Human-Designed Filters May Outperform
Machine-Learned Filters

Paul C Mocombe

Research Article

Human-Designed Filters May Outperform Machine-Learned Filters

Gengsheng L Zeng^1,2*

¹Utah Valley University, Orem, Utah, 84058, USA

²University of Utah, Salt Lake City, Utah, 84108, USA

Corresponding Author

Received Date: November 10, 2022; Published Date: November 22, 2022

Abstract

Machine-learned image processing systems in medical imaging have shown better results than those obtained by traditional human-designed techniques. The success of machine learning techniques inspires humans to design better systems. The convolutional neural network (CNN) has a multi-channel architecture, which the conventional filters do not have. This paper proposes that by borrowing the multi-channel architecture, the human-designed denoising filter can have better performance than the machined-learned version. We illustrate the feasibility of this idea with a toy example in a sinogram denoising task in the area of tomography.

Keywords: Data science; Denoising; Image processing; Machine learning; Nonlinearity; Signal processing

Article Details

Citation