Abstract: A method for detecting an object of interest in an input image includes the computer-implemented steps of: receiving an image, providing a multi-class pose classifier that identifies a plurality of pose features for estimating a pose of the object of interest, providing a plurality of cascades of serially-linked binary object feature classifiers, each cascade corresponding to different poses of the object of interest in the input image, selecting at least one of the cascades using the estimated pose, and employing the selected cascades to detect instances of the object of interest in the image.

Abstract: A method and apparatus for three-dimensional visualization and analysis for automatic non-destructive examination of a solid Rotor using ultrasonic phased array is disclosed. Data is acquired by scanning a solid rotor with a phased array ultrasound transducer producing a plurality of two dimensional ultrasound scans. Each of a plurality of sample points of a plurality of two dimensional ultrasound scans are associated with a corresponding 3D image point of a regular grid. A kernel function for each of the plurality of sample points defining a size and shape of a kernel located at the corresponding image point is determined. A weight is assigned to each kernel which, in one embodiment, is based on the sample point value. A value for each image point of the regular 3D grid is determined based on kernels overlapping each image point. A three-dimensional volume representing the solid rotor is then visualized.

Abstract: A method and apparatus for three-dimensional (3D) visualization and analysis for automatic non-destructive examination of a rotor bore using ultrasound. Data is acquired by scanning the rotor bore with an ultrasound pulser/transducer producing a plurality of one-dimensional ultrasound scans, each scan having a plurality of sample points. Each sample point is associated with a voxel of a regular 3D grid having a plurality of voxels. A Gaussian kernel is associated with each sample point and a value for a particular voxel is determined based on a weighted sum of sample points whose kernels cover the particular voxel. The values for the other voxels of the regular 3D grid are determined similarly. A 3D visualization of the rotor bore can be displayed to a user.

Abstract: A method for detecting an object of interest in an input image includes the computer-implemented steps of: receiving an image, providing a multi-class pose classifier that identifies a plurality of pose features for estimating a pose of the object of interest, providing a plurality of cascades of serially-linked binary object feature classifiers, each cascade corresponding to different poses of the object of interest in the input image, selecting at least one of the cascades using the estimated pose, and employing the selected cascades to detect instances of the object of interest in the image.

Abstract: A method for estimating a configuration of an internal structure within a medical image includes detecting a location of the internal structure. Component-based identification is performed within the detected location of the internal structure to identify a plurality of components. The configuration of the internal structure is estimated based on the relative position of the identified components.

Abstract: Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.

Abstract: Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.

Abstract: Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.

Abstract: Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.