从身份证提取脸部矩形

Question

我正在研究从ID卡提取信息的主题，并且找到了一种合适的算法来将脸部定位在正面。实际上，OpenCV为此具有Haar级联，但是我不确定可以用来提取人所在的完整矩形而不是仅提取人脸的完整矩形（就像在https://github.com/deepc94/photo-id-ocr中所做的那样）。我尚未测试的一些想法是：

1. 找到包含正面rect的卡片内的第二大矩形
2. 对面部矩形进行“爆炸”，直到其到达边界
3. 试玩过滤器以查看可以看到的内容

还有什么可以推荐在这里尝试的呢？任何想法，想法甚至现有示例都可以。

Answer 1

常规方法：

import cv2
import numpy as np
import matplotlib.pyplot as plt

image = cv2.imread("a.jpg")

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
_,thresh = cv2.threshold(gray,128,255,cv2.THRESH_BINARY)
cv2.imshow("thresh",thresh)

thresh = cv2.bitwise_not(thresh)

element = cv2.getStructuringElement(shape=cv2.MORPH_RECT, ksize=(7, 7))

dilate = cv2.dilate(thresh,element,6)
cv2.imshow("dilate",dilate)
erode = cv2.erode(dilate,element,6)
cv2.imshow("erode",erode)

morph_img = thresh.copy()
cv2.morphologyEx(src=erode, op=cv2.MORPH_CLOSE, kernel=element, dst=morph_img)
cv2.imshow("morph_img",morph_img)

_,contours,_ = cv2.findContours(morph_img,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)

areas = [cv2.contourArea(c) for c in contours]

sorted_areas = np.sort(areas)
cnt=contours[areas.index(sorted_areas[-3])] #the third biggest contour is the face
r = cv2.boundingRect(cnt)
cv2.rectangle(image,(r[0],r[1]),(r[0]+r[2],r[1]+r[3]),(0,0,255),2)

cv2.imshow("img",image)
cv2.waitKey(0)
cv2.destroyAllWindows()

我发现前两个最大轮廓是边界，第三个最大轮廓是脸。结果：

还有另一种方法来研究图像，即使用各轴的像素值之和：

x_hist = np.sum(morph_img,axis=0).tolist() 
plt.plot(x_hist)
plt.ylabel('sum of pixel values by X-axis')
plt.show()

y_hist = np.sum(morph_img,axis=1).tolist()
plt.plot(y_hist)
plt.ylabel('sum of pixel values by Y-axis')
plt.show()

基于2个像素以上的像素总和，您可以通过设置阈值来裁剪所需的区域。

Answer 2

更新到@Sanix 更暗的代码，

# Using cascade Classifiers
import numpy as np
import cv2

img = cv2.imread('link_to_your_image')
face_classifier = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

scale_percent = 60 # percent of original size
width = int(img.shape[1] * scale_percent / 100)
height = int(img.shape[0] * scale_percent / 100)
dim = (width, height)
  
# resize image
image = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# face classifier
faces = face_classifier.detectMultiScale(gray, 1.3, 5)
# When no faces detected, face_classifier returns and empty tuple
if faces is ():
    print("No faces found")

# We iterate through our faces array and draw a rectangle
# over each face in faces
for (x, y, w, h) in faces:
    x = x - 25 # Padding trick to take the whole face not just Haarcascades points
    y = y - 40 # Same here...
    cv2.rectangle(image, (x, y), (x + w + 50, y + h + 70), (27, 200, 10), 2)
    cv2.imshow('Face Detection', image)
    cv2.waitKey(0)

cv2.destroyAllWindows()
# if you want to crop the face use below code
for (x, y, width, height) in faces:
    roi = image[y:y+height, x:x+width]
    cv2.imwrite("face.png", roi)

Answer 3

Ha级联方法（最简单）

# Using cascade Classifiers
import numpy as np
import cv2

# We point OpenCV's CascadeClassifier function to where our 
# classifier (XML file format) is stored
face_classifier = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

# Load our image then convert it to grayscale
image = cv2.imread('./your/image/path.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

cv2.imshow('Original image', image)

# Our classifier returns the ROI of the detected face as a tuple
# It stores the top left coordinate and the bottom right coordiantes
faces = face_classifier.detectMultiScale(gray, 1.3, 5)

# When no faces detected, face_classifier returns and empty tuple
if faces is ():
    print("No faces found")

# We iterate through our faces array and draw a rectangle
# over each face in faces
for (x, y, w, h) in faces:
    x = x - 25 # Padding trick to take the whole face not just Haarcascades points
    y = y - 40 # Same here...
    cv2.rectangle(image, (x, y), (x + w + 50, y + h + 70), (27, 200, 10), 2)
    cv2.imshow('Face Detection', image)
    cv2.waitKey(0)

cv2.destroyAllWindows()

链接到haarcascade_frontalface_default file