How we experimented with Amazon Rekognition’s custom labels

Experiment #1 — Using custom labels to detect and count animals on a farm

  1. Whether custom labels can accurately detect the presence of cows from 12 birdseye images from two different farms captured by a drone.
  2. Whether an enriched dataset featuring an additional 290 publicly available images of different farms would improve the outcome.

Observations and outcomes

Labelling the dataset

Quality and quantity of images makes a big difference

The size and detail of each image also makes a difference

Custom labels is its own ecosystem

Experiment #2 — Using custom labels for TimTams brand recognition

Detecting TimTams on social media

Detecting TimTams on supermarket shelves

  • Custom labels can be used to detect the presence of a brand/logo in an image but cannot reliably count them with a database this small.
  • Labels were more easily detected when the logos fed to the model were not at an angle (see image below).
  • We encountered similar issues to the Shahin’s animal experiment — labelling took time and uploading images greater than 4096 pixels caused issues.

Our thoughts on custom labels



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store


We specialise in using emerging tech to solve difficult problems, get new ideas to market & disrupt business models.