Frames in bioimaging

Amina Chebira, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We survey our work on adaptive multiresolution (MR) approaches to the classification of biological images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. The system tested on different datasets (subcellular protein location images, drosophila embryo images and histological images images) gave very high accuracies. We hypothesize that the space-frequency localized information in the multiresolution subspaces adds significantly to the discriminative power of the system. Moreover, we show that a vastly reduced set of features is sufficient. Finally, we prove that frames are the class of MR techniques that performs the best in this context. This leads us to consider the construction of a new family of frames for classification, which we term lapped tight frame transforms.

Original languageEnglish (US)
Title of host publicationCISS 2008, The 42nd Annual Conference on Information Sciences and Systems
Pages727-732
Number of pages6
DOIs
StatePublished - Sep 22 2008
EventCISS 2008, 42nd Annual Conference on Information Sciences and Systems - Princeton, NJ, United States
Duration: Mar 19 2008Mar 21 2008

Other

OtherCISS 2008, 42nd Annual Conference on Information Sciences and Systems
CountryUnited States
CityPrinceton, NJ
Period3/19/083/21/08

Fingerprint

Classifiers
Decomposition
Proteins

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Control and Systems Engineering

Cite this

Chebira, A., & Kovacevic, J. (2008). Frames in bioimaging. In CISS 2008, The 42nd Annual Conference on Information Sciences and Systems (pp. 727-732). [4558617] https://doi.org/10.1109/CISS.2008.4558617

Frames in bioimaging. / Chebira, Amina; Kovacevic, Jelena.

CISS 2008, The 42nd Annual Conference on Information Sciences and Systems. 2008. p. 727-732 4558617.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chebira, A & Kovacevic, J 2008, Frames in bioimaging. in CISS 2008, The 42nd Annual Conference on Information Sciences and Systems., 4558617, pp. 727-732, CISS 2008, 42nd Annual Conference on Information Sciences and Systems, Princeton, NJ, United States, 3/19/08. https://doi.org/10.1109/CISS.2008.4558617
Chebira A, Kovacevic J. Frames in bioimaging. In CISS 2008, The 42nd Annual Conference on Information Sciences and Systems. 2008. p. 727-732. 4558617 https://doi.org/10.1109/CISS.2008.4558617
Chebira, Amina ; Kovacevic, Jelena. / Frames in bioimaging. CISS 2008, The 42nd Annual Conference on Information Sciences and Systems. 2008. pp. 727-732
@inproceedings{bc8d717dae8a402490fa602e9de9eaf6,
title = "Frames in bioimaging",
abstract = "We survey our work on adaptive multiresolution (MR) approaches to the classification of biological images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. The system tested on different datasets (subcellular protein location images, drosophila embryo images and histological images images) gave very high accuracies. We hypothesize that the space-frequency localized information in the multiresolution subspaces adds significantly to the discriminative power of the system. Moreover, we show that a vastly reduced set of features is sufficient. Finally, we prove that frames are the class of MR techniques that performs the best in this context. This leads us to consider the construction of a new family of frames for classification, which we term lapped tight frame transforms.",
author = "Amina Chebira and Jelena Kovacevic",
year = "2008",
month = "9",
day = "22",
doi = "10.1109/CISS.2008.4558617",
language = "English (US)",
isbn = "9781424422470",
pages = "727--732",
booktitle = "CISS 2008, The 42nd Annual Conference on Information Sciences and Systems",

}

TY - GEN

T1 - Frames in bioimaging

AU - Chebira, Amina

AU - Kovacevic, Jelena

PY - 2008/9/22

Y1 - 2008/9/22

N2 - We survey our work on adaptive multiresolution (MR) approaches to the classification of biological images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. The system tested on different datasets (subcellular protein location images, drosophila embryo images and histological images images) gave very high accuracies. We hypothesize that the space-frequency localized information in the multiresolution subspaces adds significantly to the discriminative power of the system. Moreover, we show that a vastly reduced set of features is sufficient. Finally, we prove that frames are the class of MR techniques that performs the best in this context. This leads us to consider the construction of a new family of frames for classification, which we term lapped tight frame transforms.

AB - We survey our work on adaptive multiresolution (MR) approaches to the classification of biological images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. The system tested on different datasets (subcellular protein location images, drosophila embryo images and histological images images) gave very high accuracies. We hypothesize that the space-frequency localized information in the multiresolution subspaces adds significantly to the discriminative power of the system. Moreover, we show that a vastly reduced set of features is sufficient. Finally, we prove that frames are the class of MR techniques that performs the best in this context. This leads us to consider the construction of a new family of frames for classification, which we term lapped tight frame transforms.

UR - http://www.scopus.com/inward/record.url?scp=51849093157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849093157&partnerID=8YFLogxK

U2 - 10.1109/CISS.2008.4558617

DO - 10.1109/CISS.2008.4558617

M3 - Conference contribution

SN - 9781424422470

SP - 727

EP - 732

BT - CISS 2008, The 42nd Annual Conference on Information Sciences and Systems

ER -