The Invariant of Zernike Moment in Image Recognition about Intravenous Infusion Needle

摘要

It is an effective solution to recognize the position of intravenous infusion needles using the Zernike moments invariants. Firstly, preprocessing and normalizing the character image are introduced; secondly, the image's rotation invariant features using Zernike moments are gotten. The result shows that the Zernike moment has better invariant properties, and can describe robustly the needle-image rotated shape.