DAT613 – Dissertation Proposal

Title/Question

Can artificial intelligence enhance the practice of digital cultural heritage?

Outline of area of study/context

I’ve always had an interest in technology and in history. When I saw the television advertisement for Microsoft’s Artificial Intelligence services that featured Yves Ubelmann’s photogrammetry work in Syria, I was intrigued. I had carried out some basic photogrammetry and worked with Microsoft’s Face API on previous projects so the combination of photogrammetry with AI, particularly in an historical context, was something I wanted to explore further. Continue reading “DAT613 – Dissertation Proposal”

DAT602 – Face Login and User Authentication with Node.js Passport

Face Login

In my previous post, I described the development of a web interface that used Javascript to access Microsoft’s Cognitive Services Azure Face API. This interface allowed an image of a face to be captured via a web-cam and identified against a previously trained Person Group.

Now that this basic system is functioning as expected, I can use it as the basis for a Node.js/Express user authentication system using the popular Node package, Passport.

Continue reading “DAT602 – Face Login and User Authentication with Node.js Passport”

DAT602 – Face Recognition with Azure Face API and Python

Face detection result

Having spent many hours tinkering with Amazon’s Rekognition API and making little progress, I decided to investigate the face recognition Face API provided as part of Microsoft Azure Cognitive Services (Microsoft, no date).

The API provides functionality to implement face detection (“detect one or more human faces in an image and get back face rectangles for where in the image the faces are, along with face attributes which contain machine learning-based predictions of facial features. The face attribute features available are: Age, Emotion, Gender, Pose, Smile, and Facial Hair along with 27 landmarks for each face in the image”) and face verification (“check the likelihood that two faces belong to the same person. The API will return a confidence score about how likely it is that the two faces belong to one person”).

Continue reading “DAT602 – Face Recognition with Azure Face API and Python”