iHero - using facial recognition in First World War photo collections

iHero is the aptly named web application that uses facial recognition technology to search the photos of Australian war service men and women. Users of iHero upload a photo to begin a search. The application uses facial analytics to determine which photos from the major libraries are a match.

Search results include:

  • The match confidence (e.g. 90%)
  • Detected characteristics (gender, glasses, smile, age)
  • The matching images with a bounding box to indicate the person matched against (for images with multiple people)

iHero was created as part of GovHack 2016 by Hack To The Future.

The Data

iHero uses data from:

The User

View a demo video of the iHero web app. The interface is clean and simple, and includes a quick search and a deeper search, which produces more results.

The benefits

Researchers and family historians may be able to identify unnamed portraits of Australian servicemen and women using their own photographs. Unnamed photos in collections in cultural institutions can also be identified and matched to valuable information/records.

The facial recognition capacity explored in this entry can be used across a wide range of applications enabling photos sitting in archives and family shoe boxes to be discovered.

App demo

Launch a larger screen version of the  iHero web app demo video.

Other world war data

Discover other world war datasets available for download from the Queensland Government Open Data Portal.