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 OCR for Pacific Salmon Records Digitization

Planning & Decision-making

What it collects

Operational data
Anonymized data
  • Scanned PDF documents from various DFO Pacific salmon programs, including fish slips, compliance and inspection reports, BC16 documents, purchase slips, dockside reports, logbooks, and sea observer reports. Source data spans unclassified, Protected A, and Protected B classifications. No personal information is involved.
Run by
Fisheries and Oceans Canada (DFO)
Where
No fixed location
Kept
Retained not specified
Shared with
Accountable organization
Your copy
You cannot see the data it holds about you. What you can do

What it is for

Planning & Decision-making

This system uses optical character recognition (OCR) software to automatically extract information from thousands of scanned and paper-based fisheries documents — such as fish slips, logbooks, and inspection reports — and convert that information into structured digital records. It is used internally by Fisheries and Oceans Canada employees to modernize data workflows and preserve historical data needed for Pacific salmon management decisions. The system does not process personal information, and users are not currently notified of AI use.

What it collects and what happens to it

Data taken in

Operational data
Anonymized data
  • Scanned PDF documents from various DFO Pacific salmon programs, including fish slips, compliance and inspection reports, BC16 documents, purchase slips, dockside reports, logbooks, and sea observer reports. Source data spans unclassified, Protected A, and Protected B classifications. No personal information is involved.

Processing

Computer Vision
  • Custom OCR (optical character recognition) models interpret scanned document images — reading printed and handwritten text, identifying field layouts, and extracting structured data values from unstructured paper-based records.
Classification & Prediction
  • Document-type classification assigns each scanned PDF to a category (e.g. fish slip, logbook, inspection report) to route it to the appropriate field-extraction model. Built from labeled historical fisheries documents.

What it does

Sensing (Perceptive AI)
Human decides
  • The system reads scanned PDF documents and extracts structured fields from them using custom OCR models. It also sorts documents by type. Extracted data is subject to manual review and verification by GC employees before use in decision making.
Deciding (Analytical AI)
Human decides
  • The system classifies scanned documents by type (e.g. fish slips, logbooks, inspection reports) to route them to the correct extraction pipeline. Classification outputs are advisory — human staff verify results.

Outputs

Operational data
Anonymized data
  • Structured digital records extracted from scanned fisheries documents, including data from fish slips, logbooks, dockside reports, and other program records. Output supports Pacific salmon management reporting, tracking, and decision making. No personal information is included in outputs.

Run by

Fisheries and Oceans Canada (DFO)
  • The federal department responsible for managing Canada's fisheries and aquatic ecosystems. Fisheries and Oceans Canada deploys and operates this OCR system to digitize historical Pacific salmon program records for internal use by GC employees.

Government of Canada AI Register — PSSIOCR (2526-DFO-MPO-010)

Built by

Government of Canada
  • The system was developed by the Government of Canada, with custom OCR models trained internally using fisheries program data.

Government of Canada AI Register — PSSIOCR (2526-DFO-MPO-010)

Kept for

Retained not specified
  • The register entry does not specify a retention period for structured output data. Given the stated goal of long-term preservation of historical fisheries data, extended retention is anticipated but not formally documented in the available source.
  • Duration: not specified

Shared with

Available to the accountable organization
  • Outputs are available to GC employees within Fisheries and Oceans Canada programs for internal reporting, tracking, and management decision making.
Not available to me
  • The system processes internal government program records, not individual citizen data. Members of the public do not have access to outputs and are not subjects of this system.

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 TransparencyAI use is not currently disclosed to users of the system. The Government of Canada has published an entry in its public AI register describing this system's purpose and capabilities. Members of the public may consult the register at open.canada.ca.

Risks and safeguards

  • Reputational harmOCR extraction errors could result in incorrect data being entered into structured records, potentially misrepresenting historical fisheries activity and affecting management decisions based on that data.Safeguard: the system explicitly supports manual review and verification of extracted data by GC employees before records are used in decision making.