Empire Technology Development LLC

Hankuk University of Foreign Studies Research and Industry-university Cooperation Foundation

Il Dong Yun

Dong Jin Kwon

Techniques for generating three dimensional image data with brushstroke effects from a two dimensional image is disclosed. One or more three dimensional brushstroke patterns from at least one brushstroke are generated. A two dimensional image is partitioned into one or more color regions. For each color region, each three dimensional brushstroke pattern is transformed to obtain a brushstroke effect. Each transformed three dimensional brushstroke pattern is then applied to each color region to generate a three dimensional image data having the brushstroke effect.

Reconstructing three dimensional oil paintings

An image displaying apparatus includes a base capable of supporting an object, a camera configured to capture a plurality of images of the object, an illumination system housing a plurality of illuminators, an illumination control system configured to control illumination provided by the plurality of illuminators, and a focus control system configured to control a focus of the camera.

Digital presenter for displaying image captured by camera with illumination system

A surveillance system including a tracking module, a controller and a detection module is provided. The tracking module processes at least one first image frame that is acquired via a first camera to track an object in the at least one first image frame, and generate location information of the object being tracked. The controller generates a control signal based on the location information and transmits the control signal to a second camera to control the movement of the second camera. The detection module processes at least one second image frame that is acquired via the second camera to detect a feature part of the object being tracked.

Surveillance system

Techniques for reconstructing an image of an object are provided. In some embodiments, an image reconstructing system includes one or more cameras, one or more light sources and an image processor. The cameras are configured to capture images of an object and the light sources are configured to irradiate the object. The image processor is configured to process the images to generate a first representation of the object and a second representation of the object, and to generate a reconstructed image of the object based on the first representation and the second representation.

Image reconstruction

An image retrieval system includes an image entry unit configured to input an image. A descriptor determining unit receives the image and transforms the image into an intermediate image to generate a descriptor of the image, for example, utilizing the distance transform (DT) application. An image comparing unit compares the image with a plurality of candidate images by comparing the descriptor of the image with descriptors of the plurality of candidate images. Finally, a retrieving unit retrieves one or more candidate images similar to the input image based on the comparison of their descriptors.

Matching images with shape descriptors

A fingerprint matching system includes a first minutiae obtaining unit and a second minutiae obtaining unit adapted to obtain minutiae information of first and second fingerprints. On the minutiae of the first fingerprint, a deformable mesh is constructed by a mesh construction unit, and a mesh transformation unit is used to transform a state of the deformable mesh, thereby obtaining a distortion-compensated first fingerprint. Based on the distortion-compensated first fingerprint, a matching determination unit determines whether the first fingerprint matches the second fingerprint or not.

Systems and methods for fingerprint matching based on transforming the deformable mesh

Techniques for segmenting images are disclosed.

Image segmentation

Techniques for segmenting an image of an object are provided. In some embodiments, an image segmentation apparatus includes an image input unit and an image processing unit. The image input unit is configured to receive as input a video image having a first image frame and a second image frame that is consecutive to the first image frame. The image processing unit is configured to segment the second image frame based at least in part on information on the first image frame.

Video image segmentation

Techniques for matching a 3D object are provided. In some embodiments, a 3D object retrieval apparatus includes an input unit configured to receive as input at least one sample view of a 3D query object to be inputted, and an object descriptor determining unit configured to generate at least one object representative image of the 3D query object from the at least one sample view and to determine a query object descriptor of the 3D query object from the at least one object representative image.

3D object descriptors

An apparatus for evaluating image registration is provided. The apparatus includes a graph generation unit configured to generate a graph based on a plurality of registered images and a plurality of transformation rules therebetween, the graph comprising a plurality of nodes respectively corresponding to the registered images and a plurality of edges respectively corresponding to at least part of the transformation rules; a general transition unit configured to identify one or more loops for at least one of the nodes within the graph and to transform the registered image corresponding to the at least one node along the one or more identified loops to provide one or more transformed images; and a general transition error unit configured to produce a similarity measure between the registered image corresponding to the at least one node and at least one of the transformed images, wherein the graphic generation unit is further configured to calculate an inverse consistency metric for at least one pair of the registered images and a pair of transformations rules between the at least one registered image pair, and to establish as the edges the pair of transformation rules with an inverse consistency metric within a prescribed range.

Growing community of inventors

Seongnam-si, South Korea

Il Dong Yun