Abstract: A reference density profile is generated in an outer circumference direction of a pipe having a reference welded portion on the basis of a reference fluoroscopic image generated from a radiation detection medium when a radiation source is disposed on a central axis of the pipe. A weld inspection density profile is generated in an outer circumference direction of a pipe having an inspection target welded portion on the basis of a weld inspection fluoroscopic image. On the basis of the reference density profile and the weld inspection density profile, density correction information is calculated. The density correction information is for correcting density irregularities in the weld inspection fluoroscopic image in the outer circumference direction of the pipe. On the basis of the density correction information, the density irregularities in the weld inspection fluoroscopic image arc corrected.

Abstract: Apparatus and methods for inspecting a specimen are disclosed. An inspection tool is used at one or more operating modes to obtain images of a plurality of training regions of a specimen, and the training regions are identified as defect-free. Three or more basis training images are derived from the images of the training regions. A classifier is formed based on the three or more basis training images. The inspection system is used at the one or more operating modes to obtain images of a plurality of test regions of a specimen. Three or more basis test images are derived from to the test regions. The classifier is applied to the three or more basis test images to find defects in the test regions.

Abstract: Provided us a visual cortical circuit apparatus comprising: a current mirror unit which uses a transistor as a current source to generate a current having the same size as that of a reaction; a transconductance unit which takes, as an input, the current generated by the current mirror unit and outputs a voltage using a transconductance; and a buffer unit for converting the voltage output from the transconductance unit into a current and buffering the current.

Abstract: A method in a computing device for quantitative surgical image registration includes: prior to a surgical procedure, obtaining, using a first imaging modality, a preoperative image of patient tissue and a plurality of preoperative measurements of a material property of the patient tissue. The preoperative measurements correspond to respective points in the preoperative image. The method includes storing the preoperative image and the preoperative measurements, and during the surgical procedure, using a second imaging modality, capturing an intraoperative image of the patient tissue and a second plurality of intraoperative measurements of the material property of the patient tissue. The intraoperative measurements correspond to respective points in the intraoperative image.

Abstract: An image processing apparatus includes a position information obtaining unit and a region detection unit. The position information obtaining unit obtains position information indicating a representative position of one or more designated regions in an image. The region detection unit detects the one or more designated regions from the position information. The region detection unit cancels a setting of the one or more designated regions for pixels within a predetermined portion of the image, and detects the one or more designated regions again for the pixels within the predetermined portion, based on a reference pixel selected from among pixels on the image for which the setting of the one or more designated regions has not been canceled.

Abstract: Provided is a method for compensating for tissue motion during magnetic resonance (MR) imaging, and an apparatus for use thereof. The method includes acquiring a plurality of short-time MR scan images; selecting a reference scan image from the acquired plurality of short-time MR scan images; defining a set of transformation images based on the acquired plurality of short-time MR scan images other than the selected reference scan image; registering the reference scan image and the defined set of transformation images; calculating an average of aligned, registered images of the defined set of transformation images; and generating a motion-corrected image based on the calculated average.

Abstract: The present invention relates to a system (200) and method for determining a relation between a first scene and a second scene. The method comprises the steps of generating at least one sensor image of a first scene with at least one sensor; accessing information related to at least one second scene, said second scene encompassing said first scene, and matching the sensor image with the second scene to map the sensor image onto the second scene. The step of accessing information related to the at least one second scene comprises accessing a 3D map comprising geocoded 3D coordinate data. The mapping involves associating geocoding information to a plurality of positions in the sensor image based on the coordinate data of the second scene.

Abstract: According to an embodiment, a device includes a detector, first and second recognizers, an estimator, a second recognizer, and an output unit. The detector is configured to detect a visible text area including a visible character from an image. The first recognizer is configured to perform character pattern recognition on the visible text area, and calculate a recognition cost according to a likelihood of a character pattern. The estimator is configured to estimate a partially-hidden text area into which a hidden text area estimated to have a hidden character and the visible text area are integrated. The second recognizer is configured to calculate an integrated cost into which the calculated cost and a linguistic cost corresponding to a linguistic likelihood of a text that fits in the entire partially-hidden text area are integrated. The output unit is configured to output a text selected or ranked based on the integrated cost.

Abstract: The present disclosure discloses a method and a terminal device for processing an image. The method includes: acquiring an image; recognizing a face contained in the image; acquiring information of character features according to the face in the image; processing the image according to the information of character features; and obtaining the processed image. In the embodiments of the present disclosure, by automatically recognizing the face in the image, and acquiring the information of character features thereby acquiring a cosmetic process mode corresponding to the information of character features, and then processing the image according to the selected cosmetic process mode, manual setting of cosmetic process parameters can be avoided and the efficiency of image processing can be improved.

Abstract: Systems and methods are described for identifying the video content as spherical video or non-spherical video in response to determining that frame scores and video scores satisfy a threshold level. For example, a plurality of image frames can be extracted from video content, classified in a dual stage process, and scored according to particular classification and scoring mechanisms.

Abstract: Systems and methods are disclosed for background modeling in a computer vision system for enabling foreground object detection. A video acquisition model receives video data from a sequence of frames. A fit test module identifies a foreground object from the video data and defines a foreground mask representative of the identified foreground object. A foreground-aware background estimation module defines a first background model from the video data and then further defines an updated background model from an association of a current frame of the video data, the first background model and the foreground mask.

Abstract: One example method to determine a position of a probe in a surgical site with a plurality of reference structures may include receiving a three-dimensional image of the surgical site generated before the probe enters the surgical site and receiving a first two-dimensional image generated by the probe from a position within the surgical site. The three-dimensional image is associated with a first coordinate system, and the first two-dimensional image is associated with a second coordinate system.

Abstract: A method and system for registering pre-operative images and intra-operative images using biomechanical simulations is disclosed. A pre-operative image is initially registered to an intra-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image, such as the liver, surrounding tissue, and the abdominal wall, using biomechanical gas insufflation model constrained. The initially registered pre-operative image is then refined using diffeomorphic non-rigid refinement.

Abstract: The present disclosure relates to a system and method for image registration and image subtraction. The technique includes perform acquiring data related to the image processing, performing a pre-processing of the images, performing an image registration, performing an image subtraction, performing a post-processing of the images and managing storage of the data.

Abstract: A reconfigurable image scaling circuit includes a horizontal scalar, a bufferer, and a vertical scalar. The horizontal scalar is configured to generate a horizontally scaled image data by scaling an input image data horizontally. The bufferer includes a mapper and a plurality of buffers. The plurality of the buffers are configured to store the horizontally scaled image data. The vertical scalar is configured to generate an output image data by scaling the horizontally scaled image vertically using a vertical scaling method.

Abstract: A disparity value deriving device includes an acquisition unit configured to acquire a degree of matching between a reference region in a reference image captured from a first imaging position and each of a plurality of region in a designated range including a corresponding region to the reference region in a comparison image captured from a second imaging position; a synthesizer configured to synthesize the degree of matching of a reference region in neighborhood of a predetermined reference region in the reference image and the degree of matching of the predetermined reference region in the reference image; and a deriving unit configured to derive a disparity value of an object whose image is being captured in the predetermined reference region and a corresponding region to the predetermined reference region, based on a synthesized degree of matching obtained by the synthesizer.

Abstract: The technology disclosed relates to tracking movement of a real world object in three-dimensional (3D) space. In particular, it relates to mapping, to image planes of a camera, projections of observation points on a curved volumetric model of the real world object. The projections are used to calculate a retraction of the observation points at different times during which the real world object has moved. The retraction is then used to determine translational and rotational movement of the real world object between the different times.

Abstract: A method for measuring overlay includes receiving a first image of a first overlay mark captured using light having a first wavelength. The method includes receiving a second image of a second overlay mark captured using light having a second wavelength different from the first wavelength. The method includes measuring a displacement between a central portion of the first image and a central portion of the second image, wherein the first and second overlay marks are disposed on different levels.

Abstract: A method for identity verification using biometric data is disclosed herein. The method comprises receiving, by a processor, an image of an identification document and receiving a video associated with a face of a user. A predefined number of frames is selected in the video. Based on the selection, it is determined whether the video depicts a live person. Additionally, the face of the user in the video is compared with the image of the identification document and, based on the comparing, results of the identity verification are provided.

Abstract: The image processing device generates an operation image by adding or subtracting an original image and a standard deviation image which maps the standard deviation for the pixels configuring the original image. In this operation image, images of the structures seen in parts in the original image other than metal pieces are erased. Consequently, structures that are not metal pieces appearing in the original image in a whitish color, for example, do not appear in the operation image. If such an operation image is subjected to binarization processing in which the metal pieces appearing in a whitish color, for example, are extracted, since accurate graph cut processing is then possible, images originating from structures that are not metal pieces do not appear in the resulting image.