Abstract: Disclosed herein is a framework for facilitating adaptive anatomical region prediction. In accordance with one aspect, a set of exemplar images including annotated first landmarks is received. User definitions of first anatomical regions in the exemplar images are obtained. The framework may detect second landmarks in a subject image. It may further compute anatomical similarity scores between the subject image and the exemplar images based on the first and second landmarks, and predict a second anatomical region in the subject image by adaptively combining the first anatomical regions based on the anatomical similarity scores.

Abstract: A treatment recommending system of plant symptom includes an operation interface, an image capture unit, a processing unit and a storage unit for storing plant symptom data and diagnostic data. The processing unit may find target contour data presenting a plant part according to symptom description and symptom characteristic data. The image capture unit obtains plant image data corresponding to the target contour data. The processing unit analyzes the plant image data, and coordinates with the symptom characteristic data to determine corresponding treatment recommendation data.

Abstract: A tracking device is provided which includes an image information acquiring unit configured to acquire image information in the form of successive frames; and a tracking unit configured to generate a plurality of sub images each smaller than a frame of the acquired image information, to calculate likelihoods with eye images, and to decide locations of eyes using a sub image having a large likelihood value. The tracking unit decides locations of the sub images, based on locations decided by a frame of image information acquired before the one frame.

Abstract: Methods and systems for evaluating bone lesions include accessing a first dataset acquired from a patient with a first imaging modality and a second dataset acquired from the patient with a second imaging modality. A segmentation is performed on the first dataset to identify a subset of the first dataset corresponding to a skeletal structure of the patient and a patient skeletal metric representing a total bone volume of the patient is automatically calculated from the subset of the first dataset. The methods and systems further include detection of at least one lesion in the second dataset, classification of the at least one lesion as a bone or non-bone lesion, automatic calculation of a bone lesion metric based on the classification, and calculation of a lesion burden as a ratio of the bone lesion metric and the patient skeletal metric.

Abstract: Technologies are generally described for a general mood adding scheme in a cloud-based game system. In some examples, a method performed under control of a computing device may include receiving from a raw database at least one set of facial expression data, each of the at least one set of facial expression data being accompanied by time information and location information, clustering a geographic area to form at least one cluster based at least in part on the at least one set of facial expression data, and storing the at least one cluster in a map database corresponding to the area.

Abstract: A method for performing multi-level eye registration comprising: obtaining a first initial reference eye image by a first diagnostic device and defining a reference coordinate system; obtaining a second eye image by a surgery device, said second eye image being obtained in a pre-surgery phase before the surgery has started; performing a first registration between said first eye image and said second eye image to obtain a first registration result; obtaining a third eye image by said surgery device, said third eye image being obtained after surgery has started; performing a second registration between said second eye image and said third eye image to obtain a second registration result; combining said first and second registration results to obtain a combined registration result to thereby obtain a registration between said initial reference eye image obtained by said diagnostic device and said third eye image obtained by said surgery device after surgery has started.

Abstract: An object detection apparatus includes a first detection unit configured to detect a first portion of an object from an input image, a second detection unit configured to detect a second portion different from the first portion of the object, a first estimation unit configured to estimate a third portion of the object based on the first portion, a second estimation unit configured to estimate a third portion of the object based on the second portion, a determination unit configured to determine whether the third portions, which have been respectively estimated by the first and second estimation units, match each other, and an output unit configured to output, if the third portions match each other, a detection result of the object based on at least one of a detection result of the first or second detection unit and an estimation result of the first or second estimation unit.

Abstract: An image processing device (100) is configured such that an edge histogram creating section (130) calculates interproximal pixel luminance difference for each of pixels constituting a frame, and a first ratio, which is a ratio of pixels whose interproximal pixel luminance difference is greater than or equal to a first threshold, and an edge enhancement section (140) performs edge enhancement in such a way that a shoot component to be added is smaller for a frame having a larger first ratio.

Abstract: A method for forming a three-dimensional reconstructed image acquires two dimensional measured radiographic projection images over a set of projection angles, wherein the measured projection image data is obtained from an energy resolving detector that distinguishes first and second energy bands. A volume reconstruction has image voxel values representative of the scanned object by back projection of the measured projection data. Volume reconstruction values are iteratively modified to generate an iterative reconstruction by repeating, for angles in the set of projection angles and for each of a plurality of pixels of the detector: generating a forward projection that includes calculating an x-ray spectral distribution at each volume voxel, calculating an error value by comparing the generated forward projection value with the corresponding measured projection image value, and adjusting one or more voxel values using the calculated error value and the x-ray spectral distribution.

Abstract: 2D images are registered with 3D volume data. In order to provide 2D/3D registration with a facilitated workflow 3D volume data (112) of an object, having a frame of reference is received. A transformation plane (116) is defined in relation to the 3D volume data. A 2D image of the object with an image plane is received. The transformation plane is projected on the image plane. The frame of reference is aligned with the 2D image. At least one alignment interaction value (128) is projected (130) on the transformation plane to determine (134) at least one transformed interaction value (132). The frame of reference is translated with the at least one transformed interaction value.

Abstract: A method of separating an object in a three dimension point cloud including acquiring a three dimension point cloud image on an object using an image acquirer, eliminating an outlier from the three dimension point cloud image using a controller, eliminating a plane surface area from the three dimension point cloud image, of which the outlier has been eliminated using the controller, and clustering points of an individual object from the three dimension point cloud image, of which the plane surface area has been eliminated using the controller.

Abstract: A gesture recognition module for recognizing a gesture of a user, includes a detecting unit, including at least one image capture device, for capturing at least one image of a hand of the user, to obtain a first position and a second position of the hand sequentially; a computing unit, electrically coupled to the detecting unit, for determining a first angle between a first virtual straight line connected between a fixed reference point and the first position and a reference plane passing through the fixed reference point, and determining a second angle between a second virtual straight line connected between the fixed reference point and the second position and the reference plane; and a determining unit, electrically coupled to the computing unit, for determining a relation between the first angle and the second angle, to decide whether a gesture of the hand is a back-and-forth gesture.

Abstract: A computer-implemented method is provided for anatomically indexing a subject. The method includes: receiving image scan data representing a volume of a subject, where the image scan data is comprised of a plurality of image slices of the subject and includes at least a portion of a vertebral column of the subject; identifying the vertebral canal of the vertebral column of the subject in the image scan data; determining a plurality of markers for the vertebral column, where each marker is indicative of a different vertebral body of the vertebral column and includes its location in the image scan data defined in a coordinate system, such that the plurality of markers define a vertebral level coordinate system; and storing each marker along with its location in a database. The markers can subsequently be used to reference other anatomical components of the subject across different image scans.

Abstract: Photographic images recorded with mobile mapping vehicles (20) in real life situations usually contain cars or other moving objects (34) that cover visual information on the road surface (24). According to the techniques of this invention, moving objects (34) are detected by grayscale differencing in overlapping pixels or sections of two or more orthorectified image tiles. Based on moving object identification, masks are generated for each orthorectified tile. The masks are then compared and priorities established based on grayscale values associated with the masks. Mosaics of a large surface of interest such as the Earth can be assembled from a plurality of overlapping photographic images with moving objects (34) largely removed from the resulting mosaic.

Abstract: A three dimensional (3D) sensing method and an apparatus thereof are provided. The 3D sensing method includes the following steps. A resolution scaling process is performed on a first pending image and a second pending image so as to produce a first scaled image and a second scaled image. A full-scene 3D measurement is performed on the first and second scaled images so as to obtain a full-scene depth image. The full-scene depth image is analyzed to set a first region of interest (ROI) and a second ROI. A first ROI image and a second ROI image is obtained according to the first and second ROI. Then, a partial-scene 3D measurement is performed on the first and second ROI images accordingly, such that a partial-scene depth image is produced.

Abstract: An optical image of a source document is captured. Two or more source document image test regions are then defined/determined. An optical image scan is performed on each source document image test region to determine if there are identifiable alpha-numeric characters or symbols present. If one or more of the source document image test regions are determined not to contain identifiable alpha-numeric characters, the captured optical image of the source document is determined to be of insufficient quality to identify and extract individual characters and symbols and it is recommended that optical images of source documents determined to be of insufficient quality to identify and extract individual characters and symbols be re-captured using an image capture device.

Abstract: A method for performing multi-level eye registration comprising: obtaining a first initial reference eye image by a first diagnostic device and defining a reference coordinate system; obtaining a second eye image by a surgery device, said second eye image being obtained in a pre-surgery phase before the surgery has started; performing a first registration between said first eye image and said second eye image to obtain a first registration result; obtaining a third eye image by said surgery device, said third eye image being obtained after surgery has started; performing a second registration between said second eye image and said third eye image to obtain a second registration result; combining said first and second registration results to obtain a combined registration result to thereby obtain a registration between said initial reference eye image obtained by said diagnostic device and said third eye image obtained by said surgery device after surgery has started.

Abstract: An apparatus and a method for detecting an obstacle are provided. The apparatus includes a memory configured to store program instructions and a processor that is configured to execute the program instructions. The program instructions when executed are configured to compensate a position of a second image based on a first image based on a moving distance of a vehicle between the first image and the second image captured at different times and respectively generate a difference image based on a difference between the first image and the second image and between the first image and the second image in which the position is compensated. In addition, binarization is performed of the difference image and a synthetic image is generated for the two difference images. Then, the obstacle is detected by selecting a pixel corresponding to an area where the bit value is detected from the synthetic image.

Abstract: A target image is deformed in such a manner that a subject in a reference image and a subject in the target image will coincide. A reference image and a target image are each divided into regions that conform to amounts of optical distortion. A region which is in the target image and which is common to the reference image and to the target image is subdivided into regions S35 to S37, S38 to S40, S42 to S44 in each of which amounts of optical distortion of both the reference image and target image are obtained. By using the amounts of optical distortion of the reference image and amounts of optical distortion of the target image 11 obtained from the subdivided regions S35 to S37, S38 to S40, S42 to S44, the target image is deformed in such a manner that a subject in the common region will coincide with the reference image.

Abstract: In a method of estimating a camera attitude, based on the past-detected position of a marker and an appropriate camera attitude provided during current frame imaging, the position of the maker to the current frame is approximately predicted. Through extraction of points which are near the predicted marker position (marker neighboring points), a group of points are obtained. An attitude of the camera (rotation matrix and translation matrix) which optimizes an estimation function is obtained for re-estimating the camera attitude, where the estimation function needs, as its condition, a distance between the marker neighboring points included in the point groups and an estimation plane on which the marker is positioned. The point groups include many points extracted from the neighborhood of the marker, so that the preliminarily estimated approximate camera attitude can be corrected and estimated with higher accuracy even in an environment with occlusion.