Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

Back to your search

AI-Assisted Salmon Age Estimation from Scale Images

Ecology · Research & Development

What it collects

About a measurement
Anonymized data
  • Scale imprint images from salmon specimens collected by the DFO Science Branch Fish Ageing Lab. These are biological sample images with no personal information attached.

Government of Canada AI Register — PSSIScaleAging

Run by
Fisheries and Oceans Canada (DFO)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization
Your copy
You cannot see the data it holds about you. What you can do

What it is for

EcologyResearch & Development

This system uses computer vision and deep learning to automatically estimate the age of salmon by analyzing scale imprint images. It is designed to assist technicians at Fisheries and Oceans Canada's Sclerochronology Lab, which processes approximately 80,000 salmon scale aging assessments per year across British Columbia and the Yukon. The system does not process personal information and is currently in development. Its use of AI has been disclosed.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Scale imprint images from salmon specimens collected by the DFO Science Branch Fish Ageing Lab. These are biological sample images with no personal information attached.

Government of Canada AI Register — PSSIScaleAging

Processing

Computer Vision
  • Deep learning models, specifically Convolutional Neural Networks (CNNs), analyze scale imprint images to detect growth rings and other features used to infer salmon age.

Government of Canada AI Register — PSSIScaleAging

Classification & Prediction
  • The CNN model classifies scale images into age categories, predicting the age of each salmon specimen to support the technician's formal assessment.

Government of Canada AI Register — PSSIScaleAging

What it does

Sensing (Perceptive AI)
Human decides
  • The system reads scale imprint images and produces structured age estimations that lab technicians use to inform their assessments; final determinations remain with the human technician.

Government of Canada AI Register — PSSIScaleAging

Deciding (Analytical AI)
Human decides
  • Uses Convolutional Neural Networks (CNNs) to predict and classify salmon age from scale image features, returning an age estimate that supports the technician's decision.

Government of Canada AI Register — PSSIScaleAging

Outputs

A recommendation or prediction
Anonymized data
  • A predicted salmon age estimate derived from scale imprint analysis, provided to lab technicians as an advisory output to inform the official aging assessment. No personal information is included.

Government of Canada AI Register — PSSIScaleAging

Run by

Fisheries and Oceans Canada (DFO)
  • The federal department deploying and operating this AI system through its Sclerochronology Lab, which provides fish age analysis services across British Columbia and the Yukon.

Government of Canada AI Register — PSSIScaleAging

Built by

Government of Canada
  • The system was developed by the Government of Canada, indicating in-house development rather than procurement from an external vendor.

Government of Canada AI Register — PSSIScaleAging

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • AI-generated age assessments are available to DFO Sclerochronology Lab technicians and Science Branch staff as an internal science tool.

Government of Canada AI Register — PSSIScaleAging

Not available to me
  • The system processes fish specimen data, not personal information. Members of the public are not subjects of this system and have no individual access to its outputs.

Government of Canada AI Register — PSSIScaleAging

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

  • Right to Algorithmic TransparencyThe Government of Canada has disclosed that this system uses AI. As this system processes no personal information and affects only internal scientific workflows, individual rights to explanation or contest are not applicable. General information about the system is publicly available through the Government of Canada AI Register.

Risks and safeguards

No risks or safeguards have been published for this system yet.