Apparently a lot of image and data analysis techniques are related – Fourier, Hough, convolution, etc.
Image analysis is about finding patterns in a 2D or 3D still image. Data analysis is about finding patterns in 1D, all the way up to multi-dimensional data. There are several ways in which to find these patterns, and this includes regression models and neural networks. Patterns can be described by the shape and orientation of their boundaries.
I had a discussion with one of the associate professors in our centre today about this. He hinted that the underlying mathematics is similar for these related techniques, but he didn’t say exactly how. One day I’ll chat to him about it again, and I’ll understand why.