What is it about?

The proposed neural network filter weights are trained with the help of heuristic technique i.e. teaching learning-based optimization (TLBO) technique. It is a nonlinear adaptive filter and helps in removing a specific or mixed type of noise.

Featured Image

Why is it important?

The proposed work simple in design as well as implementation because it uses single layer neural network i.e. FLANN and for improving the performance level of recently developed TLBO is applied to update the weights. Overall, developed filter improve the accuracy level and not only suppress the dominant rician noise but also able to suppress Gaussian and impulse noise. Hence, TLBO-FLANN filter avoids the problem of selecting a particular algorithm for specific noise.

Perspectives

The developed filter has to test with other medical images and need to improve efficiency level.

Manish Kumar
birla institute of technology

Read the Original

This page is a summary of: Teaching learning based optimization-functional link artificial neural network filter for mixed noise reduction from magnetic resonance image, Bio-Medical Materials and Engineering, November 2017, IOS Press,
DOI: 10.3233/bme-171702.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page