Korea Advanced Institute of Science and Technology

Samsung Electronics Co., Ltd.

Electronics and Telecommunications Research Institute

Korean Broadcasting System

Research and Industrial Corporation Group

MunChurl Kim

Jae Seok Choi

Chieteuk Ahn

Youngsu Moon

Hyunseung Lee

Cheon An Lee

Jin Suk Kwak

Yongwoo Kim

Jong Nam Kim

Kyeongsoo Kim

Jae Gark Choi

Myoung Ho Lee

EunHui Kim

Shinjee Pyo

Beom Goo Lee

An image processing apparatus obtains a first output image by applying an image to a first training network model, obtains a second output image by applying the image to a second training network model, and obtains a reconstructed image based on the first output image and the second output image. The first training network model is a model that uses a fixed parameter obtained through training of a plurality of sample images, the second training network model is trained to minimize a difference between a target image corresponding to the image and the reconstructed image.

Image processing apparatus and image processing method thereof

An image conversion method includes: dividing a low-resolution image to generate a plurality of low-resolution image patches having N (N being a natural number of 2 or greater) number of pixels; classifying the low-resolution image patches into a plurality of image categories; converting the low-resolution image patches by using a conversion kernel for each image patch corresponding to its image category among prestored conversion matrices, to generate high-resolution image patches having L (L being a natural number) number of pixels, which is less than the N number of pixels; and arranging the high-resolution image patches to generate a high-resolution image. According to the image conversion method, an operation amount can be reduced compared with a conventional technique, and thus the image conversion method can be implemented in hardware having low complexity. A high quality and high-resolution image can be generated regardless of characteristic information of an image signal.

Method of converting low-resolution image to high-resolution image and image conversion device performing method

Disclosure relates to an apparatus, system, and method for related recommendation of TV program contents and web contents that enable plentiful information acquisition and effective TV watching by discovering and recommending Internet web contents having a high association with the TV program contents when a TV is watched using a TV terminal connected to the Internet, and to a computer-readable recording medium having a program recorded thereon for executing the method. The apparatus includes: an user profile unit that produces and updates an user profile of a smart TV; a first information collection unit that collects first information that is TV program contents metadata from a smart TV network; a second information collection unit that collects second information that is web contents information from a web; and an integrated content database that stores third integrated information structured with correlation discovered between the first information and the second information.

Apparatus, system, method and computer readable recording medium storing the program for related recommendation of TV program contents and web contents

A multimedia contents service system transforms original contents based on selected user preferences chosen by a user or automatic preferences generated from accumulated statistics on user's contents consumption. The system transmits the transformed contents to the user and provides services which perform rendering or storing according to user preferences. Therefore, the system provides contents transformed according to user's interests to thereby increase user's convenience (universal multimedia access) and satisfy a variety of user's demands.

System, method and storage medium for providing a multimedia contents service based on user's preferences

A video object segmentation method applicable to a video system is presented. The method includes primarily segmenting objects existing in a frame of a video sequence manually or semi-manually. The objects within a video sequence including the primarily segmented object are automatically segmented. The method also determines whether any scene change is made between consecutive frames or any new object other than the primarily segmented object appears within the video sequence being automatically segmented, when repeatedly performing automatically segmenting the objects within the video sequence for consecutive frames. And, the method repeatedly performs primarily segmenting objects existing in a frame of a video sequence manually or semi-manually if it is determined that any scene change is made between consecutive frames or any new object other than the primarily segmented object appears within the video sequence being automatically segmented.

Method for objects segmentation in video sequences by object tracking and user assistance

Growing community of inventors

Daejeon, South Korea

MunChurl Kim