Koninklijke Philips Corporation N.V.

U.S. Philips Corporation

Sh&eacute;rif Makram-Ebeid

Raoul Florent

Steven Lobregt

Sylvain Devillers

Thomas D Deschamps

Laurent Cohen

Christel Soyer

Olivier Gerard

Matthieu Philip

Image processing method and system for following a moving object from one image to an other image sequence

The invention relates to an image processing method with steps of acquiring (1) a sequence of translation overlapping images ( ) representing an elongated scene; determining regions (ROI) in image pairs (Pk) and region sections (Bj) having dimensions suitable for matching (2); estimating region and section displacement fields ( ); regularizing (3) said region and section displacement fields ( ); interpolating pixel values of sections that have dimensions suitable for merging calculated from the regularized section displacement field, so as to evaluate the pixel values of corresponding regions and further scaling the sections in said regions to dimensions calculated from the regularized region displacement field, and reconstructing (4) an overview image ( ) of the elongated scene ( ) with said regions. The invention also relates to a system for implementing said method and a medical examination apparatus having said image processing system.

Image processing method, system and apparatus for forming an overview image of an elongated scene

The invention relates to an image processing method for processing an image representing a tubular structure having walls, comprising steps for determining a flight path (EP) inside this tubular structure between a first and a second predetermined end points, said flight path being both the shortest path between said end points and the farthest from the structure walls (NB ). Said steps may comprise locating the structure wall points, determining a surface at a predetermined constant distance from said wall points, inside the structure, for forming a central region (CR), and determining, in said central region, the shortest path (EP) between the first and second end points.

Image processing method, system and apparatus for processing an image representing tubular structure and for constructing a path related to said structure

The invention relates to an image processing method for preserving the edges of objects reproduced in an intensity image and for reducing the noise, including the steps of acquisition of the intensity image in the form of a multidimensional matrix of points (2-D, 3-D), determination of the intensity gradient at each point, defined by its direction ((&thgr; ) and its modulus (&par;{right arrow over (G)} &par;), and the passage at each point of a recursive spatial filter having an anisotropic kernel and providing a degree of smoothing which is greater in the direction perpendicular to the direction of the gradient than in the direction of the intensity gradient. The kernel is spherical on the scanning lines which are not normal to the intensity gradient and it is shaped as a flattened sphere whose major dimension extends in the direction of lines normal to the intensity gradient in a scanned point. The invention also relates to a medical X-ray imagine apparatus for carrying out this method.

Method of processing a noisy multidimensional image and medical imaging apparatus for carrying out this method

An image processing method which includes the acquisition ( ) of an intensity image (J) formed by a matrix of points (A) having non-binary intensity values and representing filiform objects, and also includes steps for the detection of filiform objects, which steps include: automatic determination ( ) of an intensity vector field ({right arrow over (V)}), forming a state image constituted by characteristics concerning magnitudes and angles &lsqb;&par;{right arrow over (V)}&par;,&thgr;&rsqb; of intensity vectors a the various points (A) of the intensity image, an operation ( ) for chaining the points of an individual filiform object by means of automatic filtering &lsqb;Q(i)&rsqb; of the state image, thus performing a selection of a dense and continuous field of intensity vectors corresponding to points of the filiform object.

Image processing method including a chaining step, and medical imaging apparatus including means for carrying out this method

Image processing method and system involving contour detection steps

The invention relates to a method for the processing of a multidimensional image which is formed by points representing objects of different intensity and are delimited from a background by way of their edges; this method includes steps for the segmentation (,) of the image into cells belonging to the background and cells belonging to the objects, for the application of criteria which impose that said cells (C,) have substantially uniform intensities, that the cells neither intersect nor enclose any object edge, and that the object edges coincide with cells edges; this method includes a step for the presegmentation (,) of the image into a first number of cells while performing a classification of the image points in the various cells as a function of intensity gradients of these points, and an actual segmentation step (,) for reducing the first number of cells by classifying the cells in the form of pairs of adjoining cells (C,, C,), by evaluating a merger threshold (&lgr;,(j,k)) for the cells of the pairs as a function of their intensity variance (&sgr;,) and of their intensity gradients (&par;G&par;), by evaluating a specific merger threshold (l,) below which a predetermined number (H,) of adjoining cells of pairs is merged, and by performing the concomitant merger of adjoining cells of pairs whose merger threshold is below said specific threshold.

Growing community of inventors

Dampierre, France

Shérif Makram-Ebeid

Growing community of inventors

Dampierre, France

Sh&eacute;rif Makram-Ebeid

Shérif Makram-Ebeid