python - 我如何检测识别形状中的文本

Question

需要你的帮助。现在我正在编写 python 脚本来识别形状中的文本。可以从任何角度从 RTSP(IP 摄像机)捕获此形状。 有关示例，请参见附件。我的代码在这里，但是裁剪旋转形状的坐标是手动设置的

import cv2
import numpy as np


def main():
    fn  = cv2.VideoCapture("rtsp://admin:Admin123-@172.16.10.254")
    flag, img = fn.read()
    cnt = np.array([
            [[64, 49]],
            [[122, 11]],
            [[391, 326]],
            [[308, 373]]
        ])
    print("shape of cnt: {}".format(cnt.shape))
    rect = cv2.minAreaRect(cnt)
    print("rect: {}".format(rect))

    box = cv2.boxPoints(rect)
    box = np.int0(box)

    print("bounding box: {}".format(box))
    cv2.drawContours(img, [box], 0, (0, 255, 0), 2)

    img_crop, img_rot = crop_rect(img, rect)

    print("size of original img: {}".format(img.shape))
    print("size of rotated img: {}".format(img_rot.shape))
    print("size of cropped img: {}".format(img_crop.shape))

    new_size = (int(img_rot.shape[1]/2), int(img_rot.shape[0]/2))
    img_rot_resized = cv2.resize(img_rot, new_size)
    new_size = (int(img.shape[1]/2)), int(img.shape[0]/2)
    img_resized = cv2.resize(img, new_size)

    cv2.imshow("original contour", img_resized)
    cv2.imshow("rotated image", img_rot_resized)
    cv2.imshow("cropped_box", img_crop)

    # cv2.imwrite("crop_img1.jpg", img_crop)
    cv2.waitKey(0)

def crop_rect(img, rect):
    # get the parameter of the small rectangle
    center = rect[0]
    size = rect[1]
    angle = rect[2]
    center, size = tuple(map(int, center)), tuple(map(int, size))

# get row and col num in img
height, width = img.shape[0], img.shape[1]
print("width: {}, height: {}".format(width, height))

M = cv2.getRotationMatrix2D(center, angle, 1)
img_rot = cv2.warpAffine(img, M, (width, height))

img_crop = cv2.getRectSubPix(img_rot, size, center)

return img_crop, img_rot


if __name__ == "__main__":
    main()

example pic

Answer 1

您可以从 following post 中的示例开始.
代码示例会检测车牌，还会检测带有文本的“形状”。

在检测到文本的“形状”后，您可以使用以下阶段:

• 对裁剪区域应用阈值。
• 求等高线，求出面积最大的等高线。
• 构建 mask ， mask 轮廓外的区域(如车牌示例)。
• 使用 minAreaRect(如 fmw42 评论的那样)，并获取矩形的角度。
• 旋转裁剪区域(angle+90 度)。
• 使用 pytesseract.image_to_string 应用 OCR。

---

完整代码如下:

import cv2
import numpy as np
import imutils
import pytesseract

pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'  # I am using Windows

# Read the input image
img = cv2.imread('Admin123.jpg')

# Reused code:
# https://stackoverflow.com/questions/60977964/pytesseract-not-recognizing-text-as-expected/60979089#60979089
################################################################################
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #convert to grey scale
gray = cv2.bilateralFilter(gray, 11, 17, 17)
edged = cv2.Canny(gray, 30, 200) #Perform Edge detection

cnts = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None

# loop over our contours
for c in cnts:
    # approximate the contour
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.018 * peri, True)
    # if our approximated contour has four points, then
    # we can assume that we have found our screen
    if len(approx) == 4:
        screenCnt = approx
        break

# Masking the part other than the "shape"
mask = np.zeros(gray.shape,np.uint8)
new_image = cv2.drawContours(mask,[screenCnt],0,255,-1,)
new_image = cv2.bitwise_and(img,img,mask=mask)

# Now crop
(x, y) = np.where(mask == 255)
(topx, topy) = (np.min(x), np.min(y))
(bottomx, bottomy) = (np.max(x), np.max(y))
cropped = gray[topx:bottomx+1, topy:bottomy+1]
################################################################################

# Apply threshold the cropped area
_, thresh = cv2.threshold(cropped, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)

# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnts = imutils.grab_contours(cnts)

# Get contour with maximum area
c = max(cnts, key=cv2.contourArea)

# Build a mask (same as the code above)
mask = np.zeros(cropped.shape, np.uint8)
new_cropped = cv2.drawContours(mask, [c], 0, 255, -1)
new_cropped = cv2.bitwise_and(cropped, cropped, mask=mask)

# Draw green rectangle for testing
test = cv2.cvtColor(new_cropped, cv2.COLOR_GRAY2BGR)
cv2.drawContours(test, [c], -1, (0, 255, 0), thickness=2)

# Use minAreaRect as fmw42 commented
rect = cv2.minAreaRect(c)
angle = rect[2]  # Get angle of the rectangle

# Rotate the cropped rectangle.
rotated_cropped = imutils.rotate(new_cropped, angle + 90)

# Read the text in the "shape"
text = pytesseract.image_to_string(rotated_cropped, config='--psm 3')
print("Extracted text is:\n\n", text)

# Show images for testing:
cv2.imshow('cropped', cropped)
cv2.imshow('thresh', thresh)
cv2.imshow('test', test)
cv2.imshow('rotated_cropped', rotated_cropped)
cv2.waitKey(0)
cv2.destroyAllWindows()

---

OCR输出结果:

 AB12345
DEPARTMENT OF
INFORMATION

COMMUNICATION
TECHNOLOGY

---

裁剪:

阈值:

测试:

rotated_cropped: