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 paperpeer-review

65 Citations (Scopus)


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
Number of pages5
ISBN (Electronic)9781467399616
ISBN (Print)9781467399616
Publication statusPublished - 3 Aug 2016
Event2016 IEEE International Conference on Image Processing - Phoenix, United States
Duration: 25 Sept 201628 Sept 2016
Conference number: 23rd


Conference2016 IEEE International Conference on Image Processing
Abbreviated titleICIP 2016
Country/TerritoryUnited States


Dive into the research topics of 'Coral classification with hybrid feature representations'. Together they form a unique fingerprint.

Cite this