Efficiency and accuracy assessment of an automated image classifier for commercially important fish species

Acharya, Arnab; Guenther, Sara; Wielgus, Jeffrey; Grasso, Monica; Gardner, George; Chittila, Ravi; Conran, Joseph; Wodajo, Tadesse; Wilhelm, Tony; Thomas, Sara; Campbell, Matthew; Martin, Kelsey; Prior, Jack

doi:10.25923/30by-3897

i

Efficiency and accuracy assessment of an automated image classifier for commercially important fish species

2026
By Acharya, Arnab ; Guenther, Sara ; Wielgus, Jeffrey
Series: Performance, Risk and Social Science papers ; 004

Details

Personal Author:

Acharya, Arnab ; Guenther, Sara ; Wielgus, Jeffrey ; Grasso, Monica ; Gardner, George ; Chittila, Ravi ; Conran, Joseph ; Wodajo, Tadesse ; Wilhelm, Tony ; Thomas, Sara ; Campbell, Matthew ; Martin, Kelsey ; Prior, Jack
Corporate Authors:

Performance, Risk, and Social Science Office. ; Office of the Chief Finance Officer. ; Southeast Fisheries Science Center (U.S.). ; Montana State University-Bozeman.
NOAA Program & Office:

NMFS (National Marine Fisheries Service) ; SEFSC (Southeast Fisheries Science Center) ; OCFO (Office of the Chief Financial Officer) ; PRSSO (Performance, Risk, and Social Science Office)
Description:

Experts that analyze video collected from underwater optical systems can routinely provide accurate species counts. However, the high opportunity costs of expert time have entailed delays in processing large amounts of video data. Artificial Intelligence (AI) has the potential to reduce these delays and costs. To establish a baseline for this potential, we conducted a formative evaluation of a model used to count fish by species, run in the Visual and Image Analytics for Multiple Environments (VIAME) software.
Keywords:
Series:

Performance, Risk and Social Science papers ; 004
DOI:

https://doi.org/10.25923/30by-3897
Format:

pdf
Document Type:

Program & Policy Document
License:

https://creativecommons.org/publicdomain/zero/1.0/
Rights Information:

CC0 Public Domain
Compliance:

Submitted
Download URL:

https://repository.library.noaa.gov/view/noaa/73740/noaa_73740_DS1.pdf
File Type:

[PDF - 691.95 KB]
Collection(s):

National Marine Fisheries Service (NMFS)
Main Document Checksum:

urn:sha-512:5bac7766c6c19afb526406b3c38c6d5d4d61acc017759f719ce5a3e61d2b3630dc2fae9aba49df64a06cdc9026a29822b614f4640d40dd447e772c231a871c78

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.