OpenCV 和 Tesseract 在门标签检测上的应用
OpenCV and Tesseract on door label detection
我对 OpenCv 和 tesseract 还很陌生。我最近正在构建一个使用计算机视觉检测门标签的项目。希望对视障人士有所帮助
程序的思路是对输入图像进行预处理，将其转换为二值颜色，然后使用canny edge检测门标的轮廓，然后对canny edge结果进行膨胀。在这些之后，将图像提供给 tesseract，同时尝试显示用框检测到的文本。
预期结果是文本上的绿色矩形。在打印文本本身时。
问题是缺少矩形和文本检测失败。
我试过这些：
- Recognize Text in images using Canny Edge detection in Opencv
问题和解决方案太简单或不相关。有些也不在 python 中。
下面附上我对代码的尝试：
import pytesseract as pytess
import cv2 as cv
import numpy as np
from PIL import Image
from pytesseract import Output
img = cv.imread(r"C:\Users\User\Desktop\dataset\p\Image_31.jpg", 0)
# edges store the canny version of img
edges = cv.Canny(img, 100, 200)
# ker as in kernel
# (5, 5) is the matrix while uint8 is datatype
ker = np.ones((3, 3), np.uint8)
# dil as in dilation
# edges as the src, ker is the kernel we set above, number of dilation
dil = cv.dilate(edges, ker, iterations=1)
# setup pytesseract parameters
configs = r'--oem 3 --psm 6'
# feed image to tesseract
result = pytess.image_to_data(dil, output_type=Output.DICT, config=configs, lang='eng')
print(result.keys())
boxes = len(result['text'])
# make a new copy of edges
new_item = dil.copy()
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 30: # removed constraints
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
new_item = cv.rectangle(new_item, (x, y), (x + w, y + h), (0, 255, 0), 2)
# detect sentence with tesseract
# pending as rectangle not achieved
cv.imshow("original", img)
cv.imshow("canny", edges)
cv.imshow("dilation", dil)
cv.imshow("capturedText", new_item)
#ignore below this line, it is only for testing
#testobj = Image.fromarray(dil)
#testtext = pytess.image_to_string(testobj, lang='eng')
#print(testtext)
cv.waitKey(0)
cv.destroyAllWindows()
结果图像：
代码的测试部分return结果如下图：
a)
Meets
其中，显然不满足objective.
编辑
发布问题后，我意识到我一开始可能做错了。我应该尝试使用 OpencV 来检测门标签的轮廓并隔离包含文本的部分，然后再发送矩形中的任何内容以进行 OCR 识别。
EDIT2
由于我们的 Whosebug 成员，我现在已经确定了问题，现在我正在尝试添加图像 rectification/image 环绕技术来检索直接的前视图，从而使系统更准确。即将更新。
EDIT3
经过一定的错误修复，减少约束，同时允许函数在原始图像上绘制，我得到了以下结果。同时附上更新后的代码。
import cv2 as cv
import numpy as np
import pytesseract as pytess
from pytesseract import Output
# input of img source
img = cv.imread(r"C:\Users\User\Desktop\dataset\p\Image_31.jpg")
# necessary image color conversion
img2 = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
# edges store the canny version of img
edges = cv.Canny(img2, 100, 200)
# ker as in kernel
# (5, 5) is the matrix while uint8 is datatype
ker = np.ones((3, 3), np.uint8)
# dil as in dilation
# edges as the src, ker is the kernel we set above, number of dilation
dil = cv.dilate(edges, ker, iterations=1)
# setup pytesseract parameters
configs = r'--oem 3 --psm 6'
# feed image to tesseract
result = pytess.image_to_data(dil, output_type=Output.DICT, config=configs, lang='eng')
# number of boxes that encapsulate the boxes
boxes = len(result['text'])
# make a new copy of edges
new_item = dil.copy()
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 0: #removed constraints
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
# draw rectangle boxes on the original img
cv.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
# Crop the image
crp = new_item[y:y + h, x:x + w]
# OCR
txt = pytess.image_to_string(crp, config=configs)
# returns recognised text
print(txt)
cv.imshow("capturedText", crp)
cv.waitKey(0)
# cv.imshow("original", img)
# cv.imshow("canny", edges)
# cv.imshow("dilation", dil)
cv.imshow("results", img)
cv.waitKey(0)
cv.destroyAllWindows()
我认为您在这里寻找的是 python 中的 image rectificaiton (warping image to make it look like taken from another point of view) and there seem to be tool。但是，问题变得更加复杂，因为在您的情况下，您需要检测如何纠正它。我不确定你应该怎么做。
您已在图片中找到所有检测到的文字：
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 30:
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
new_item = cv.rectangle(new_item, (x, y), (x + w, y + h), (0, 255, 0), 2)
但是你也说现在的置信度应该在70%以上。
- 如果我们移除约束
- 如果我们对每个新项目进行 OCR
结果将是：
现在如果你阅读：
txt = pytesseract.image_to_string(new_item, config="--psm 6")
print(txt)
OCR 将为：
Meeting Room §
当前pytesseract版本的输出0.3.7
代码：
# Load the libraries
import cv2
import pytesseract
# Load the image
img = cv2.imread("fsUSw.png")
# Convert it to the gray-scale
gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# OCR detection
d = pytesseract.image_to_data(gry, config="--psm 6", output_type=pytesseract.Output.DICT)
# Get ROI part from the detection
n_boxes = len(d['level'])
# For each detected part
for i in range(1, 2):
# Get the localized region
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
# Draw rectangle to the detected region
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 5)
# Crop the image
crp = gry[y:y + h, x:x + w]
# OCR
txt = pytesseract.image_to_string(crp, config="--psm 6")
print(txt)
# Display the cropped image
cv2.imshow("crp", crp)
cv2.waitKey(0)
# Display
cv2.imshow("img", img)
cv2.waitKey(0)
我对 OpenCv 和 tesseract 还很陌生。我最近正在构建一个使用计算机视觉检测门标签的项目。希望对视障人士有所帮助
程序的思路是对输入图像进行预处理，将其转换为二值颜色，然后使用canny edge检测门标的轮廓，然后对canny edge结果进行膨胀。在这些之后，将图像提供给 tesseract，同时尝试显示用框检测到的文本。
预期结果是文本上的绿色矩形。在打印文本本身时。
问题是缺少矩形和文本检测失败。
我试过这些：
- Recognize Text in images using Canny Edge detection in Opencv
问题和解决方案太简单或不相关。有些也不在 python 中。
下面附上我对代码的尝试：
import pytesseract as pytess
import cv2 as cv
import numpy as np
from PIL import Image
from pytesseract import Output
img = cv.imread(r"C:\Users\User\Desktop\dataset\p\Image_31.jpg", 0)
# edges store the canny version of img
edges = cv.Canny(img, 100, 200)
# ker as in kernel
# (5, 5) is the matrix while uint8 is datatype
ker = np.ones((3, 3), np.uint8)
# dil as in dilation
# edges as the src, ker is the kernel we set above, number of dilation
dil = cv.dilate(edges, ker, iterations=1)
# setup pytesseract parameters
configs = r'--oem 3 --psm 6'
# feed image to tesseract
result = pytess.image_to_data(dil, output_type=Output.DICT, config=configs, lang='eng')
print(result.keys())
boxes = len(result['text'])
# make a new copy of edges
new_item = dil.copy()
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 30: # removed constraints
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
new_item = cv.rectangle(new_item, (x, y), (x + w, y + h), (0, 255, 0), 2)
# detect sentence with tesseract
# pending as rectangle not achieved
cv.imshow("original", img)
cv.imshow("canny", edges)
cv.imshow("dilation", dil)
cv.imshow("capturedText", new_item)
#ignore below this line, it is only for testing
#testobj = Image.fromarray(dil)
#testtext = pytess.image_to_string(testobj, lang='eng')
#print(testtext)
cv.waitKey(0)
cv.destroyAllWindows()
结果图像：
代码的测试部分return结果如下图：
a)
Meets
其中，显然不满足objective.
编辑
发布问题后，我意识到我一开始可能做错了。我应该尝试使用 OpencV 来检测门标签的轮廓并隔离包含文本的部分，然后再发送矩形中的任何内容以进行 OCR 识别。
EDIT2
由于我们的 Whosebug 成员，我现在已经确定了问题，现在我正在尝试添加图像 rectification/image 环绕技术来检索直接的前视图，从而使系统更准确。即将更新。
EDIT3
经过一定的错误修复，减少约束，同时允许函数在原始图像上绘制，我得到了以下结果。同时附上更新后的代码。
import cv2 as cv
import numpy as np
import pytesseract as pytess
from pytesseract import Output
# input of img source
img = cv.imread(r"C:\Users\User\Desktop\dataset\p\Image_31.jpg")
# necessary image color conversion
img2 = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
# edges store the canny version of img
edges = cv.Canny(img2, 100, 200)
# ker as in kernel
# (5, 5) is the matrix while uint8 is datatype
ker = np.ones((3, 3), np.uint8)
# dil as in dilation
# edges as the src, ker is the kernel we set above, number of dilation
dil = cv.dilate(edges, ker, iterations=1)
# setup pytesseract parameters
configs = r'--oem 3 --psm 6'
# feed image to tesseract
result = pytess.image_to_data(dil, output_type=Output.DICT, config=configs, lang='eng')
# number of boxes that encapsulate the boxes
boxes = len(result['text'])
# make a new copy of edges
new_item = dil.copy()
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 0: #removed constraints
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
# draw rectangle boxes on the original img
cv.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
# Crop the image
crp = new_item[y:y + h, x:x + w]
# OCR
txt = pytess.image_to_string(crp, config=configs)
# returns recognised text
print(txt)
cv.imshow("capturedText", crp)
cv.waitKey(0)
# cv.imshow("original", img)
# cv.imshow("canny", edges)
# cv.imshow("dilation", dil)
cv.imshow("results", img)
cv.waitKey(0)
cv.destroyAllWindows()
我认为您在这里寻找的是 python 中的 image rectificaiton (warping image to make it look like taken from another point of view) and there seem to be tool。但是，问题变得更加复杂，因为在您的情况下，您需要检测如何纠正它。我不确定你应该怎么做。
您已在图片中找到所有检测到的文字：
for sequence_number in range(boxes):
if int(result['conf'][sequence_number]) > 30:
(x, y, w, h) = (result['left'][sequence_number], result['top'][sequence_number],
result['width'][sequence_number], result['height'][sequence_number])
new_item = cv.rectangle(new_item, (x, y), (x + w, y + h), (0, 255, 0), 2)
但是你也说现在的置信度应该在70%以上。
- 如果我们移除约束
- 如果我们对每个新项目进行 OCR
结果将是：
现在如果你阅读：
txt = pytesseract.image_to_string(new_item, config="--psm 6")
print(txt)
OCR 将为：
Meeting Room §
当前pytesseract版本的输出0.3.7
代码：
# Load the libraries
import cv2
import pytesseract
# Load the image
img = cv2.imread("fsUSw.png")
# Convert it to the gray-scale
gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# OCR detection
d = pytesseract.image_to_data(gry, config="--psm 6", output_type=pytesseract.Output.DICT)
# Get ROI part from the detection
n_boxes = len(d['level'])
# For each detected part
for i in range(1, 2):
# Get the localized region
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
# Draw rectangle to the detected region
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 5)
# Crop the image
crp = gry[y:y + h, x:x + w]
# OCR
txt = pytesseract.image_to_string(crp, config="--psm 6")
print(txt)
# Display the cropped image
cv2.imshow("crp", crp)
cv2.waitKey(0)
# Display
cv2.imshow("img", img)
cv2.waitKey(0)