Blur-Image is a compact image processing toolkit developed in Python, designed to improve image sharpness through advanced blurring techniques. Based on the Richardson-Lucy deconvolution algorithm, this toolkit allows users to apply different blur kernels and iterative enhancements to improve image quality.

• Blurring and sharpening: Implement Richardson-Lucy deconvolution for image blurring, as well as standard blurring techniques using different kernels.
• Batch image processing: Process entire directories of images for bulk blurring and sharpening.
• Quality measurements: Calculate and report the Peak Signal-to-Noise Ratio (PSNR) to measure the quality of processed images.
• Visual logging: Color-coded console for easy monitoring of processing steps.

Clone the repository to your local machine:

git clone https://github.com/mathusanm6/Blur-Image.git
cd Blur-Image

Ensure you have Python installed along with the following packages:

• numpy
• scipy
• pillow (PIL)

You can install the required packages via pip:

pip install numpy scipy pillow

After tuning the parameters in the core.py and blind_core.py files, you can run the toolkit using the following command:

python ./run.sh

Below are some examples of images processed by the Blur-Image toolkit, showing the original images, the blurred versions, and the deblurred outputs after applying various kernels and iteration counts.

Blurring are done using the following kernels:

• Average 3x3
• Average 5x5
• Average 11x11
• Gaussian 3x3, sigma: 1.0
• Gaussian 3x3, sigma: 2.0
• Gaussian 5x5, sigma: 1.0
• Gaussian 5x5, sigma: 2.0

Sharpening are done knowing the kernel used for blurring and the number of iterations using the Richardson-Lucy deconvolution algorithm as follows:

Input: Blurred image I, PSF P, number of iterations n_it
Output: Restored image J

# Initialize
J0 = I

# Iterative deconvolution
for n in range(1, n_it + 1):
    # Convolve Jn with P to obtain a blurred estimation I_estimated
    I_estimated = convolve(Jn, P)

    # Calculate the relative blur ratio
    Ratio = I / (I_estimated + epsilon)

    # Convolve this ratio with the mirror of the PSF
    Correction = convolve(Ratio, P_mirror)

    # Update the estimation
    Jn = Jn * Correction

# Return the final restored image
return Jn_it

Average 3x3	Average 5x5	Average 11x11	Gaussian 3x3, sigma: 1.0	Gaussian 3x3, sigma: 2.0	Gaussian 5x5, sigma: 1.0	Gaussian 5x5, sigma: 2.0
Blurred Images
Unblurred Images
5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations
10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations
15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations

Average 3x3	Average 5x5	Average 11x11	Gaussian 3x3, sigma: 1.0	Gaussian 3x3, sigma: 2.0	Gaussian 5x5, sigma: 1.0	Gaussian 5x5, sigma: 2.0
Blurred Images
Unblurred Images
5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations	5 Iterations
10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations	10 Iterations
15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations	15 Iterations

Sharpening are done not knowing the kernel used for blurring and the number of iterations using the Blind Richardson-Lucy deconvolution algorithm as follows:

Input: Blurred image I, initial PSF P, number of iterations for image n_it, number of iterations for PSF psf_it
Output: Restored image J, refined PSF P

# Initialize
J0 = I

# Iterative deconvolution
for n in range(1, n_it + 1):
    # Convolve Jn with P to obtain a blurred estimation I_estimated
    I_estimated = convolve(Jn, P)

    # Calculate the relative blur ratio
    Ratio = I / (I_estimated + epsilon)

    # Convolve this ratio with the mirror of the PSF
    Correction = convolve(Ratio, P_mirror)

    # Update the estimation
    Jn = Jn * Correction

    # PSF refinement
    for m in range(1, psf_it + 1):
        # Convolve Jn+1 with P to obtain a new blurred estimation I_estimated
        I_estimated = convolve(Jn, P)

        # Calculate the error ratio
        E = I / (I_estimated + epsilon)

        # Convolve this ratio with the mirror of the restored image Jn+1
        PSF_Update = convolve(E, Jn_mirror)

        # Update the PSF
        P = P * PSF_Update

        # Normalize the PSF
        P = P / sum(P)

# Return the final restored image and refined PSF
return Jn_it, P

Average 3x3	Average 5x5	Average 11x11	Gaussian 5x5, sigma: 1.0	Gaussian 5x5, sigma: 2.0
15 Iterations, 25 PSF Iterations	15 Iterations, 25 PSF Iterations	15 Iterations, 25 PSF Iterations	15 Iterations, 25 PSF Iterations	15 Iterations, 25 PSF Iterations
30 Iterations, 25 PSF Iterations	30 Iterations, 25 PSF Iterations	30 Iterations, 25 PSF Iterations	30 Iterations, 25 PSF Iterations	30 Iterations, 25 PSF Iterations
60 Iterations, 25 PSF Iterations	60 Iterations, 25 PSF Iterations	60 Iterations, 25 PSF Iterations	60 Iterations, 25 PSF Iterations	60 Iterations, 25 PSF Iterations
120 Iterations, 25 PSF Iterations	120 Iterations, 25 PSF Iterations	120 Iterations, 25 PSF Iterations	120 Iterations, 25 PSF Iterations	120 Iterations, 25 PSF Iterations

This project is licensed under the MIT License. See the LICENSE.md file for details.