Sub-pixel Edge Detection of Cubic Spline in HSV Color Space

Abstract

In the process of image position and detection, the pixel-level edge image sometimes cannot meet the demand, which requires more precise sub-pixel edge detection technology. This article detected the pixel-level edge image using the sin cos HSV  color distance model in HSV space firstly, then obtained the sub-pixel edge image using Cubic spline to interpolate, and made a comparative study with B-spline to their results. The results showed that the entropy of the sub-pixel image is richer than the pixel-level image, and Cubic spline is better than B-spline.