Abstract: A method and system for extracting a visual descriptor using a feature selection are provided. The system includes an image input unit configured to receive an image, a candidate feature point group detecting unit configured to detect a point having a local maximum or minimum of local region filtering in scale-space images as being included in a candidate feature point group, a feature point selecting unit configured to calculate an importance for each candidate feature point, depending on its characteristics, select the candidate feature point as a feature point when its importance is greater than the predetermined threshold value, a dominant orientation calculating unit configured to calculate a dominant orientation of the selected feature point and a visual descriptor extracting unit configured to extract a patch for each feature point, according to its scale, location and dominant orientation, and extract a visual descriptor from the patch.

Abstract: Disclosed herein is technology for providing a medical image knowledge service. An apparatus for providing a medical image knowledge service according to an embodiment includes an image processing device for acquiring image information of at least a partial region of an analysis target based on a distribution of reactive oxygen species or magnetic particles, and generating final image information of an overall region of the analysis target based on results of analysis of the acquired image information. A medical knowledge service device constructs a medical knowledge model based on the acquired final image information, and provides a medical image knowledge service to a user using the constructed medical knowledge model.

Abstract: Disclosed are an apparatus for controlling a service of a network robot system based on remote procedure calls and a method thereof. The apparatus for controlling services of a network robot system according to an exemplary embodiment of the present invention includes: a terminal agent calling an asynchronous procedure of the robot services to acquire asynchronous operation objects and performing asynchronous operations on the asynchronous operation objects according to previously established scheduling policies, when receiving an execution of robot services from a service server through a network; and a plurality of drivers executing the robot services according to the asynchronous operations of the terminal agent. By this configuration, the exemplary embodiment of the present invention can avoid resource collision due to resource approach at a plurality of robot services, improve the simultaneity of the robot services, and implement operation applications for high performance control.

Abstract: The present disclosure relates to a system and a method for finger printing for comics. A system for searching comics according to the present disclosure includes: a fingerprint database storing fingerprints extracted from comics, a comics fingerprint extraction unit extracting fingerprints configured of at least one of box frames, cuts, and speech bubbles included in input comic images, a fingerprint based candidate group search unit searching candidate groups among comics stored in the fingerprint database using the extracted fingerprints, and a similarity measuring unit measuring similarity between the searched candidate groups and the comic images corresponding to the extracted fingerprints.

Abstract: An apparatus and method for processing an image based on feature points is provided, more specifically, provides a technology used in extracting feature points with high importance after determination of importance, searching images, and the like. Therefore, matching images can be effectively performed, and efficiency of time and memory can be increased.

Abstract: The present invention relates generally to a method and apparatus for searching for recommended music using the emotional information of music and, more particularly, to a method and apparatus that enable recommended music to be searched for using mixed emotions by extracting emotional values including a valence value and an arousal value from an input search condition when a predetermined search condition is input by a user, extracting an emotion rank combination corresponding to the extracted emotional value information using an emotion model that includes mixed emotions corresponding to the emotional values, searching a music emotion DB for music information corresponding to the emotion rank combination, and outputting a recommended music list based on the results of the search, thus improving the user's satisfaction with the results of the search.

Abstract: Disclosed are a method and a device for loading a service application of a robot based on a ubiquitous robotic companion (URC) environment. The method for loading a service application of a robot includes: generating a service code for a service which is implemented by the robot from at least one descriptor; and generating at least one service object based on the generated service code and loading the at least one generated service object on the robot.

Abstract: A forensic mark insertion apparatus includes: an original content segment storage unit for storing multiple original contents; and a service control unit for, in response to a request for a content from a user, retrieving an original content corresponding to the request for the content from the original content segment storage unit, separating the retrieved original content into plurality of content segments, selectively inserting a forensic mark into some of the content segments, and assembling the content segments to produce an forensic-mark inserted content to be provided to the user.

Abstract: Provided are an apparatus and method for forensic marking of digital content. The apparatus includes a forensic marker configured to generate first content by inserting a first binary forensic mark in original content and second content by inserting a second binary forensic mark in the original content, and when a content service request is generated, combine the first content and the second content on the basis of information about a user who has requested the content service and thereby generate third content in which a forensic mark corresponding to the user information is inserted, a content database configured to store the first and second content, and a transceiver configured to transmit the third content.

Abstract: Provided is a technique that enables a robot to be remotely controlled (by a server) and enables a robot component to access an external component (a component of a server) in order for cooperation of heterogeneous robots operating on the basis of different component models. A component integration apparatus for collaboration of a heterogeneous robot according to an embodiment of the present invention comprises: a standard interface unit that provides a common standard interface for controlling components that control the individual functions of the robot; an adapter component that transmits commands to enable external components to call the components through the standard interface unit; and a proxy component that transmits commands to enable the components to call the external components through the standard interface unit.

Abstract: Disclosed herein is an apparatus and method for measuring quality of audio. The apparatus includes a distorted signal generation unit, an extraction unit, a distortion level measurement unit, a distortion function generation unit, and a search and measurement unit. The distorted signal generation unit generates a plurality of distorted signals with respect to audio in compliance. The extraction unit extracts a fingerprint and AV information corresponding to the audio and fingerprints and AV information corresponding to the plurality of distorted signals. The distortion level measurement unit measures fingerprint distance differences, and arousal and valence (AV) distance differences. The distortion function generation unit generates a fingerprint distortion function and an AV distortion function.

Abstract: An apparatus for extracting features from a video includes a frame rate converter for performing a frame rate conversion on the video to a preset frame rate, a gray scale converter for performing a grey scale conversion on the frame rate-converted video, a frame size normalizer for performing a frame size normalization on the gray scale-converted video to a preset image size, and a feature extractor for partitioning the normalized video into image blocks of a predetermined size, and extracting features from the image blocks on the basis of luminance values of the image blocks. A video identification system employs the feature extracting apparatus to identify an original video and an object video.

Abstract: Disclosed are a method and an apparatus for extracting a fingerprint of a publication. And disclosed are a system and a method for identifying a publication using a fingerprint. The system for identifying the publication using the fingerprint includes: a fingerprint extraction unit for extracting fingerprints for collected query publications to identify the copyrights infringement; a fingerprint query unit for querying fingerprints of original publications corresponding from the fingerprint extraction unit; a DBMS for storing the fingerprints extracted from the original publications and additional information from the original publications, and providing a search result candidate group which is composed of fingerprints of at least one of the original publications corresponding to the queries of the fingerprint query unit; and a candidate group verification unit for determining copyright infringement for the query publications by verifying the search result candidate group provided from the DBMS.

Abstract: Disclosed are a mobile apparatus and a method for controlling the same. More particularly, disclosed are an autonomous mobile apparatus and a method for controlling the same. The method for controlling an autonomous mobile apparatus disclosed in the specification includes: recognizing a direction of a call signal based on the call signal; receiving and analyzing video information regarding the direction; estimating a position of a signal source of the call signal using the sound source localization and the detected person's shape; generating a moving command to the position of the signal source; and recognizing the subject of the signal source after movement according to the moving command.

Abstract: Disclosed are a robot and a method of controlling the robot, and more particularly are an autonomous robot and a method of controlling the autonomous robot. The autonomous robot includes a sensor for detecting a change of a situation; an actuator; and a controller for controlling the actuator based on information input through the sensor, wherein the controller controls the actuator in accordance with mode information including an act abstraction layer which defines a unit act by combining functions of the sensor and the actuator.

Abstract: A music search apparatus using an emotion model includes a music database (DB) for storing sound source data about a plurality of pieces of music and Arousal-Valence (AV) coefficients of the respective pieces of music. An emotion model generation unit classifies different emotion types into a plurality of groups, and generates an emotion classification model from using respective probability distributions of the plurality of groups for an AV coefficient plane. A music search unit identifies an emotion type from using information entered by a user when a music search request is received, detects an AV coefficient range for designating an AV coefficient corresponding to the identified emotion type from using the emotion classification model, and searches the music DB for music corresponding to the AV coefficient range.

Abstract: A method for managing digital videos includes extracting a feature of an input digital video, searching for candidate features having similarity to the extracted feature, and comparing the extracted feature with each of the candidate features to select at least one of the candidate features similar to the extracted feature and provide information on a digital video corresponding to the selected candidate feature.

Abstract: Disclosed are a method and an apparatus for providing contents about conversation, which collect voice information from conversation between a user and another person, search contents on the basis of the collected voice information, and provide contents about the conversation between the user and the person. The method of providing contents about conversation includes: a voice information collecting step of collecting voice information from conversation between a user and another person; a keyword creating control step of creating search keywords by using the collected voice information; and a contents providing control step of searching contents by using the created search keywords, and providing the searched contents.

Abstract: The present invention relates generally to a method and apparatus for searching for recommended music using the emotional information of music and, more particularly, to a method and apparatus that enable recommended music to be searched for using mixed emotions by extracting emotional values including a valence value and an arousal value from an input search condition when a predetermined search condition is input by a user, extracting an emotion rank combination corresponding to the extracted emotional value information using an emotion model that includes mixed emotions corresponding to the emotional values, searching a music emotion DB for music information corresponding to the emotion rank combination, and outputting a recommended music list based on the results of the search, thus improving the user's satisfaction with the results of the search.

Abstract: Disclosed are a forensic marking method and a forensic marking system capable of inserting in real-time a forensic mark for user information in digital contents provided online.