Melanosome Tracking Using Automatic Error Correction

Toshiaki OKABE; Kazuhiro HOTTA

doi:10.1587/transinf.2013EDP7458

Melanosome Tracking Using Automatic Error Correction

Toshiaki OKABE, Kazuhiro HOTTA

Full Text Views

0

Cite this

Summary :

This paper proposes an automatic error correction method for melanosome tracking. Melanosomes in intracellular images are currently tracked manually when investigating diseases, and an automatic tracking method is desirable. We detect all melanosome candidates by SIFT with 2 different parameters. Of course, the SIFT also detects non-melanosomes. Therefore, we use the 4-valued difference image (4-VDimage) to eliminate non-melanosome candidates. After tracking melanosome, we re-track the melanosome with low confidence again from t+1 to t. If the results from t to t+1 and from t+1 to t are different, we judge that initial tracking result is a failure, the melanosome is eliminated as a candidate and re-tracking is carried out. Experiments demonstrate that our method can correct the error and improves the accuracy.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.12 pp.3201-3209

Publication Date: 2014/12/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2013EDP7458

Type of Manuscript: PAPER

Category: Biological Engineering

Authors

Toshiaki OKABE
Meijo University
Kazuhiro HOTTA
Meijo University

Keyword

tracking, melanosome, intracellular image, system biology, error correction

Cite this

Copy

Toshiaki OKABE, Kazuhiro HOTTA, "Melanosome Tracking Using Automatic Error Correction" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 12, pp. 3201-3209, December 2014, doi: 10.1587/transinf.2013EDP7458.
Abstract: This paper proposes an automatic error correction method for melanosome tracking. Melanosomes in intracellular images are currently tracked manually when investigating diseases, and an automatic tracking method is desirable. We detect all melanosome candidates by SIFT with 2 different parameters. Of course, the SIFT also detects non-melanosomes. Therefore, we use the 4-valued difference image (4-VDimage) to eliminate non-melanosome candidates. After tracking melanosome, we re-track the melanosome with low confidence again from t+1 to t. If the results from t to t+1 and from t+1 to t are different, we judge that initial tracking result is a failure, the melanosome is eliminated as a candidate and re-tracking is carried out. Experiments demonstrate that our method can correct the error and improves the accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2013EDP7458/_p

Copy

@ARTICLE{e97-d_12_3201,
author={Toshiaki OKABE, Kazuhiro HOTTA, },
journal={IEICE TRANSACTIONS on Information},
title={Melanosome Tracking Using Automatic Error Correction},
year={2014},
volume={E97-D},
number={12},
pages={3201-3209},
abstract={This paper proposes an automatic error correction method for melanosome tracking. Melanosomes in intracellular images are currently tracked manually when investigating diseases, and an automatic tracking method is desirable. We detect all melanosome candidates by SIFT with 2 different parameters. Of course, the SIFT also detects non-melanosomes. Therefore, we use the 4-valued difference image (4-VDimage) to eliminate non-melanosome candidates. After tracking melanosome, we re-track the melanosome with low confidence again from t+1 to t. If the results from t to t+1 and from t+1 to t are different, we judge that initial tracking result is a failure, the melanosome is eliminated as a candidate and re-tracking is carried out. Experiments demonstrate that our method can correct the error and improves the accuracy.},
keywords={},
doi={10.1587/transinf.2013EDP7458},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Melanosome Tracking Using Automatic Error Correction
T2 - IEICE TRANSACTIONS on Information
SP - 3201
EP - 3209
AU - Toshiaki OKABE
AU - Kazuhiro HOTTA
PY - 2014
DO - 10.1587/transinf.2013EDP7458
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2014
AB - This paper proposes an automatic error correction method for melanosome tracking. Melanosomes in intracellular images are currently tracked manually when investigating diseases, and an automatic tracking method is desirable. We detect all melanosome candidates by SIFT with 2 different parameters. Of course, the SIFT also detects non-melanosomes. Therefore, we use the 4-valued difference image (4-VDimage) to eliminate non-melanosome candidates. After tracking melanosome, we re-track the melanosome with low confidence again from t+1 to t. If the results from t to t+1 and from t+1 to t are different, we judge that initial tracking result is a failure, the melanosome is eliminated as a candidate and re-tracking is carried out. Experiments demonstrate that our method can correct the error and improves the accuracy.
ER -