Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.v.

Friedrich-Alexander-Universitat Erlangen-Nürnberg

Tobias Bergen

Thomas Wittenberg

Christian Winter

Christian Münzenmayer

Andreas Ernst

Stephan Rupp

Dietrich Paulus

Christian Muenzenmayer

Steffen Ruthotto

Thorsten Zerfass

Jens-Uwe Garbas

Matthias Elter

Frederik Zilly

Dirk Steckhan

Michaela Benz

Malte Avenhaus

Alexander Gryanik

Mathis Hoffmann

Christian MÜNZENMAYER

Nikita Shevchenko

Martin Raithel

Christian Dr-Ing Winter

A method for detecting a known pattern having homogeneous areas includes the steps of taking an image of the known pattern or, of at least a portion of the known pattern, and performing detection. Detection includes an initial detection of a first region of the image and the detection of a feature of the known pattern within a second region of the image. The second region is arranged adjacent to the first region. The initial detection is aimed at estimating at least one region parameter, such as a position of the region of the pattern, and/or orientation of the region or distortion of same. Starting from this, the second region can be selected in which a feature, such as a corner of the checkerboard is detectable. This second detection step is aimed at obtaining at least one region parameter such as the position of a feature within the second region.

Pattern detection

Image processing device for producing in real-time a digital composite image from a sequence of digital images recorded by a camera device, in particular an endoscopic camera device, the image processing device including a selecting unit, a key point detection unit, a transforming unit and a joining unit, wherein the key point detection unit includes a maximum detection unit configured for executing following steps separately for the filter response for the reference image and for the filter response for the further image, wherein a variable threshold is used:i) creating blocks by dividing the respective filter response,ii) calculating the variable threshold for each of the blocks,iii) discarding those blocks of the blocks from further consideration, in which the respective filter response at a reference point of the respective block is less than the respective variable threshold.

Image processing device and method for producing in real-time a digital composite image from a sequence of digital images

Embodiments of the present invention relate to a method for generating a microscopy representation of a three-dimensional sample having a lateral extension in the x and y directions. The method has the following steps: a) arranging the flat three-dimensional sample on a positioner; b) recording the sample by means of an imaging device to obtain a first microscopy picture of the sample having a first section; c) altering the perspective onto the two-dimensional sample in the z direction; d) recording the sample by means of the imaging device to obtain a second microscopy picture of the sample having a second section; e) determining change information which allows drawing conclusions as to the change in perspective in the z direction, using a difference between the first and second microscopy pictures; and f) merging the first and second microscopy pictures while considering the change information to obtain the microscopy panoramic representation.

Method and device for generating a microscopy panoramic representation

In a device and a corresponding method for joining a plurality of individual digital images to form a total image, a plurality of features is determined in a first individual image by means of a selection unit using a feature-based algorithm and then tracked in a second individual image by means of a tracking unit. A transformation matrix, with which the individual images are joined in an output unit to form the total image, is calculated from the determined feature correspondences in a transformation unit. The individual images can be joined in real time and with a high degree of accuracy by means of the feature-based algorithm in combination with a robust algorithm to calculate the transformation matrix.

Method and device for joining a plurality of individual digital images to form a total image

In a sensor system and a corresponding method for image capture of an object, an imaging sensor is arranged in a recording area of an optical sensor, the recording area being defined for the object, in such a way as to be essentially stationary relative to said object. By means of an evaluation unit, relative movements between the imaging sensor and the object can be derived from the recorded image data of the optical sensor, and a three-dimensional object image can be reconstructed from the imaging data as a function of the relative movements. When determining the relative movements, it is in particular possible as well to detect relative movements caused by the object's own motion which can be taken into account when reconstructing the object image. As a result, a high image quality of the object image is achieved.

Sensor system and method for image capture of an object

In a method and a device for the segmentation of a lesion, a quantity of candidate regions for the lesion is determined proceeding from a starting region by means of a candidate unit. The candidate regions are arranged substantially concentrically to the starting region. A candidate region closest to the lesion is selected automatically by means of a selection unit or manually by means of a correction unit from the quantity of candidate regions. The selected candidate region is a reliable and robust basis for a classification of the lesion.

Method and device for the segmentation of a lesion

A method for determining a contour of an object in a digital image includes determining a preliminary object center and determining contour candidate image points. The contour candidate image points are determined as image points on a plurality of paths leading away from a preliminary object center by detecting a change from a first section to a second section on a feature space based on the image point value range of the digital image or by detecting the exceeding of a predetermined strength of a feature change in the feature space, wherein the contour candidate image points have a distance to the preliminary or to an improved object center and are ordered according to a polar angle. Further, the method includes determining zones of neighboring contour candidate image points within which a change of the distance of the contour candidate image points lies above a threshold value and an elimination of contour candidate image points which lie between the zones of neighboring contour candidate image points. Finally, a determination of the contour is executed on the basis of the remaining contour candidate image points.

Method and device for determining a contour and a center of an object

Growing community of inventors

Erlangen, Germany

Tobias Bergen