Abstract: An image acquisition unit of a machine learning device acquires n learning images assigned with labels to be used for categorization (n is a natural number larger than or equal to 2). A feature vector acquisition unit acquires a feature vector representing a feature from each of the n learning images. A vector conversion unit converts the feature vector for each of the n learning images to a similarity feature vector based on a similarity degree between the learning images. A classification condition learning unit learns a classification condition for categorizing the n learning images, based on the similarity feature vector converted by the vector conversion unit and the label assigned to each of the n learning images. A classification unit categorizes unlabeled testing images in accordance with the classification condition learned by the classification condition learning unit.

Abstract: The present disclosure relates to systems, methods, and computer-readable storage media for segmenting medical image. Embodiments of the present disclosure may locate a target in a three-dimensional (3D) volume. For example, an image acquisition device may provide a 3D medical image containing a region of interest of the target. A processor may then extract a plurality of two-dimensional (2D) slices from the 3D image. The processor may also determine a 2D patch for each 2D slice, wherein the 2D patch corresponds to an area of the 2D slice associated with the target. The processor may also convert the 2D patch to an adaptive filter model for determining a location of the region of interest.

Abstract: An estimation method executed by a computer includes: extracting, from an image, a plurality of characteristic points satisfying a certain requirement regarding changes in gray levels between the plurality of characteristic points and surrounding points; identifying, as map points from the plurality of characteristic points, characteristic points existing on planes, by excluding corners of an object depicted on the image; extracting, from another image, another plurality of characteristic points satisfying the certain requirement; executing matching of the another plurality of characteristic points with the map points based on a region including the map points; and estimating, based on results of the matching, a position and an orientation of an imaging device while the another image is captured.

Abstract: A digital image of a surface of a check is received. A check scanning device captures the digital image as the check moves through the check scanning device. A fingerprint is impressed on the surface of the check. A computing system uses the digital image to determine an initial match score for the fingerprint image and an image quality metric to create an adjusted match score. An alert is presented based on the adjusted match score.

Abstract: Provided are an apparatus and a method for generating a multi-viewpoint image. The apparatus includes: a camera photographing a stereo image; an image processing unit detecting features from left and right images of the stereo image; a reference image generating unit generating a reference image for viewpoint n by warping an image which is distant between the left image and the right image at viewpoint n based on an n-th viewpoint among N viewpoints that exist between the left image and the right image; and a warping image generating unit calculating a warping equation for viewpoint n by using the reference image and generating a final warping image for viewpoint n by using the calculated warping equation.

Abstract: Provided is an image evaluation device including an acquisition unit that acquires an image including plural patterns having different spatial frequencies and contrasts, and an output unit that compares each of plural patterns included in the image acquired by the acquisition unit with each of plural ideal patterns corresponding to the plural patterns, calculates similarities therebetween, and outputs an evaluation value for evaluating performance regarding a resolution of the image based on a sum of the calculated similarities of the plural patterns.

Abstract: A method of generating a patient-specific prosthetic includes receiving anatomic imaging data representative of a portion of a patient's anatomy. A first digital representation of the anatomic imaging data is defined. The first digital representation of the anatomic imaging data is modified. A second digital representation of the portion of the patient's anatomy is defined based on the modifying of the first digital representation of the anatomic imaging data. A patient-specific prosthetic template of the portion of the patient's anatomy is generated based at least in part on the second digital representation of the anatomic imaging data.

Abstract: A method of generating a patient-specific prosthesis includes receiving anatomic imaging data representative of a portion of a patient's anatomy. A first digital representation of the anatomic imaging data is defined. The first digital representation of the anatomic imaging data is modified. A second digital representation of the portion of the patient's anatomy is defined based on the modifying of the first digital representation of the anatomic imaging data. A patient-specific prosthesis is generated based at least in part on the second digital representation of the anatomic imaging data.

Abstract: A three-dimensional object recognition apparatus according to the invention includes: an omnidirectional sensor that measures surrounding objects in all directions, and generates positional information capable of specifying positions of the objects as a result of the measurement; a three-dimensional measurement device that measures an object within a certain measurement range among the surrounding objects, and generates three-dimensional shape information capable of specifying a three-dimensional shape of the object as a result of the measurement; and a control unit that updates a shape to be recognized as the three-dimensional shape of the object based on the three-dimensional shape information generated by the three-dimensional measurement device when the object is within the measurement range of the three-dimensional measurement device.

Abstract: An object identification apparatus selects, for each partial area of an object in a registered image, a corresponding sample image from sample images based on feature quantities of the partial area, for objects in the registered image, sets a similarity of feature quantities for each partial area between objects of an identical individual and between objects of different individuals based on a similarity related to the selected sample images for each partial area, makes a discriminator learn based on the set similarity, acquires a similarity for each partial area between objects in an input image and the registered image, and determines whether the object in the input image is identical to the object in the registered image based on the acquired similarity and a result of discrimination by the discriminator.

Abstract: An apparatus performs a biometric authentication by acquiring matching data detected at a time of a biometric authentication and including a matching biometric data, a manner of holding and a posture of a terminal. A processor performs a process including acquiring matching data detected at a time of a biometric authentication and including a matching biometric data, a manner of holding and a posture of the terminal, and performing a matching process. The matching process compares the matching data and registered data including registered biometric data related to manners of holding and postures of the terminal, to extract the registered data including the manner of holding and the posture similar to those included in the matching data, and judge a successful biometric authentication when a similarity of the registered biometric data included in the extracted registered data with respect to the matching biometric data is a threshold value or greater.

Abstract: An estimation method executed by a computer includes: extracting, from an image, a plurality of characteristic points satisfying a certain requirement regarding changes in gray levels between the plurality of characteristic points and surrounding points; identifying, as map points from the plurality of characteristic points, characteristic points existing on planes, by excluding corners of an object depicted on the image; extracting, from another image, another plurality of characteristic points satisfying the certain requirement; executing matching of the another plurality of characteristic points with the map points based on a region including the map points; and estimating, based on results of the matching, a position and an orientation of an imaging device while the another image is captured.

Abstract: The present invention relates to a method for reconstructing a 3D image from 2D X-ray images acquired with an X-ray imaging system, said method comprising the steps of: a) receiving a set of 2D X-ray images of a region of a patient with said X-ray imaging system, b) computing an initial 3D image within the coordinate system of the X-ray imaging system by using at least part of said 2D X-ray images with their respective projective geometry data; c) projecting said initial 3D image on at least part of said 2D X-ray images and adjusting the respective projective geometry data of said images, said adjustment comprising registration of said images with the projection of the initial 3D image using an image-to-image registration technique; d) computing an updated 3D image using the complete set of 2D X-ray images with their respective adjusted projective geometry data.

Abstract: The size of a feature descriptor is reduced with the accuracy of object identification maintained. A local feature descriptor extracting apparatus includes a feature point detecting unit configured to detect feature points in an image, a local region acquiring unit configured to acquire a local region for each of the feature points, a subregion dividing unit configured to divide each local region into a plurality of subregions, a subregion feature vector generating unit configured to generate a feature vector with a plurality of dimensions for each of the subregions in each local region, and a dimension selecting unit configured to select dimensions from the feature vector in each subregion so as to reduce a correlation between the feature vectors in proximate subregions based on positional relations among the subregions in each local region and output elements of the selected dimensions as a feature descriptor of the local region.

Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.

Abstract: An image generation apparatus includes a holding unit configured to acquire and hold pixel values of pixel groups that serve as targets for comparison from the respective first and second images; a reading unit configured to sequentially read out, from the pixel values of the respective pixel groups that are held in the holding unit, pixel values in one direction for each area that is set depending on a pixel position of the range image; a calculation unit configured to calculate an evaluation value based on the pixel values read out by the reading unit; an estimation unit configured to estimate the subject distance based on the evaluation value; and a generation unit configured to generate a range image based on the subject distance estimated by the estimation unit.

Abstract: Systems and methods are disclosed for correcting for artificial deformations in anatomical modeling. One method includes obtaining an anatomic model; obtaining information indicating a presence of an artificial deformation of the anatomic model; identifying a portion of the anatomic model associated with the artificial deformation; estimating a non-deformed local area corresponding to the portion of the anatomic model; and modifying the portion of the anatomic model associated with the artificial deformation, based on the estimated non-deformed local area.

Abstract: A method of determining the histological grade of Hepatocellular Carcinoma (HCC) including: acquiring a Computed Tomography (CT) image of a person including an HCC tumor; delineating the HCC tumor; and assigning a histological grade to the HCC tumor, wherein assigning the histological grade to the HCC tumor includes: applying a plurality of filters to the HCC tumor, wherein each of the filters produces a corresponding response image and, for each of the filters, a convolution operation is performed on the filter and the CT image to produce the response image corresponding to that filter; computing an average response of the HCC tumor in each of the response images and recording each of the average responses as an Independent Subspace Analysis (ISA) feature; and determining the histological grade of the HCC tumor based on the ISA features by using a classifier.

Abstract: There is provided an image processing apparatus including a movement amount deciding unit configured to decide a movement amount for moving a target object that is a movement target among objects included in a plurality of captured images imaged by an imaging device including optical units that have imaging ranges overlapping with each other in part on the basis of a distance from the imaging device to the target object and an angle from a reference line at a reference position of the imaging device to the target object in a manner that the plurality of captured images look like images imaged from the reference position, the imaging device using all directions as an imaging range, the plurality of captured images corresponding to the respective optical units.

Abstract: There is provided a method of producing a hydrolysate containing sugar from a lingocellulosic biomass, comprising the steps of: a) pretreating the lingocellulosic biomass in a pretreatment process to form a slurry comprising cellulosic particles; b) saccharification of the slurry obtained in step a) in the presence of hydrolytic enzymes in an enzymatic hydrolysis process to obtain a hydrolysate containing sugar; c) analyzing cellulosic particles present in the slurry obtained in step a) and/or cellulosic particles present in the enzymatic hydrolysis process during step b) using an image analysis method to obtain a data set; and d) controlling at least one process parameter of the pretreatment process in step a) and/or enzymatic hydrolysis process in step b) in response to the data set obtained in step c). A corresponding system is also provided.