Messages, emails and actions

Facial Recognition

ResourceSpace has facial recognition capability by integrating with OpenCV, an open source computer vision and machine learning software library. ResourceSpace annotation feature has also been used in order to create the association between a fixed list field and a face.

To tag someone, simply do the following:

  • Go to view the resource
  • Hover over the bottom of the preview of the image and click on the annotation tool icon
  • Select a face by dragging. Click and drag. Once you release the mouse, if the system has been already trained it will try to predict a person to you.
  • The system can suggest two things: "unknown person" or someones name
  • Clicking on the suggested name will approve the tag
  • Click save

Note: as per how annotations work, you MUST save at the end in order for it to take effect.

Once you've tagged someone, the system will not automatically recognise them unless it has been (re)trained with those faces. A system/ server administrator should have created a cronjob/ scheduled task to run pages/tools/facial_recognition_trainer.php


  • ResourceSpace is using LBPH (Local Binary Patterns Histograms) algorithm for its face recognizer.
  • Fairly good predictions can appear usually after the system has been trained with at least 10 faces for the same person.
  • To increase the reliablity of this feature, the system should be trained with various environments and appearances e.g. indoors / outdoors, with / without glasses, long / short hair

Using annotations and facial recognition together

Version 9.0+

ResourceSpace has the ability to allow tagging an image for both facial recognition and as part of annotation feature (core feature on top of which facial recognition is sitting on).

When using annotations in this mode, the user will be first presented with a dropdown box to select the field he/ she is going to tag. Once a field is selected, the rest of functionality should already be familiar - start typing and soon suggestions will be presented and select the ones relevant to the image.