Abstract:
A method of generating a three-dimensional (3D) face model includes extracting feature points of a face from input images comprising a first face image and a second face image; deforming a generic 3D face model to a personalized 3D face model based on the feature points; projecting the personalized 3D face model to each of the first face image and the second face image; and refining the personalized 3D face model based on a difference in texture patterns between the first face image to which the personalized 3D face model is projected and the second face image to which the personalized 3D face model is projected.
Abstract:
A method and an apparatus for registering a face, and a method and an apparatus for recognizing a face are disclosed, in which a face registering apparatus may change a stored three-dimensional (3D) facial model to an individualized 3D facial model based on facial landmarks extracted from two-dimensional (2D) face images, match the individualized 3D facial model to a current 2D face image of the 2D face images, and extract an image feature of the current 2D face image from regions in the current 2D face image to which 3D feature points of the individualized 3D facial model are projected, and a face recognizing apparatus may perform facial recognition based on image features of the 2D face images extracted by the face registering apparatus.
Abstract:
An apparatus for registering medical images includes a processor configured to acquire, via an ultrasound probe, a first cross-section of a first medical image, the first cross-section comprising a reference point of an object; and a memory configured to store a second medical image. The processor is configured to obtain a second cross-section of the second medical image corresponding to the first cross-section by using the reference point, and register the first and second medical images with each other.
Abstract:
At least some example embodiments disclose a device and a method for determining a landmark of an image. The device may compare, to a key landmark set as a reference landmark, a first candidate landmark detected from a region of interest (ROI) of an input image and a second candidate landmark tracked from a previous frame, and determine a landmark similar to the key landmark to be a final landmark.
Abstract:
A medical image registration method includes performing a first registration by registering first medical images, including a registration image and a display image, the display image being an image to be displayed, performing a second registration by registering a second medical image having a different modality than a modality of the first medical images, with the registration image, and extracting a cross-section of one of the first medical images, corresponding to a cross-section of the second medical image, from the display image, according to the first registration and the second registration.
Abstract:
A medical image registration method and apparatus are described. By performance of a medical image registration method, a highly accurate registered image, in which breathing deformation information is considered, may be obtained by generation of non-real-time medical images in which the breathing deformation information is reflected before a medical procedure is conducted and by rigid registration of a real-time medical image and the generated non-real-time medical images during the medical procedure.
Abstract:
A method and an apparatus for registering a face, and a method and an apparatus for recognizing a face are disclosed, in which a face registering apparatus may change a stored three-dimensional (3D) facial model to an individualized 3D facial model based on facial landmarks extracted from two-dimensional (2D) face images, match the individualized 3D facial model to a current 2D face image of the 2D face images, and extract an image feature of the current 2D face image from regions in the current 2D face image to which 3D feature points of the individualized 3D facial model are projected, and a face recognizing apparatus may perform facial recognition based on image features of the 2D face images extracted by the face registering apparatus.
Abstract:
A method for registering medical images includes calculating, when a probe is disposed on a reference point of a target, a transformation relation for registering a first medical image and a second medical image having a different modality from the first medical image by using the reference point, wherein the first medical image is obtained by using the probe; and obtaining a sectional image of the second medical image corresponding to a sectional image of the first medical image from the second medical image by using the transformation relation.
Abstract:
A method for registering medical images of different types, includes: receiving a selection of at least one point in a first medical image that is acquired in non-real time; extracting, from the first medical image, a first anatomic object which includes the selected point and a second anatomic object which is adjacent to the selected point; extracting, from a second medical image that is acquired in real time, a third anatomic object which corresponds to the first anatomic object and a fourth anatomic object which corresponds to the second anatomic object; and registering the first medical image and the second medical image based on a geometric relation between the first, second, third, and fourth anatomic objects.
Abstract:
Provided are a method and apparatus for registering medical images. The method includes: setting, as a reference, axis an axis of a probe that is disposed to be parallel to an axis of an object; extracting a first sub-object from a first medical image that is obtained by using the probe; extracting a second sub-object from a second medical image that has a modality different from a modality of the first medical image; and registering the first medical image and the second medical image by aligning the first sub-object and the second sub-object about the reference axis.