LLC encoded BoW features and softmax regression for microscopic image classification

Dongyun Lin, Zhiping Lin, Lei Sun, Kar Ann Toh, Jiuwen Cao

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

5 Citations (Scopus)

Abstract

This paper proposes a method based on the bag-of-words (BoW) and the softmax regression for microscopic image classification. Essentially, the locality-constrained linear coding (LLC) is adopted for local feature encoding. Compared with the traditionally adopted vector quantization (VQ) in the BoW framework, the LLC encodes local structures of microscopic images with lower quantization errors and generates a sparse image representation. This enables the use of linear classifiers with low computational complexity. A softmax regression classifier is then adopted to address the multi-categorical classification task where the confidence of categorical prediction is quantified by posterior probabilities. Compared with other linear classifiers (such as the linear SVM) which only assign labels to images, such probabilistic outputs provide extra quantitative information to analyze misclassified images. Our experiments on the 2D-Hela and the PAP smear data sets show significant performance improvement of the proposed method comparing with competing methods using different features and classifiers under the BoW framework.

Original languageEnglish
Title of host publicationIEEE International Symposium on Circuits and Systems
Subtitle of host publicationFrom Dreams to Innovation, ISCAS 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467368520
DOIs
Publication statusPublished - 2017 Sep 25
Event50th IEEE International Symposium on Circuits and Systems, ISCAS 2017 - Baltimore, United States
Duration: 2017 May 282017 May 31

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
ISSN (Print)0271-4310

Other

Other50th IEEE International Symposium on Circuits and Systems, ISCAS 2017
CountryUnited States
CityBaltimore
Period17/5/2817/5/31

Fingerprint

Image classification
Classifiers
Vector quantization
Labels
Computational complexity
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Lin, D., Lin, Z., Sun, L., Toh, K. A., & Cao, J. (2017). LLC encoded BoW features and softmax regression for microscopic image classification. In IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings [8050243] (Proceedings - IEEE International Symposium on Circuits and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2017.8050243
Lin, Dongyun ; Lin, Zhiping ; Sun, Lei ; Toh, Kar Ann ; Cao, Jiuwen. / LLC encoded BoW features and softmax regression for microscopic image classification. IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{6a1a5480b71345d486df7726e4293114,
title = "LLC encoded BoW features and softmax regression for microscopic image classification",
abstract = "This paper proposes a method based on the bag-of-words (BoW) and the softmax regression for microscopic image classification. Essentially, the locality-constrained linear coding (LLC) is adopted for local feature encoding. Compared with the traditionally adopted vector quantization (VQ) in the BoW framework, the LLC encodes local structures of microscopic images with lower quantization errors and generates a sparse image representation. This enables the use of linear classifiers with low computational complexity. A softmax regression classifier is then adopted to address the multi-categorical classification task where the confidence of categorical prediction is quantified by posterior probabilities. Compared with other linear classifiers (such as the linear SVM) which only assign labels to images, such probabilistic outputs provide extra quantitative information to analyze misclassified images. Our experiments on the 2D-Hela and the PAP smear data sets show significant performance improvement of the proposed method comparing with competing methods using different features and classifiers under the BoW framework.",
author = "Dongyun Lin and Zhiping Lin and Lei Sun and Toh, {Kar Ann} and Jiuwen Cao",
year = "2017",
month = "9",
day = "25",
doi = "10.1109/ISCAS.2017.8050243",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "IEEE International Symposium on Circuits and Systems",
address = "United States",

}

Lin, D, Lin, Z, Sun, L, Toh, KA & Cao, J 2017, LLC encoded BoW features and softmax regression for microscopic image classification. in IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings., 8050243, Proceedings - IEEE International Symposium on Circuits and Systems, Institute of Electrical and Electronics Engineers Inc., 50th IEEE International Symposium on Circuits and Systems, ISCAS 2017, Baltimore, United States, 17/5/28. https://doi.org/10.1109/ISCAS.2017.8050243

LLC encoded BoW features and softmax regression for microscopic image classification. / Lin, Dongyun; Lin, Zhiping; Sun, Lei; Toh, Kar Ann; Cao, Jiuwen.

IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 8050243 (Proceedings - IEEE International Symposium on Circuits and Systems).

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

TY - GEN

T1 - LLC encoded BoW features and softmax regression for microscopic image classification

AU - Lin, Dongyun

AU - Lin, Zhiping

AU - Sun, Lei

AU - Toh, Kar Ann

AU - Cao, Jiuwen

PY - 2017/9/25

Y1 - 2017/9/25

N2 - This paper proposes a method based on the bag-of-words (BoW) and the softmax regression for microscopic image classification. Essentially, the locality-constrained linear coding (LLC) is adopted for local feature encoding. Compared with the traditionally adopted vector quantization (VQ) in the BoW framework, the LLC encodes local structures of microscopic images with lower quantization errors and generates a sparse image representation. This enables the use of linear classifiers with low computational complexity. A softmax regression classifier is then adopted to address the multi-categorical classification task where the confidence of categorical prediction is quantified by posterior probabilities. Compared with other linear classifiers (such as the linear SVM) which only assign labels to images, such probabilistic outputs provide extra quantitative information to analyze misclassified images. Our experiments on the 2D-Hela and the PAP smear data sets show significant performance improvement of the proposed method comparing with competing methods using different features and classifiers under the BoW framework.

AB - This paper proposes a method based on the bag-of-words (BoW) and the softmax regression for microscopic image classification. Essentially, the locality-constrained linear coding (LLC) is adopted for local feature encoding. Compared with the traditionally adopted vector quantization (VQ) in the BoW framework, the LLC encodes local structures of microscopic images with lower quantization errors and generates a sparse image representation. This enables the use of linear classifiers with low computational complexity. A softmax regression classifier is then adopted to address the multi-categorical classification task where the confidence of categorical prediction is quantified by posterior probabilities. Compared with other linear classifiers (such as the linear SVM) which only assign labels to images, such probabilistic outputs provide extra quantitative information to analyze misclassified images. Our experiments on the 2D-Hela and the PAP smear data sets show significant performance improvement of the proposed method comparing with competing methods using different features and classifiers under the BoW framework.

UR - http://www.scopus.com/inward/record.url?scp=85032694969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032694969&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2017.8050243

DO - 10.1109/ISCAS.2017.8050243

M3 - Conference contribution

AN - SCOPUS:85032694969

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - IEEE International Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lin D, Lin Z, Sun L, Toh KA, Cao J. LLC encoded BoW features and softmax regression for microscopic image classification. In IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. 8050243. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2017.8050243