Compressive Sensing | Image Reconstruction | Sparse Signals

Introduction

This lab demonstrates the reconstruction of a sparse image from a set of parallel projections using compressive sensing. Compressive sensing is a technique for efficiently acquiring and reconstructing signals that are sparse in some domain. In this case, we are interested in reconstructing a 2D image from a small number of projections acquired along different angles. We will compare the performance of L1 and L2 penalization methods for this task.

VM Tips

After the VM startup is done, click the top left corner to switch to the Notebook tab to access Jupyter Notebook for practice.

Sometimes, you may need to wait a few seconds for Jupyter Notebook to finish loading. The validation of operations cannot be automated because of limitations in Jupyter Notebook.

If you face issues during learning, feel free to ask Labby. Provide feedback after the session, and we will promptly resolve the problem for you.

Import Libraries

In this step, we will import the necessary libraries.

import numpy as np
from scipy import sparse
from scipy import ndimage
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
import matplotlib.pyplot as plt

Define Helper Functions

In this step, we will define helper functions to generate the tomography design matrix and create synthetic binary data.

def _weights(x, dx=1, orig=0):
    x = np.ravel(x)
    floor_x = np.floor((x - orig) / dx).astype(np.int64)
    alpha = (x - orig - floor_x * dx) / dx
    return np.hstack((floor_x, floor_x + 1)), np.hstack((1 - alpha, alpha))

def _generate_center_coordinates(l_x):
    X, Y = np.mgrid[:l_x, :l_x].astype(np.float64)
    center = l_x / 2.0
    X += 0.5 - center
    Y += 0.5 - center
    return X, Y

def build_projection_operator(l_x, n_dir):
    X, Y = _generate_center_coordinates(l_x)
    angles = np.linspace(0, np.pi, n_dir, endpoint=False)
    data_inds, weights, camera_inds = [], [], []
    data_unravel_indices = np.arange(l_x**2)
    data_unravel_indices = np.hstack((data_unravel_indices, data_unravel_indices))
    for i, angle in enumerate(angles):
        Xrot = np.cos(angle) * X - np.sin(angle) * Y
        inds, w = _weights(Xrot, dx=1, orig=X.min())
        mask = np.logical_and(inds >= 0, inds < l_x)
        weights += list(w[mask])
        camera_inds += list(inds[mask] + i * l_x)
        data_inds += list(data_unravel_indices[mask])
    proj_operator = sparse.coo_matrix((weights, (camera_inds, data_inds)))
    return proj_operator

def generate_synthetic_data():
    rs = np.random.RandomState(0)
    n_pts = 36
    x, y = np.ogrid[0:l, 0:l]
    mask_outer = (x - l / 2.0) ** 2 + (y - l / 2.0) ** 2 < (l / 2.0) ** 2
    mask = np.zeros((l, l))
    points = l * rs.rand(2, n_pts)
    mask[(points[0]).astype(int), (points[1]).astype(int)] = 1
    mask = ndimage.gaussian_filter(mask, sigma=l / n_pts)
    res = np.logical_and(mask > mask.mean(), mask_outer)
    return np.logical_xor(res, ndimage.binary_erosion(res))

Generate Data

In this step, we will generate synthetic binary data and projections.

l = 128
proj_operator = build_projection_operator(l, l // 7)
data = generate_synthetic_data()
proj = proj_operator @ data.ravel()[:, np.newaxis]
proj += 0.15 * np.random.randn(*proj.shape)

Reconstruct Image with L2 Penalization

In this step, we will reconstruct the image using L2 (Ridge) penalization.

rgr_ridge = Ridge(alpha=0.2)
rgr_ridge.fit(proj_operator, proj.ravel())
rec_l2 = rgr_ridge.coef_.reshape(l, l)

Reconstruct Image with L1 Penalization

In this step, we will reconstruct the image using L1 (Lasso) penalization.

rgr_lasso = Lasso(alpha=0.001)
rgr_lasso.fit(proj_operator, proj.ravel())
rec_l1 = rgr_lasso.coef_.reshape(l, l)

Visualize Results

In this step, we will visualize the original image and the reconstructed images using L2 and L1 penalization.

plt.figure(figsize=(8, 3.3))
plt.subplot(131)
plt.imshow(data, cmap=plt.cm.gray, interpolation="nearest")
plt.axis("off")
plt.title("Original Image")
plt.subplot(132)
plt.imshow(rec_l2, cmap=plt.cm.gray, interpolation="nearest")
plt.title("L2 Penalization")
plt.axis("off")
plt.subplot(133)
plt.imshow(rec_l1, cmap=plt.cm.gray, interpolation="nearest")
plt.title("L1 Penalization")
plt.axis("off")

plt.subplots_adjust(hspace=0.01, wspace=0.01, top=1, bottom=0, left=0, right=1)

plt.show()

Summary

In this lab, we demonstrated the use of compressive sensing for reconstructing a 2D image from a small number of projections acquired along different angles. We compared the performance of L1 and L2 penalization methods and observed that L1 penalization produces a better result with less artifacts.

Compressive Sensing Image Reconstruction