Active learning methods for remote sensing image classification

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.

Voyages astraux et hors du corps. Héautoscopie, extase et hallucinations expérientielles d'origine épileptique [Astral and out-of-body voyages. Heautoscopy, ecstasis and experimental hallucinations of epileptic origin]

We report a 38 year-old patient who had temporoparietal epilepsy and unusual ictal "out of body" experiences that remained undiagnosed for more than ten years, until her admission for a motor seizure of the left hemibody. Out of body episodes were experienced as intense and ecstatic astral journeys. EEG showed a bilateral extension of epileptiform abnormalities to the parietal regions, predominantly on the right side. We discuss the various forms of heautoscopy and their putative mechanisms. We suggest that a disturbance in representing space in independent extrapersonal and personal coordinates might be as crucial as the elusive hypothesis of a body schema disorder. Combined involvement of the parietal neocortex and temporolimbic structures might allow those experiences to gain a subjective vividness which appears to be indissociable from normal conscious experiences.

Direct Fourier Tomographic Reconstruction Image-To-Image Filter

We present an open-source ITK implementation of a directFourier method for tomographic reconstruction, applicableto parallel-beam x-ray images. Direct Fourierreconstruction makes use of the central-slice theorem tobuild a polar 2D Fourier space from the 1D transformedprojections of the scanned object, that is resampled intoa Cartesian grid. Inverse 2D Fourier transform eventuallyyields the reconstructed image. Additionally, we providea complex wrapper to the BSplineInterpolateImageFunctionto overcome ITKâeuro?s current lack for image interpolatorsdealing with complex data types. A sample application ispresented and extensively illustrated on the Shepp-Loganhead phantom. We show that appropriate input zeropaddingand 2D-DFT oversampling rates together with radial cubicb-spline interpolation improve 2D-DFT interpolationquality and are efficient remedies to reducereconstruction artifacts.