Category: lirec

Testing how my face gets expressed in eigenface space as I change my expression. The face on the left is my face synthesised by the trained algorithm. Ideally, there would be no expression on any of the faces in the face database, and my synthesised eigenface would remain the same no matter what silly face…

This time using Dr Libor Spacek’s face database which comprises about 400 individuals. The faces along the top express the 30 most significant eigenfaces found in the data, and the three faces along the bottom are the average face, my face, and my face expressed in terms of the eigenfaces – i.e. generated from the…

We had another Lirec consortium meeting, this time in Poland at the Wroclaw University of Technology. I took some pictures of their mechanoids, which included COSMOS, a 2 wheel balancing robot, and the best use of xeyes I’ve seen for some time:

In the computer vision business, you have to get quite used to seeing your face a lot, as it’s generally the easiest to find subject for your experiments 🙂 This is me in lots of different lighting environments: The standard face modelling approach is principle component analysis which is used to understand the appearance of…

It feels like the recent work on the faceident competency for Lirec has spawned far too many avenues of research, and not much actual improvement. I thought I’d spend some time consolidating the new features and running them through test videos. Firstly I got rid of the adaptive blending, it’s too fragile and causes the…

Recent additions to the faceident project, both are attempts at dealing with lighting changes – which is the main area that needs addressing, as lighting changes are far more significant algorithmically than identifying features, and so cause lots of problems. Firstly, I’ve added support for multiple images per identity/user – so we can at least…

I’ve haven’t said much about Lirec lately, as I’ve mainly been doing not so interesting technical stuff (looking into cmake and yarp), or quietly researching robot art. During the course of the latter however, I’ve been reading about Norman White who is one of these inspiring people who were getting on with doing exciting work…

My first bit of computer vision code under the GPL: It’s just a noddy method to try and identify different people, built on top of OpenCV’s face finder. It’s for the lirec project, as a potential way of identifying who is who for the scenarios involving the iCat.