上传文件至 /

这个提交包含在:
2025-11-23 08:29:10 +00:00
父节点 ebb5f13151
当前提交 71c93e9acf
共有 2 个文件被更改,包括 124 次插入 和 0 次删除

17
ysml.py 普通文件
查看文件

@ -0,0 +1,17 @@
import cv2
import numpy as np
import matplotlib.pyplot as plt
def laplacian_sharpen(image_path):
img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
laplacian = cv2.Laplacian(img, cv2.CV_64F)
sharpened = cv2.convertScaleAbs(img - laplacian)
return sharpened
# 读取图像
image = cv2.imread('ysmltest.png', cv2.IMREAD_GRAYSCALE)
sharp_laplacian = laplacian_sharpen('ysmltest.png')
#cv2.imshow('Original Image', image)
#cv2.imshow('Filtered Image', sharp_laplacian)
cv2.waitKey(0)
cv2.destroyAllWindows()

107
ysml01.py 普通文件
查看文件

@ -0,0 +1,107 @@
import cv2
import numpy as np
import matplotlib.pyplot as plt
import ysml as pill
import os
# 定义直方图均衡化函数
def histogram_equalization(image):
# 应用直方图均衡化
eq = cv2.equalizeHist(image)
return eq
# 定义自适应直方图均衡化函数
def adaptive_histogram_equalization(image):
# 创建 CLAHE 对象
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
# 应用自适应直方图均衡化
cl = clahe.apply(image)
return cl
# 定义 Gamma 校正函数
def gamma_correction(image, gamma=1.0):
inv_gamma = 1.0 / gamma
table = np.array([((i / 255.0) ** inv_gamma) * 255 for i in range(256)]).astype("uint8")
# 应用 Gamma 校正查找表
adjusted = cv2.LUT(image, table)
return adjusted
# 定义对比度拉伸函数
def contrast_stretching(image, low_percentile=2, high_percentile=98):
# 计算灰度级的百分位数
low_val = np.percentile(image, low_percentile)
high_val = np.percentile(image, high_percentile)
# 应用对比度拉伸
stretched = np.clip((image - low_val) * 255 / (high_val - low_val), 0, 255).astype(np.uint8)
return stretched
def save_processed_image_opencv(input_path, output_path, compression_params=None):
if compression_params is None:
compression_params = [cv2.IMWRITE_JPEG_QUALITY, 95]
try:
# 读取图片
img = cv2.imread(input_path)
if img is None:
raise ValueError("无法读取图片文件")
processed_img=pill.laplacian_sharpen(input_path)
# 确保输出目录存在
os.makedirs(os.path.dirname(output_path), exist_ok=True)
# 保存图片
cv2.imwrite(output_path, processed_img, compression_params)
print(f"图片已保存到: {output_path}")
except Exception as e:
print(f"处理图片时出错: {e}")
save_processed_image_opencv('ysmltest.png', 'output/processed_opencv.jpg')
# 读取原始图像
sharp_laplacian = pill.laplacian_sharpen('ysmltest.png')
image_path = ('output/processed_opencv.jpg')
img_gray = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
# 对灰度图像进行处理
enhanced_eq = histogram_equalization(img_gray)
enhanced_clahe = adaptive_histogram_equalization(img_gray)
enhanced_gamma = gamma_correction(img_gray, gamma=0.8)
enhanced_stretched = contrast_stretching(img_gray)
# 将处理后的灰度图像转换为彩色图像
enhanced_eq_color = cv2.cvtColor(enhanced_eq, cv2.COLOR_GRAY2RGB)
enhanced_clahe_color = cv2.cvtColor(enhanced_clahe, cv2.COLOR_GRAY2RGB)
enhanced_gamma_color = cv2.cvtColor(enhanced_gamma, cv2.COLOR_GRAY2RGB)
enhanced_stretched_color = cv2.cvtColor(enhanced_stretched, cv2.COLOR_GRAY2RGB)
# 展示图像
plt.figure(figsize=(12, 12))
#.subplot(3, 2, 1)
#plt.imshow(cv2.cvtColor(img_gray, cv2.COLOR_GRAY2RGB))
#plt.title('Original Grayscale Image')
#plt.axis('off')
#plt.subplot(3, 2, 2)
#plt.imshow(enhanced_eq_color)
#plt.title('Histogram Equalization')
#plt.axis('off')
#plt.subplot(3, 2, 3)
#plt.imshow(enhanced_clahe_color)
#plt.title('Adaptive Histogram Equalization')
#plt.axis('off')
#plt.subplot(3, 2, 4)
#plt.imshow(enhanced_gamma_color)
#plt.title('Gamma Correction')
#plt.axis('off')
#plt.subplot(3, 2, 5)
plt.imshow(enhanced_stretched_color)
plt.title('Contrast Stretching')
plt.axis('off')
plt.tight_layout()
plt.show()