Morphological Segmentation of Plantar Pressure Images by Using Mean Shift Local De-Dimensionality

摘要

The analysis of plantar pressure imaging does not perform well preprocessing, dimensionality reduction and feature calculation; this makes the research of foot comfort by statistical methods have the defects of linearization and poor robustness. The intelligent analysis technology to achieve the extraction of the plantar functional area, providing a streamlined and content-rich data set for the study of plantar pressure comfort is very effective and feasible. Different from the existing local-based segmentation technique of the plantar pressure image, the bottom pressure image mean shifting segmentation model segments the plantar pressure image from a global perspective to obtain more accurate segmentation results; by using pixel precision, average pixel precision, uniform cross-section, frequency-to-weight ratio, segmentation accuracy, over-segmentation rate, under-segmentation rate and Dice coefficient for contrast segmentation, the proposed mean shift local de-dimensionality morphological segmentation performs higher effectiveness.