使用字典学习进行图像去噪#

一个示例，比较了分别使用在线字典学习和各种变换方法重建浣熊面部图像的噪声片段的效果。

在图像扭曲的左半部分拟合字典，然后用于重建右半部分。请注意，通过拟合未失真（即无噪声）图像可以获得更好的性能，但这里我们从假设它不可用的情况开始。

评估图像去噪结果的常见做法是查看重建图像与原始图像之间的差异。如果重建是完美的，这看起来像高斯噪声。

从图中可以看出，具有两个非零系数的正交匹配追踪 (OMP) 的结果比仅保留一个系数（边缘看起来不太突出）的偏差略小。此外，它在 Frobenius 范数中更接近于真实值。

最小角回归的结果偏差更大：差异让人联想到原始图像的局部强度值。

阈值化显然不利于去噪，但它在这里是为了表明它可以以非常高的速度产生提示性输出，因此可用于其他任务，例如对象分类，其中性能不一定与可视化相关。

生成失真图像#

import numpy as np

try:  # Scipy >= 1.10
    from scipy.datasets import face
except ImportError:
    from scipy.misc import face

raccoon_face = face(gray=True)

# Convert from uint8 representation with values between 0 and 255 to
# a floating point representation with values between 0 and 1.
raccoon_face = raccoon_face / 255.0

# downsample for higher speed
raccoon_face = (
    raccoon_face[::4, ::4]
    + raccoon_face[1::4, ::4]
    + raccoon_face[::4, 1::4]
    + raccoon_face[1::4, 1::4]
)
raccoon_face /= 4.0
height, width = raccoon_face.shape

# Distort the right half of the image
print("Distorting image...")
distorted = raccoon_face.copy()
distorted[:, width // 2 :] += 0.075 * np.random.randn(height, width // 2)

Distorting image...

显示失真图像#

import matplotlib.pyplot as plt


def show_with_diff(image, reference, title):
    """Helper function to display denoising"""
    plt.figure(figsize=(5, 3.3))
    plt.subplot(1, 2, 1)
    plt.title("Image")
    plt.imshow(image, vmin=0, vmax=1, cmap=plt.cm.gray, interpolation="nearest")
    plt.xticks(())
    plt.yticks(())
    plt.subplot(1, 2, 2)
    difference = image - reference

    plt.title("Difference (norm: %.2f)" % np.sqrt(np.sum(difference**2)))
    plt.imshow(
        difference, vmin=-0.5, vmax=0.5, cmap=plt.cm.PuOr, interpolation="nearest"
    )
    plt.xticks(())
    plt.yticks(())
    plt.suptitle(title, size=16)
    plt.subplots_adjust(0.02, 0.02, 0.98, 0.79, 0.02, 0.2)


show_with_diff(distorted, raccoon_face, "Distorted image")

Distorted image, Image, Difference (norm: 11.71)

提取参考块#

from time import time

from sklearn.feature_extraction.image import extract_patches_2d

# Extract all reference patches from the left half of the image
print("Extracting reference patches...")
t0 = time()
patch_size = (7, 7)
data = extract_patches_2d(distorted[:, : width // 2], patch_size)
data = data.reshape(data.shape[0], -1)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0)
print(f"{data.shape[0]} patches extracted in %.2fs." % (time() - t0))

Extracting reference patches...
22692 patches extracted in 0.01s.

从参考块中学习字典#

from sklearn.decomposition import MiniBatchDictionaryLearning

print("Learning the dictionary...")
t0 = time()
dico = MiniBatchDictionaryLearning(
    # increase to 300 for higher quality results at the cost of slower
    # training times.
    n_components=50,
    batch_size=200,
    alpha=1.0,
    max_iter=10,
)
V = dico.fit(data).components_
dt = time() - t0
print(f"{dico.n_iter_} iterations / {dico.n_steps_} steps in {dt:.2f}.")

plt.figure(figsize=(4.2, 4))
for i, comp in enumerate(V[:100]):
    plt.subplot(10, 10, i + 1)
    plt.imshow(comp.reshape(patch_size), cmap=plt.cm.gray_r, interpolation="nearest")
    plt.xticks(())
    plt.yticks(())
plt.suptitle(
    "Dictionary learned from face patches\n"
    + "Train time %.1fs on %d patches" % (dt, len(data)),
    fontsize=16,
)
plt.subplots_adjust(0.08, 0.02, 0.92, 0.85, 0.08, 0.23)

Dictionary learned from face patches Train time 17.8s on 22692 patches

Learning the dictionary...
2.0 iterations / 125 steps in 17.85.

提取噪声块并使用字典重建它们#

from sklearn.feature_extraction.image import reconstruct_from_patches_2d

print("Extracting noisy patches... ")
t0 = time()
data = extract_patches_2d(distorted[:, width // 2 :], patch_size)
data = data.reshape(data.shape[0], -1)
intercept = np.mean(data, axis=0)
data -= intercept
print("done in %.2fs." % (time() - t0))

transform_algorithms = [
    ("Orthogonal Matching Pursuit\n1 atom", "omp", {"transform_n_nonzero_coefs": 1}),
    ("Orthogonal Matching Pursuit\n2 atoms", "omp", {"transform_n_nonzero_coefs": 2}),
    ("Least-angle regression\n4 atoms", "lars", {"transform_n_nonzero_coefs": 4}),
    ("Thresholding\n alpha=0.1", "threshold", {"transform_alpha": 0.1}),
]

reconstructions = {}
for title, transform_algorithm, kwargs in transform_algorithms:
    print(title + "...")
    reconstructions[title] = raccoon_face.copy()
    t0 = time()
    dico.set_params(transform_algorithm=transform_algorithm, **kwargs)
    code = dico.transform(data)
    patches = np.dot(code, V)

    patches += intercept
    patches = patches.reshape(len(data), *patch_size)
    if transform_algorithm == "threshold":
        patches -= patches.min()
        patches /= patches.max()
    reconstructions[title][:, width // 2 :] = reconstruct_from_patches_2d(
        patches, (height, width // 2)
    )
    dt = time() - t0
    print("done in %.2fs." % dt)
    show_with_diff(reconstructions[title], raccoon_face, title + " (time: %.1fs)" % dt)

plt.show()

Extracting noisy patches...
done in 0.00s.
Orthogonal Matching Pursuit
1 atom...
done in 0.66s.
Orthogonal Matching Pursuit
2 atoms...
done in 1.30s.
Least-angle regression
4 atoms...
done in 9.15s.
Thresholding
 alpha=0.1...
done in 0.09s.

脚本总运行时间：（0 分 30.515 秒）