Digit recognition using trispectral features

Features derived from the trispectra of DFT magnitude slices are used for multi-font digit recognition. These features are insensitive to translation, rotation, or scaling of the input. They are also robust to noise. Classification accuracy tests were conducted on a common data base of 256× 256 pixel bilevel images of digits in 9 fonts. Randomly rotated and translated noisy versions were used for training and testing. The results indicate that the trispectral features are better than moment invariants and affine moment invariants. They achieve a classification accuracy of 95% compared to about 81% for Hu's (1962) moment invariants and 39% for the Flusser and Suk (1994) affine moment invariants on the same data in the presence of 1% impulse noise using a 1-NN classifier. For comparison, a multilayer perceptron with no normalization for rotations and translations yields 34% accuracy on 16× 16 pixel low-pass filtered and decimated versions of the same data.

Looking into the light : reinventing the apparatus in contemporary art

Technical images such as photography, film and video, are dependent on apparatuses for their production and dissemination, yet the apparatus itself is often hidden or obscured in the experience of the work and the discourse that surrounds it. This practice-led research identifies key practice strategies to foreground the apparatus both in the production of work and in its presentation. It therefore develops critical and generative strategies to explore and interrogate the workings of the 'apparatus-audience complex,' and the particular modes of spectatorship that this entails.