A method performed by an image registration entity includes obtaining a matching between a first set of objects in a first image of a scene and a second set of objects in a second image of the scene, and obtaining a first set of key-points from the first image and a second set of key-points from the second image. Image registration is performed by matching the first set of key-points to the second set of key-points. Those of the first set of key-points that are mapped to objects in the first set of objects and that have matching objects in the second set of objects are restricted to only be matched to those of the second set of key-points that are mapped to any of the matching objects in the second set of objects. The matching between key-points resulting from the image registration is applied when constructing an image representation of the scene.

A three-dimensional shape registration method includes a step of acquiring three-dimensional CT data of a subject and at least three positioning members, which are acquired by performing X-ray CT imaging on the positioning members together with the subject, a step of measuring relative positions between the subject and each of the positioning members, and a step of performing registration between the subject in the CT data and the subject in three-dimensional design data of the subject based on the CT data, the design data, and information on the relative positions.

Systems, methods and devices for use in tracking are described, using optical modalities to detect spatial attributes or natural features of objects, such as, tools and patient anatomy. Spatial attributes or natural features may be known or may be detected by the tracking system. The system, methods and devices can further be used to verify a calibration of a tool either by a computing unit or by a user. Further, the disclosure relates to detection of spatial attributes, including depth information, of the anatomy for purposes of registration or to create a 3D surface profile of the anatomy.

Systems and methods are disclosed for integrating imaging data from multiple sources to create a single, accurate model of a patient's anatomy. One method includes receiving a representation of a target object for modeling; determining one or more first anatomical parameters of the target anatomical object from at least one of one or more first images of the target anatomical object; determining one or more second anatomical parameters of the target anatomical object from at least one of one or more second images of the target anatomical object; updating the one or more first anatomical parameters based at least on the one or more second anatomical parameters; and generating a model of the target anatomical object based on the updated first anatomical parameters.

The mesh tracking described herein involves mesh tracking on 3D face models. In contrast to existing mesh tracking algorithms which generally require user intervention and manipulation, the mesh tracking algorithm is fully automatic once a template mesh is provided. In addition, an eye and mouth boundary detection algorithm is able to better reconstruct the shape of eyes and mouths.

An apparatus comprises processing circuitry configured to receive a plurality of training image data sets and a plurality of predetermined displacements. The processing circuitry is further configured to use the training image data sets and predetermined displacements to train a transformation regressor in combination with a discriminator in an adversarial fashion by repeatedly alternating a transformation regressor training process in which the transformation regressor is trained to predict displacements, and a discriminator training process in which the discriminator is trained to distinguish between predetermined displacements and displacements predicted by the transformation regressor.

A medical apparatus includes a registration tool, which includes a position sensor, A position-tracking system is configured to acquire position coordinates of the sensor in a first frame of reference defined by the position-tracking system. A processing unit is configured to receive 3D image data with respect to the body of the patient in a second frame of reference, to generate a 2D image of the surface of the patient based on the 3D image data, to render the 2D image to a display screen, and to superimpose onto the 2D image icons indicating locations of respective landmarks. The processing unit receives the position coordinates acquired by the position-tracking system while the registration tool contacts the locations on the patient corresponding to the icons on the display, and registers the first and second frames of reference by comparing the position coordinates to the three-dimensional image data.

There is provided with an image processing apparatus. An obtaining unit obtains a first image serving as a read image of an inspection target medium having undergone printing, and a second image serving as a read image of a reference medium representing a target print result. An inspection unit inspects a defect on the inspection target medium based on the first image and the second image by performing inspection at inspection settings different between a print region and a peripheral region of the inspection target medium.

Provided are a method and an apparatus for restoring an object image, capable of restoring an image naturally by detecting positions of landmarks of an object in a bounding-box detected from an input image, performing warping to align the object at a central position or a reference position on the basis of the landmarks, improving the image using a learning model learned from the aligned object image, performing inverse warping for rotating the improved object image in an original direction or at an original angle, and inserting the inversely-warped object image into the input image. In addition, provided are a method and an apparatus for restoring an object image, capable of detecting positions of landmarks of an object in a bounding-box detected from an input image, performing pose estimation for a side object on the basis of the landmarks, and improving an image using a learning model learned from a side object image corresponding to the pose estimation result.

In accordance with at least some embodiments of the present disclosure, a process to improve computed tomography (CT) to cone beam computed tomography (CBCT) registration is disclosed. The process may include receiving a CT image generated by CT-scanning of an object, and receiving a CBCT image generated by CBCT-scanning of the object. The process may include generating an image mask based on Digital Imaging and Communications in Medicine (DICOM) information extracted from the CBCT image. For a specific pixel in the CBCT image, the image mask contains a corresponding data-field indicating whether the specific pixel contains image data generated based on the CBCT-scanning of the object. The process may further include generating a registered image by utilizing the image mask to perform a DIR between the CT image and the CBCT image.