公开(公告)号：KR1020120109943A

公开(公告)日：2012-10-09

申请号：KR1020110027862

申请日：2011-03-28

Applicant: 가톨릭대학교 산학협력단

Inventor： 강행봉

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/28 ,  G06F17/27

Abstract: PURPOSE: An emotion classifying method for emotion analysis is provided to extract an emotion feature of a word which consists of a sentence and to classify emotion embedded in the sentence by using an emotion classifier. CONSTITUTION: A word is classified according to each part of speech by using a morpheme analyzer(S100). An emotion feature about the word is extracted by using an emotion dictionary by part of speech(S200). The emotion of the sentence is classified through a -trained emotion sorter by using the extracted emotion feature(S300). [Reference numerals] (S100) A word is classified according to each part of speech by using a morpheme analyzer; (S200) An emotion feature is extracted; (S300) An emotion of a sentence is classified

Abstract translation: 目的：提供情感分析的情感分类方法，提取由句子组成的单词的情感特征，并通过使用情感分类器对嵌入在句子中的情感进行分类。 构成：通过使用语素分析器（S100），根据每个语音部分对字进行分类。 通过语音部分使用情感词典提取关于该单词的情感特征（S200）。 通过使用提取的情感特征通过训练的情感分类器对该句子的情感进行分类（S300）。 （附图标记）（S100）通过使用语素分析器，根据每个语音部分对字进行分类; （S200）提取情绪特征; （S300）对句子的情感进行分类

公开(公告)号：KR1020110000910A

公开(公告)日：2011-01-06

申请号：KR1020090058235

申请日：2009-06-29

Applicant: 가톨릭대학교 산학협력단 ,  (주)키즈엔터테인먼트 ,  재단법인 경기콘텐츠진흥원

Inventor： 강행봉

IPC: H04N9/64

CPC classification number: G06T7/90 ,  G06K9/4652 ,  G06T5/40 ,  G09G2340/06 ,  H04N9/64 ,  H04N9/77 ,  H04N19/94

Abstract: PURPOSE: A color conversion method of an image based on relation between the chromatics and the feeling maximizing the interest of a use is provided to implement the color conversion suitable for a user by reflecting the preference of the user to a color conversion algorithm execution. CONSTITUTION: A plurality of color templates is set up(S10). The color template defines color distribution corresponding to the feeling of person. A color converting algorithm is set up for color conversion of an image(S11). The preference of the user according to each feeling is analyzed through the color conversion algorithm. The weighted value is calculated(S12). The feeling information toward the feeling of user is inputted(S13).

Abstract translation: 目的：提供基于色彩与使用感兴趣的感觉之间的关系的图像的颜色转换方法，以通过将用户的偏好反映到颜色转换算法执行来实现适合于用户的颜色转换。 构成：设置多个颜色模板（S10）。 颜色模板根据人的感觉定义颜色分布。 为图像的颜色转换设置颜色转换算法（S11）。 通过颜色转换算法分析用户根据每种感觉的偏好。 计算加权值（S12）。 输入针对用户感觉的感觉信息（S13）。

公开(公告)号：KR1020100001409A

公开(公告)日：2010-01-06

申请号：KR1020080061307

申请日：2008-06-27

Applicant: 가톨릭대학교 산학협력단 ,  (주)키즈엔터테인먼트 ,  재단법인 경기콘텐츠진흥원

Inventor： 강행봉

IPC: G06T7/40 ,  G06T7/00

CPC classification number: G06K9/00221 ,  G06K9/00302 ,  G06T3/0093 ,  G06T7/40

Abstract: PURPOSE: A method for recognizing the facial expression of a user and a control method of the robot for visual contents impression using the same are provided to operate the image contents according to the recognized face pose by recognizing face pose and expression of a user. CONSTITUTION: A face range is extracted from an inputted image. A pose of the extracted face range is presumed(S101). In case the pose examines the front, a face shape and a texture are extracted(S103). The face shape and the texture are generated in an average form(S104). The average face form and the texture are processed in retinex(S105). A first face parameter about each facial expression learns based on the average face form and the texture of the retinex about each facial expression(S106).

Abstract translation: 目的：提供一种用于识别用户的面部表情的方法和使用其的用于视觉内容印象的机器人的控制方法，以通过识别用户的脸部姿势和表情来根据识别的脸部姿势来操作图像内容。 构成：从输入图像中提取面部范围。 推定提取的脸部范围的姿势（S101）。 如果姿势检查前方，则提取脸部形状和纹理（S103）。 以平均形式生成面部形状和纹理（S104）。 在retinex中处理平均脸部形状和纹理（S105）。 关于每个面部表情的第一面部参数基于每个面部表情的平均脸部形式和视网膜的纹理来学习（S106）。