Author Archives: Michael Murtaugh

Super Resolution

The image as a database containing echoes of itself. Abstract: Methods for super-resolution (SR) can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose […]

KHIO Performative Lecture

Notes from a “performative presentation” made at the KHiO, Oslo Norway Thursday 15 October, 2015 http://pad.constantvzw.org/public_pad/sicv_khio_presentation_2015

Degenerate images

Running the “orderings” code on a larger selection of images from Guttorm Guttormgaard’s collection (still under construction), several images caused the code to break as “exceptions” (unexpected errors or situations occured). The first image caused the texture processor to throw a mysterious floating point exception. In a later pass, the following image caused an exception […]

“One Millisecond Face Alignment with an Ensemble of Regression Trees”

This paper addresses the problem of Face Alignment for a single image. We show how an ensemble of regression trees can be used to estimate the face’s landmark positions directly from a sparse subset of pixel intensities, achieving super-realtime performance with high quality predictions. We present a general framework based on gradient boosting for learning […]

Bag of aerial words

Appearing in the New York Times, a posting by Mark Vanhoenacker about flight. The world’s airspace is divided. There are various sorts of divisions. To the pilots who cross them every day, their borders form what we may regard as the countries of the sky. […] An airplane typically navigates through sky countries along a […]

SIFTing through the pages of ARKIV

A book in one sense is an ordering of a set of images. Here, a probe to consider how the layout of a book could be used to (reconstruct) an ordering of its original constituent images using SIFT feature detection. Read more…

Scanscape

A scan is not a photograph. The scanner head is like a comb of light-emitting fingers that slowly strokes its subject in order to see it. The final image denies this temporality in its conventional single and simultaneous presentation. This probe attempts to reintroduce the temporality of the scanner. Continue reading…

Image gradients

imagegradient Image gradients are a fundamental transformation used in image processing, search indexing, and computer vision. Like a weather map showing the direction and strength of the wind, an image gradient depicts the strength and direction of changes in intensity over the surface of the image.