此图像中提取文本。有没有办法可以旋转它以完美对齐文本,然后将其提供给 pytesseract?如果我的问题需要更清楚,请告诉我。
解决方案
这是一个简单的方法:
查找轮廓并排序最大轮廓。我们找到轮廓,然后使用轮廓区域过滤
cv2.contourArea()
以隔离矩形轮廓。执行透视变换。接下来我们执行轮廓近似
cv2.contourArea()
以获得矩形轮廓。最后我们利用imutils.perspective.four_point_transform
实际获得图像的鸟瞰图。
二进制图像
结果
要实际提取文本,请查看
代码
from imutils.perspective import four_point_transform
import cv2
import numpy
# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread("1.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Find contours and sort for largest contour
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
displayCnt = None
for c in cnts:
# Perform contour approximation
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
if len(approx) == 4:
displayCnt = approx
break
# Obtain birds' eye view of image
warped = four_point_transform(image, displayCnt.reshape(4, 2))
cv2.imshow("thresh", thresh)
cv2.imshow("warped", warped)
cv2.waitKey()