基于Python+OpenCV实现文档扫描与OCR识别系统

def order_points(pts):
    # 初始化4个坐标点
    rect = np.zeros((4, 2), dtype = "float32")
    
    # 按顺序找到对应坐标：左上、右上、右下、左下
    s = pts.sum(axis = 1)
    rect[0] = pts[np.argmin(s)]  # 左上：x+y最小
    rect[2] = pts[np.argmax(s)]  # 右下：x+y最大
    
    diff = np.diff(pts, axis = 1)
    rect[1] = pts[np.argmin(diff)]  # 右上：x-y最小
    rect[3] = pts[np.argmax(diff)]  # 左下：x-y最大
    
    return rect

def four_point_transform(image, pts):
    rect = order_points(pts)
    (tl, tr, br, bl) = rect
    
    # 计算目标宽度和高度
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))
    
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))
    
    # 变换后对应坐标位置
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype = "float32")
    
    # 计算变换矩阵
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    
    return warped

# 1. 读取图像并缩放
image = cv2.imread(args["image"])
ratio = image.shape[0] / 500.0
orig = image.copy()
image = resize(orig, height = 500)

# 2. 边缘检测
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(gray, 75, 200)

# 3. 轮廓检测
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[0]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]

# 4. 找到四边形轮廓
for c in cnts:
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.02 * peri, True)
    if len(approx) == 4:
        screenCnt = approx
        break

# 5. 透视变换和二值化
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)

from PIL import Image
import pytesseract
import cv2
import os

preprocess = 'blur'  # thresh

image = cv2.imread('scan.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# 预处理
if preprocess == "thresh":
    gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
elif preprocess == "blur":
    gray = cv2.medianBlur(gray, 3)

# 调用Tesseract OCR
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
pytesseract.pytesseract.tesseract_cmd = r'./Tesseract-OCR/tesseract.exe'
text = pytesseract.image_to_string(Image.open(filename))
print(text)
os.remove(filename)

pip install numpy opencv-python pytesseract pillow

# 使用默认图像
python scan.py
​
# 指定输入图像
python scan.py -i images/page.jpg

python test.py

text = pytesseract.image_to_string(Image.open(filename), lang='chi_sim')