Phase Congruency Parameter Optimization for Enhanced Detection of Image Features for both Natural and Medical Applications
This work addresses parameter optimization for image feature detection, which is incremental as it builds on existing 2D-MSPC methods.
The paper tackled the problem of tuning many parameters in 2D multi-scale phase congruency for image feature detection by defining a criterion based on maximum and minimum moments, and verified its effectiveness on natural and medical images including those from multiple sclerosis patients.
Following the presentation and proof of the hypothesis that image features are particularly perceived at points where the Fourier components are maximally in phase, the concept of phase congruency (PC) is introduced. Subsequently, a two-dimensional multi-scale phase congruency (2D-MSPC) is developed, which has been an important tool for detecting and evaluation of image features. However, the 2D-MSPC requires many parameters to be appropriately tuned for optimal image features detection. In this paper, we defined a criterion for parameter optimization of the 2D-MSPC, which is a function of its maximum and minimum moments. We formulated the problem in various optimal and suboptimal frameworks, and discussed the conditions and features of the suboptimal solutions. The effectiveness of the proposed method was verified through several examples, ranging from natural objects to medical images from patients with a neurological disease, multiple sclerosis.