Abstract:
PURPOSE: A system and a method for a multimedia contents service based on a user preference and a recording medium thereof are provided to transcode and offer the multimedia contents including audio/video/text by reflecting the interest of each contents and the preference for a contents rendering method of a user. CONSTITUTION: A preference inputting block(111) generates the selective user preference and registers it as the metadata. A metadata generating block(113) generates the contents request data including the user preference information by responding to a service request of the contents. A metadata transmitting block(115) transmits the contents request data including the user preference information to a remote contents server(130). A metadata parsing block(133) analyzes the user preference by parsing the contents request data including the user preference information. A contents transcoding block(135) transcodes the requested contents based on the analyzed user preference. A contents transmitting block(137) transmits the transcoded contents to a user terminal. A contents providing block(140) generates or stores the transcoded contents.
Abstract:
본 발명은 저니키(Zernike)/선형 판별 분석(LDA)을 이용한 얼굴 인식 방법 및 그 방법을 기록한 기록매체에 관한 것이다. 본 발명은 하나 이상의 등록 대상 얼굴 영상을 입력받아 각각의 등록 대상 얼굴 영상에 상응하는 등록 대상 얼굴 영상 특징값을 추출하여 데이터베이스에 저장한 후, 인식 대상 얼굴 영상을 입력받아 상응하는 인식 대상 얼굴 영상 특징값을 추출하고, 데이터베이스에 이미 저장된 하나 이상의 등록 대상 얼굴 영상 특징값 중 추출된 인식 대상 얼굴 영상 특징값과 최소의 차이값을 가지는 등록 대상 얼굴 영상 특징값을 선택하여 각각 상응하는 영상인 것으로 인식하는 과정을 포함하여 구성되며, 이때 얼굴 영상 특징값은 저니키 모멘트(Zernike moment) 및 선형 판별 분석(LDA)을 이용하여 추출되는 것을 특징으로 한다. 따라서 본 발명에 따른 얼굴 인식 방법 및 그 방법을 기록한 기록매체는 방송 동영상에서 자주 발생하는 얼굴 회전에 강인하게 반응할 수 있는 효과를 가진다. 얼굴 인식, 선형 판별 분석, 저니키 모멘트, Zernike Moment, LDA(Linear Discriminant Analysis)
Abstract:
PURPOSE: A multimedia service system, a method, and a recording medium thereof based on a user characteristic and environment are provided to supply contents including an intention of an author by considering characteristics of a user, terminal, network resources, environment and so on in a general multimedia access and consumption environment. CONSTITUTION: A contents consumption monitoring block(202) extracts a contents consumption history by monitoring transformation(adaptation) contents consumption form received from a user interface and presentation block. The extracted contents consumption history is accumulated and stored in a contents consumption history storing block(204) with a previous contents history. A user characteristic information calculation block(206) calculates a predetermined user characteristic information such as a genre, a player, a channel, a contents consumption price, a subject, a principal contents consumption time, a contents consumption method, a band width of a network connected to a user terminal, the number of network users, etc. based on an accumulated statistics value with respect to the contents consumption of a user. The calculated user characteristic information is stored in a memory as meta data. Thus, the user receives transformation(adaptation) contents using automatically calculated user characteristic information or user characteristic information selected and inputted by the user.