Angel Amenze

Hi, I’m Angel.

I graduated from the University of Kent with a first-class degree in computer science. For one project, I tested whether a model could tell animals apart by the texture in their photos. Try the demo with a zebra or a giraffe.

A close-up of black and white stripes on a Grévy’s zebra
Grévy’s zebra. Photo by Servali.

Classifying animal images

I turned textures into numbers using local binary patterns (LBP) and grey-level co-occurrence matrices (GLCM). I tried four classifiers and used confusion matrices to see which classes they mixed up.

Project mark
82%
Model accuracy in the project
About 70%

A closer look at texture

Choose a sample photo to see what each method picks up.

Zebra stripe sample
Sample photoA crop of a zebra’s stripes.
Local binary patternsEach colour shows how a pixel compares with its eight neighbours.
Grey-level pairsLighter squares show grey-value pairs that occur more often.

Analysing the sample…

About me

I also work as a teaching assistant. In a small maths group, I used Dienes blocks to show what each digit in a number represents. Afterwards, all five pupils could add and subtract two- and three-digit numbers.

I’m looking for my first role in data engineering, actuarial work or quantitative analysis in London. Away from my laptop, I like baking.