Complex-order Derivative and Integral Filters and its Applications

TL;DR

This paper introduces complex-order derivative and integral filters that enhance signal detail extraction, demonstrating their effectiveness in image processing tasks, especially in medical imaging for prostate disease detection.

Contribution

It proposes a novel class of complex-order filters that extend fractional calculus, showing their advantages over real-order filters in practical applications.

Findings

Complex-order filters reveal more signal details.

Effective in medical image analysis, especially prostate TRUS images.

Complex-order integral filters can identify diseased regions.

Abstract

In this paper, complex-order derivative and integral filters are proposed, which are consistent with the filters with fractional derivative and integral orders. Compared with the filters designed only with real orders, complex order filters can reveal more details of input signals, and this can benefit a large number of tasks. The tremendous effect of the proposed complex-order filters, has been verified by several image processing examples. Especially, for the challenging problem indicating the diseased regions in prostate TRUS images, the proposed complex order filters look very promising. It is very astonishing that, indicating the diseased regions is fulfilled by complex-order integral, not by derivative. This is completely against the traditional views that using derivative operators to achieve the goal.