Wen/scan.py

# 导入工具包
import numpy as np
import argparse
import cv2
import pytesseract
import os
from PIL import Image

# def process_image(image_path):
#     try:
#         # 使用Pillow库打开并显示图片
#         with Image.open(image_path) as img:
#             img.show()
#             # 在这里添加更多处理图片的代码...
#     except IOError:
#         print(f"无法打开图片: {image_path}")

def main():
    parser = argparse.ArgumentParser(description="处理图片的脚本")
    parser.add_argument("-i", "--image", required=True, help="指定要处理的图片的路径")
    args = parser.parse_args()
    # process_image(args.image)
    print("main")

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

def four_point_transform(image, pts):
	# 获取输入坐标点
	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
	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

# 设置参数
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True,
	help = "Path to the image to be scanned")
args = vars(ap.parse_args())
print("arg")

print(__name__)
if __name__ == "__main__":
    main()

# 读取输入
image = cv2.imread(args["image"])
#坐标也会相同变化
ratio = image.shape[0] / 500.0
orig = image.copy()
image = resize(orig, height = 500)

# 预处理
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # 色彩空间转换
gray = cv2.GaussianBlur(gray, (5, 5), 0)  # 高斯模糊
edged = cv2.Canny(gray, 75, 200)

# 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()

# 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]  # 降序排列+切片

# 遍历轮廓
for c in cnts:
	# 计算轮廓近似
	peri = cv2.arcLength(c, True)
	# C表示输入的点集（数组）
	# epsilon表示从原始轮廓到近似轮廓的最大距离，它是一个准确度参数
	# True表示封闭的
	approx = cv2.approxPolyDP(c, 0.10 * peri, True)  # 近似

	# 4个点的时候就拿出来
	if len(approx) == 4:
		screenCnt = approx
		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()

# 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)
# cv2.destroyAllWindows()

# OCR扫描
preprocess = "blur"

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

filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
text = pytesseract.image_to_string(Image.open(filename))  # 调用Tesseract OCR引擎对保存的图像进行文本识别
os.remove(filename)

encodings = ['utf-8', 'latin1', 'iso-8859-1', 'cp1252', 'gbk', 'big5']
for encoding in encodings:
	try:
		with open("out.txt", 'w', encoding=encoding, errors="replace") as file:
			file.write(text)
			break
	except UnicodeDecodeError:
		continue
file.close()
print("text is written to out.txt")

# Wait for pressing any key
cv2.waitKey(0)
cv2.destroyAllWindows()