111 lines
3.9 KiB
Python
111 lines
3.9 KiB
Python
import cv2
|
||
import numpy as np
|
||
from sklearn.cluster import KMeans
|
||
from PIL import Image, ImageOps
|
||
import matplotlib.pyplot as plt
|
||
|
||
# 定义函数，透视变换
|
||
import cv2
|
||
import numpy as np
|
||
|
||
import cv2
|
||
import numpy as np
|
||
|
||
def perspective_transform(img_path):
|
||
# 通过cv2加载图片
|
||
img = cv2.imread(img_path)
|
||
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
|
||
# 复制图片
|
||
img_copy = img.copy()
|
||
# 将图片转灰度图
|
||
img_copy = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
|
||
# 二值化
|
||
# 使用OTSU阈值算法将灰度图转换为二值图
|
||
_, binary_image = cv2.threshold(img_copy, 127, 255, cv2.THRESH_OTSU)
|
||
# inverted_binary_image = cv2.bitwise_not(binary_image)
|
||
# 黑白颜色反转
|
||
img_copy = cv2.bitwise_not(img_copy)
|
||
|
||
plt.title("Original Image")
|
||
plt.imshow(img_copy, cmap='gray')
|
||
plt.show()
|
||
|
||
wechatqr = cv2.wechat_qrcode.WeChatQRCode("wechat_qrcode/detect.prototxt", "wechat_qrcode/detect.caffemodel",
|
||
"wechat_qrcode/sr.prototxt", "wechat_qrcode/sr.caffemodel")
|
||
res, points = wechatqr.detectAndDecode(binary_image)
|
||
# 在原图上标记二维码的角点
|
||
if len(res) > 0:
|
||
print(res)
|
||
# for point in points[0]:
|
||
# cv2.circle(img, tuple(int(i) for i in point), 10, (255, 0, 0), -1) # 红色圆点，半径为10
|
||
|
||
point = points[0]
|
||
width = max(np.linalg.norm(point[0] - point[1]), np.linalg.norm(point[2] - point[3]))
|
||
height = max(np.linalg.norm(point[1] - point[2]), np.linalg.norm(point[3] - point[0]))
|
||
# 不添加边距
|
||
points_dst = np.array([[0, 0], [width, 0], [width, height], [0, height]], dtype=point.dtype)
|
||
# 生成变换矩阵
|
||
matrix = cv2.getPerspectiveTransform(point, points_dst)
|
||
# 应用透视变换，纠正图像
|
||
corrected_image = cv2.warpPerspective(img, matrix, (int(width), int(height)))
|
||
|
||
return corrected_image, img # 返回校正后的图像和标记后的原图
|
||
|
||
return None, img # 如果没有检测到二维码，仅返回原图
|
||
|
||
def perfect_reflectance_white_balance(img):
|
||
# 将图像从 BGR 转换到 LAB 色彩空间
|
||
lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
|
||
|
||
# 分离 L, A, B 通道
|
||
l, a, b = cv2.split(lab)
|
||
|
||
# 寻找图像中的最亮区域（假设这些是白色区域）
|
||
max_lightness = np.max(l)
|
||
L_white = np.where(l == max_lightness)
|
||
|
||
# 计算这些区域在 A 和 B 通道上的平均值
|
||
a_white_avg = np.mean(a[L_white])
|
||
b_white_avg = np.mean(b[L_white])
|
||
|
||
# 适当调整 A 和 B 通道的平均值，避免过度调整
|
||
a_shift = (128 - a_white_avg) * 0.1 # 减少调整幅度
|
||
b_shift = (128 - b_white_avg) * 0.1 # 减少调整幅度
|
||
a = a.astype(np.float32) + a_shift
|
||
b = b.astype(np.float32) + b_shift
|
||
|
||
# 确保 a, b 范围在 0 到 255 之间，并转换回 uint8 类型
|
||
a = np.clip(a, 0, 255).astype(np.uint8)
|
||
b = np.clip(b, 0, 255).astype(np.uint8)
|
||
|
||
# 重新合成 LAB 图像并转换回 BGR 色彩空间
|
||
lab = cv2.merge([l, a, b])
|
||
corrected_image = cv2.cvtColor(lab, cv2.COLOR_LAB2BGR)
|
||
|
||
return corrected_image
|
||
|
||
|
||
corrected_image, img = perspective_transform("IMG_3606.png")
|
||
|
||
# 判断corrected_image不为空
|
||
if corrected_image is not None:
|
||
# 保存图片文件
|
||
corrected_image_bgr = cv2.cvtColor(corrected_image, cv2.COLOR_RGB2BGR)
|
||
cv2.imwrite("corrected_image.png", corrected_image_bgr)
|
||
# 通过 PIL 显示图片
|
||
plt.title("Original Image")
|
||
plt.imshow(corrected_image, cmap='gray')
|
||
plt.show()
|
||
else:
|
||
print("目标无法识别")
|
||
|
||
# # 读取图像
|
||
# image = cv2.imread('corrected_image.png')
|
||
# # 应用完美反射白平衡算法
|
||
# white_balanced_image = perfect_reflectance_white_balance(image)
|
||
#
|
||
# # 显示结果
|
||
# cv2.imshow('Original Image', image)
|
||
# cv2.imshow('White Balanced Image', white_balanced_image)
|
||
# cv2.waitKey(0)
|
||
# cv2.destroyAllWindows() |