Files in this item



application/pdfECE499-Sp2013-liXing.pdf (1MB)Restricted to U of Illinois
(no description provided)PDF


Title:Automated Cell-Tracking System Using Locally Laplacian Shift Features Detecting Cell Growth on Slanted Nano-Pillar Structure
Author(s):Li, Xing
Contributor(s):Liu, Logan; Hsia, Jimmy K.
Laplacian scale-invariant features transform (SIFT)
cell-detection Laplacian SIFT
DIC microscopy
Abstract:In this project, a novel cell-tracking scheme using Laplacian scale-invariant features transform (SIFT) is proposed for automatic cell motion analysis in grayscale microscopic videos, particularly for mouse muscle cells (C2C12) growing on our slanted Nano-pillar structures. In this proposed novel approach, cells were successfully detected in the microscopic images and a locality detecting algorithm using Laplacian SIFT is also proposed to track the SIFT feature points along successive frames of low-contrast differential interference contrast (DIC) microscopy videos. Experiments on low-contrast DIC microscopy videos of hundreds of healthy living-cells grow on slanted Nano-pillar structure materials show that comparing with based SIFT tracking, the proposed locally Laplacian SIFT can significantly reduce the error, improve the robustness and save the run-time. With this novel scheme, further experimental results demonstrate that living-cells have particular preferred moving directions and motion patterns related to the degree of the slanted Nano-pillar materials. Thus, the proposed algorithm is a robust and accurate approach to tackling the challenge of living-cells tracking in DIC microscopy.
Issue Date:2013-05
Publication Status:unpublished
Peer Reviewed:not peer reviewed
Date Available in IDEALS:2014-03-19

This item appears in the following Collection(s)

Item Statistics