摘要:
The invention relates to a method and an apparatus for reconstructing a three-dimensional image volume from two-dimensional projection images of a subject which have been taken from different projection directions by rotating the recording system around the subject, wherein the grayscale values of the voxels of the image volume are calculated by back projection of the projection images. The invention is characterized in that prior to back projection at least one projection image is modified in such a way that it corresponds to a projection image taken with a virtual detector whose axes are aligned parallel to the rotational axis of the recording system.
摘要:
A calendar date display comprises a ten-day indicator (2) and a unit indicator (1) driven by a program drive (8), which is provided with a calendar date display (9) whose toothing is engaged with the beak (15) of a lever (16) in such a way that a wheel is moved one step forward by one date number change. Between each calendar number change, the beak (15) is engaged between the first and second teeth (11, 12) of the wheel (9). At the time of the calendar number change, the beak (15) is disengaged from said first and second teeth (11, 12) in such a way that it is engaged between the second and third (12, 13) teeth of the wheel (9), thereby moving said wheel one step forward.
摘要:
A method and an arrangement are presented for pattern recognition on the basis of statistics. According to the method, for an object to be recognized on the basis of a complete set of two-class or multiclass classifiers, the association with each target class of the class set is estimated with a numerical value that is produced by cascaded use of polynomial classifiers. According to the invention, on a learning sample in which all class patterns to be recognized are sufficiently represented, there is a selection, from all the two-class or multiclass classifiers by way of their estimation vector spectrum, of those two-class or multiclass classifiers with estimations contributing the most to minimize a scalar quantity calculated over the estimation vector spectrum and having high separating relevance. The selected two-class or multiclass classifiers are subsequently used to form, via an expanded learning sample, estimation vectors from which expanded characteristic vectors are produced by polynomial linking. An evaluation classifier is formed on the basis of said characteristic vectors for estimating all target classes.