文档扫描OCR识别-1（python）
工具包导入
import numpy as np
import cv2
1
2
函数设定
# 四边形坐标求解
def order_points(pts):
# 一共 4 个坐标点
rect = np.zeros((4, 2), dtype = "float32")
# 按顺序找到对应坐标 0123 分别是 左上，右上，右下，左下
# 计算左上，右下
s = pts.sum(axis = 1)
rect[0] = pts[np.argmin(s)]
rect[2] = pts[np.argmax(s)]
# 计算右上和左下
diff = np.diff(pts, axis = 1)
rect[1] = pts[np.argmin(diff)]
rect[3] = pts[np.argmax(diff)]
return rect
# 获取输入坐标点
def four_point_transform(image, pts):
rect = order_points(pts)
(tl, tr, br, bl) = rect
# 计算输入的 w 和 h 值
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 透视变换 -- 二维升三维再降维 齐次坐标 : 用 N+1 维来代表 N 维坐标 [kx,ky,k]
M = cv2.getPerspectiveTransform(rect, dst)
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
# 返回变换后结果
return warped
def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
dim = None
(h, w) = image.shape[:2]
if width is None and height is None:
return image
if width is None:
r = height / float(h)
dim = (int(w * r), height)
else:
r = width / float(w)
dim = (width, int(h * r))
resized = cv2.resize(image, dim, interpolation=inter)
return resized
读取输入
image = cv2.imread('images/receipt.jpg')
1
边缘检测
ratio = image.shape[0] / 500.0
# image.shape[0], 图片垂直尺寸
# image.shape[1], 图片水平尺寸
# image.shape[2], 图片通道数
orig = image.copy()
image = resize(orig, height=500) # 等比例缩放
# 预处理
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0) # 去除噪音点
edged = cv2.Canny(gray, 75, 200) # 边缘检测
# 展示预处理结果
print("STEP 1: 边缘检测 ")
cv2.imshow("Image", image)
cv2.imshow("Edged", edged)
cv2.waitKey(0)
cv2.destroyAllWindows()
获取轮廓
# 轮廓检测
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5] # 选取前五个 , 最大的轮廓
# 遍历轮廓
for c in cnts:
# 计算轮廓近似
peri = cv2.arcLength(c, True) # retval=cv.arcLength(curve, closed) retval 返回值，轮廓的周长 closed 曲线是是否闭合
# C 表示输入的点集
# epsilon 表示从原始轮廓到近似轮廓的最大距离，外汇跟单gendan5.com它是一个准确度参数
# True 表示封闭的
approx = cv2.approxPolyDP(c, 0.02 * peri, True) # 轮廓 , 轮廓精度 , 越小可能是多边形 , 越大可能是矩形
# 4 个点的时候就拿出来
if len(approx) == 4:
screenCnt = approx
# print(screenCnt) # 四个点的坐标
break
# 展示结果
print("STEP 2: 获取轮廓 ")
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
cv2.imshow("Outline", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
变换
# 透视变换
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
# 二值处理
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)
# 展示结果
print("STEP 3: 变换 ")
cv2.imshow("Original", resize(orig, height = 650))
cv2.imshow("Scanned", resize(ref, height = 650))
cv2.waitKey(0)