Efficient Image Set Classification Using Linear Regression Based Image Reconstruction

Research output: Chapter in Book/Conference paperConference paper

7 Citations (Scopus)

Abstract

We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based on the minimum reconstruction error between the reconstructed and the original images, a weighted voting strategy is used to classify the test set. We performed extensive evaluation on the benchmark UCSD/Honda, CMU Mobo and YouTube Celebrity datasets for face classification, and ETH-80 dataset for object classification. The results demonstrate that by using only a small amount of training data, our technique achieved competitive classification accuracy and superior computational speed compared with the state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages601-610
Number of pages10
Volume2017-July
ISBN (Electronic)9781538607336
DOIs
Publication statusPublished - 22 Aug 2017
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: 21 Jul 201726 Jul 2017

Conference

Conference30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
CountryUnited States
CityHonolulu
Period21/07/1726/07/17

Fingerprint

Image reconstruction
Linear regression

Cite this

Shah, S. A. A., Nadeem, U., Bennamoun, M., Sohel, F., & Togneri, R. (2017). Efficient Image Set Classification Using Linear Regression Based Image Reconstruction. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (Vol. 2017-July, pp. 601-610). [8014822] USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPRW.2017.88
Shah, Syed A.A. ; Nadeem, Uzair ; Bennamoun, Mohammed ; Sohel, Ferdous ; Togneri, Roberto. / Efficient Image Set Classification Using Linear Regression Based Image Reconstruction. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 601-610
@inproceedings{e6a91e6843084896849c74f838039f0e,
title = "Efficient Image Set Classification Using Linear Regression Based Image Reconstruction",
abstract = "We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based on the minimum reconstruction error between the reconstructed and the original images, a weighted voting strategy is used to classify the test set. We performed extensive evaluation on the benchmark UCSD/Honda, CMU Mobo and YouTube Celebrity datasets for face classification, and ETH-80 dataset for object classification. The results demonstrate that by using only a small amount of training data, our technique achieved competitive classification accuracy and superior computational speed compared with the state-of-the-art methods.",
author = "Shah, {Syed A.A.} and Uzair Nadeem and Mohammed Bennamoun and Ferdous Sohel and Roberto Togneri",
year = "2017",
month = "8",
day = "22",
doi = "10.1109/CVPRW.2017.88",
language = "English",
volume = "2017-July",
pages = "601--610",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Shah, SAA, Nadeem, U, Bennamoun, M, Sohel, F & Togneri, R 2017, Efficient Image Set Classification Using Linear Regression Based Image Reconstruction. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. vol. 2017-July, 8014822, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 601-610, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 21/07/17. https://doi.org/10.1109/CVPRW.2017.88

Efficient Image Set Classification Using Linear Regression Based Image Reconstruction. / Shah, Syed A.A.; Nadeem, Uzair; Bennamoun, Mohammed; Sohel, Ferdous; Togneri, Roberto.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 601-610 8014822.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Efficient Image Set Classification Using Linear Regression Based Image Reconstruction

AU - Shah, Syed A.A.

AU - Nadeem, Uzair

AU - Bennamoun, Mohammed

AU - Sohel, Ferdous

AU - Togneri, Roberto

PY - 2017/8/22

Y1 - 2017/8/22

N2 - We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based on the minimum reconstruction error between the reconstructed and the original images, a weighted voting strategy is used to classify the test set. We performed extensive evaluation on the benchmark UCSD/Honda, CMU Mobo and YouTube Celebrity datasets for face classification, and ETH-80 dataset for object classification. The results demonstrate that by using only a small amount of training data, our technique achieved competitive classification accuracy and superior computational speed compared with the state-of-the-art methods.

AB - We propose a novel image set classification technique using linear regression models. Downsampled gallery image sets are interpreted as subspaces of a high dimensional space to avoid the computationally expensive training step. We estimate regression models for each test image using the class specific gallery subspaces. Images of the test set are then reconstructed using the regression models. Based on the minimum reconstruction error between the reconstructed and the original images, a weighted voting strategy is used to classify the test set. We performed extensive evaluation on the benchmark UCSD/Honda, CMU Mobo and YouTube Celebrity datasets for face classification, and ETH-80 dataset for object classification. The results demonstrate that by using only a small amount of training data, our technique achieved competitive classification accuracy and superior computational speed compared with the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85030222913&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.88

DO - 10.1109/CVPRW.2017.88

M3 - Conference paper

VL - 2017-July

SP - 601

EP - 610

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Shah SAA, Nadeem U, Bennamoun M, Sohel F, Togneri R. Efficient Image Set Classification Using Linear Regression Based Image Reconstruction. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July. USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 601-610. 8014822 https://doi.org/10.1109/CVPRW.2017.88