Coral classification with hybrid feature representations

Arif Mahmood, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid, Renae Hovey, Gary Kendrick, Robert Fisher

Research output: Chapter in Book/Conference paperConference paper

14 Citations (Scopus)

Abstract

Coral reefs exhibit significant within-class variations, complex between-class boundaries and inconsistent image clarity. This makes coral classification a challenging task. In this paper, we report the application of generic CNN representations combined with hand-crafted features for coral reef classification to take advantage of the complementary strengths of these representation types. We extract CNN based features from patches centred at labelled pixels at multiple scales. We use texture and color based hand-crafted features extracted from the same patches to complement the CNN features. Our proposed method achieves a classification accuracy that is higher than the state-of-art methods on the MLC benchmark dataset for corals.
Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing
EditorsLina Karam
Place of PublicationUSA
PublisherWiley-IEEE Press
Pages519-523
Number of pages5
ISBN (Print)9781467399616
DOIs
Publication statusPublished - 2016
Event2016 IEEE International Conference on Image Processing (ICIP) - Phoenix, United States
Duration: 25 Sep 201628 Sep 2016

Conference

Conference2016 IEEE International Conference on Image Processing (ICIP)
CountryUnited States
CityPhoenix
Period25/09/1628/09/16

Fingerprint

Reefs
Textures
Pixels
Color

Cite this

Mahmood, A., Bennamoun, M., An, S., Sohel, F., Boussaid, F., Hovey, R., ... Fisher, R. (2016). Coral classification with hybrid feature representations. In L. Karam (Ed.), 2016 IEEE International Conference on Image Processing (pp. 519-523). USA: Wiley-IEEE Press. https://doi.org/10.1109/ICIP.2016.7532411
Mahmood, Arif ; Bennamoun, Mohammed ; An, Senjian ; Sohel, Ferdous ; Boussaid, Farid ; Hovey, Renae ; Kendrick, Gary ; Fisher, Robert . / Coral classification with hybrid feature representations. 2016 IEEE International Conference on Image Processing . editor / Lina Karam. USA : Wiley-IEEE Press, 2016. pp. 519-523
@inproceedings{847d2ead64224ea4930f3230957b5712,
title = "Coral classification with hybrid feature representations",
abstract = "Coral reefs exhibit significant within-class variations, complex between-class boundaries and inconsistent image clarity. This makes coral classification a challenging task. In this paper, we report the application of generic CNN representations combined with hand-crafted features for coral reef classification to take advantage of the complementary strengths of these representation types. We extract CNN based features from patches centred at labelled pixels at multiple scales. We use texture and color based hand-crafted features extracted from the same patches to complement the CNN features. Our proposed method achieves a classification accuracy that is higher than the state-of-art methods on the MLC benchmark dataset for corals.",
author = "Arif Mahmood and Mohammed Bennamoun and Senjian An and Ferdous Sohel and Farid Boussaid and Renae Hovey and Gary Kendrick and Robert Fisher",
year = "2016",
doi = "10.1109/ICIP.2016.7532411",
language = "English",
isbn = "9781467399616",
pages = "519--523",
editor = "Lina Karam",
booktitle = "2016 IEEE International Conference on Image Processing",
publisher = "Wiley-IEEE Press",

}

Mahmood, A, Bennamoun, M, An, S, Sohel, F, Boussaid, F, Hovey, R, Kendrick, G & Fisher, R 2016, Coral classification with hybrid feature representations. in L Karam (ed.), 2016 IEEE International Conference on Image Processing . Wiley-IEEE Press, USA, pp. 519-523, 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, United States, 25/09/16. https://doi.org/10.1109/ICIP.2016.7532411

Coral classification with hybrid feature representations. / Mahmood, Arif; Bennamoun, Mohammed; An, Senjian; Sohel, Ferdous; Boussaid, Farid; Hovey, Renae; Kendrick, Gary; Fisher, Robert .

2016 IEEE International Conference on Image Processing . ed. / Lina Karam. USA : Wiley-IEEE Press, 2016. p. 519-523.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Coral classification with hybrid feature representations

AU - Mahmood, Arif

AU - Bennamoun, Mohammed

AU - An, Senjian

AU - Sohel, Ferdous

AU - Boussaid, Farid

AU - Hovey, Renae

AU - Kendrick, Gary

AU - Fisher, Robert

PY - 2016

Y1 - 2016

N2 - Coral reefs exhibit significant within-class variations, complex between-class boundaries and inconsistent image clarity. This makes coral classification a challenging task. In this paper, we report the application of generic CNN representations combined with hand-crafted features for coral reef classification to take advantage of the complementary strengths of these representation types. We extract CNN based features from patches centred at labelled pixels at multiple scales. We use texture and color based hand-crafted features extracted from the same patches to complement the CNN features. Our proposed method achieves a classification accuracy that is higher than the state-of-art methods on the MLC benchmark dataset for corals.

AB - Coral reefs exhibit significant within-class variations, complex between-class boundaries and inconsistent image clarity. This makes coral classification a challenging task. In this paper, we report the application of generic CNN representations combined with hand-crafted features for coral reef classification to take advantage of the complementary strengths of these representation types. We extract CNN based features from patches centred at labelled pixels at multiple scales. We use texture and color based hand-crafted features extracted from the same patches to complement the CNN features. Our proposed method achieves a classification accuracy that is higher than the state-of-art methods on the MLC benchmark dataset for corals.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85006713280&origin=resultslist&sort=plf-f&src=s&st1=coral+classification+with+hybrid+feature+representation&st2=&sid=7AF89F655958D18B3D315A9D4106EC48.wsnAw8kcdt7IPYLO0V48gA%3a1650&sot=b&sdt=b&sl=70&s=TITLE-ABS-KEY%28coral+classification+with+hybrid+feature+representation%29&relpos=0&citeCnt=0&searchTerm=

U2 - 10.1109/ICIP.2016.7532411

DO - 10.1109/ICIP.2016.7532411

M3 - Conference paper

SN - 9781467399616

SP - 519

EP - 523

BT - 2016 IEEE International Conference on Image Processing

A2 - Karam, Lina

PB - Wiley-IEEE Press

CY - USA

ER -

Mahmood A, Bennamoun M, An S, Sohel F, Boussaid F, Hovey R et al. Coral classification with hybrid feature representations. In Karam L, editor, 2016 IEEE International Conference on Image Processing . USA: Wiley-IEEE Press. 2016. p. 519-523 https://doi.org/10.1109/ICIP.2016.7532411