-
公开(公告)号：KR1020030050617A
公开(公告)日：2003-06-25
申请号：KR1020010081102
申请日：2001-12-19
Applicant: 한국전자통신연구원
IPC: G06T7/00
Abstract: PURPOSE: A system for extracting a face color area using edge and color information, and a method thereof are provided to improve the accuracy of face authentication by preventing a face area from merging with a background area. CONSTITUTION: A color area dividing unit(10) detects edge information from an input color image and divides areas from an entire image by the edge information. An isolated area forming unit(11) makes a background area and a face area binary for forming each isolated area. A skin color area selecting unit(12) extracts the isolated area adjacent to a center position of an image in the isolated areas for selecting an area satisfying conditions of mean gray level, size information, and color distribution as a representative face candidate area. An image merging unit(13) extracts the areas satisfying the conditions of the color and position information from the adjacent isolated areas based on the mean color distribution and position information of the selected representative face candidate area for merging images, so that the image merging unit extracts a face color area.
Abstract translation: 目的：提供使用边缘和颜色信息提取面部颜色区域的系统及其方法，其方法是通过防止面部区域与背景区域合并来提高面部认证的准确性。 构成：颜色区域划分单元（10）检测来自输入彩色图像的边缘信息，并且将来自整个图像的区域除以边缘信息。 隔离区域形成单元（11）使得形成每个隔离区域的背景区域和面部区域成为二进制形式。 皮肤颜色区域选择单元（12）提取与分离区域中的图像的中心位置相邻的隔离区域，用于选择满足平均灰度级别，大小信息和颜色分布条件的区域作为代表面部候选区域。 图像融合单元（13）基于用于合并图像的所选择的代表面部候选区域的平均颜色分布和位置信息，提取满足来自相邻隔离区域的颜色和位置信息的条件的区域，使得图像合成单元 提取面部颜色区域。
-
公开(公告)号：KR100353842B1
公开(公告)日：2002-09-26
申请号：KR1019990061217
申请日：1999-12-23
Applicant: 한국전자통신연구원
IPC: G06T1/00
Abstract: 본발명은쿼시(Quasi) 3차마르코프랜덤필드(MRF)를이용한영역분할영상후처리방법및 상기방법을실현시키기위한프로그램을기록한컴퓨터로읽을수 있는기록매체에관한것으로서, 영상처리시스템에서쿼시(Quasi) 3차마르코프랜덤필드(MRF)의통계학적접근을통해영역분할(Segmentation)의오분류(Misclassification) 에러를줄이기위한영역분할영상후처리방법및 상기방법을실현시키기위한프로그램을기록한컴퓨터로읽을수 있는기록매체를제공하기위하여, 영상처리시스템에서영역분할된영상의후처리방법에있어서, 영역분할된영상에서보다많은주변픽셀들의영역레벨정보를얻기위하여, 쿼시(Quasi) 3차마르코프랜덤필드(MRF)를사용하여작은윈도우로구성된이웃시스템을정의하는제 1 단계; 상기쿼시 3차마르코프랜덤필드(MRF)에의해정의된상기이웃시스템의중심픽셀과주변픽셀들과의관계를각기다른영역레벨의조건하에서각각의조건확률함수로표현하고, 그중 가장높은확률을제공하는영역레벨을해당윈도우의중심픽셀의영역레벨로보정하는제 2 단계; 및각 윈도우를서로중첩시켜에러를포함하고있는영역분할된전체영상을보정하는제 3 단계를포함하되, 상기이웃시스템은 2차 MRF에해당하는 8개의픽셀과 3차 MRF 이웃시스템에해당하는 5×5 윈도우의외곽픽셀 16개중 중심픽셀로부터수평, 수직그리고 2개의대각선방향에위치하여있는 8개의픽셀로구성되며, 영상분할및 분류처리등에이용됨.
-
公开(公告)号：KR100349673B1
公开(公告)日：2002-08-22
申请号：KR1019990061254
申请日：1999-12-23
Applicant: 한국전자통신연구원
IPC: G06F17/30
Abstract: 본발명은고차원영상특징량의대표값을이용한영상검색방법에관한것으로, 고차원의특징량벡터로부터그 특징량을대표할수 있는대표값을추출하여, 검색대상이되는데이터베이스의특징량범위를한정함으로써, 효율적인검색속도및 검색효율을제공할수 있는고차원영상특징량의대표값을이용한영상검색방법을제공하기위하여, 특징추출부가질의영상특징량을추출하는제 1 단계; 검색범위한정부가상기질의영상특징량을수신하여적어도하나이상의대표값을추출하는제 2 단계; 상기검색범위한정부가상기질의영상과유사도계산을위해상기대표값으로부터소정범위내의대표값을적어도하나이상의후보집합을선정하는제 3 단계; 상기검색범위한정부가상기적어도하나이상의후보집합을비트배열의형태로구성하는제 4 단계; 상기검색범위한정부가복수의비트배열로구성된적어도하나이상의후보집합에비트와이즈앤드연산을수행하여, 최종검색후보집합을구성하는제 5 단계; 및유사도평가부가상기질의영상특징량과최조검색후보집합의특징량의유사도를평가하여질의영상에대응되는영상을검색하는제 6 단계를포함하며, 영상검색시스템등에이용됨.
-
公开(公告)号：KR1020000039197A
公开(公告)日：2000-07-05
申请号：KR1019980054452
申请日：1998-12-11
Applicant: 한국전자통신연구원
IPC: H04N7/087
CPC classification number: H04N7/0255 , G06K9/3258
Abstract: PURPOSE: An apparatus for separating text region using geographic text characteristics information and a method therefor are provided to detect characteristic points of texts and collect the detected points. CONSTITUTION: An apparatus for separating text region using geographic text characteristics information includes a geographic text characteristics separator/candidate region separator(110) and a candidate region prover(120). The geographic text characteristics separator/candidate region separator(110) detects the geographic characteristics of text of an input image from outside and defines the candidate region. The candidate region prover(120) increases the size of the candidate region in the geographic text characteristics separator/candidate region separator(110) proves whether the region is a real text region.
Abstract translation: 目的：提供一种使用地理文本特征信息分离文本区域的方法及其方法，用于检测文本的特征点并收集检测到的点。 构成：使用地理文本特征信息分离文本区域的装置包括地理文本特征分隔符/候选区域分隔符（110）和候选区域证明器（120）。 地理文本特征分离器/候选区域分离器（110）从外部检测输入图像的文本的地理特征并定义候选区域。 候选区域识别器（120）增加地理文本特征分离器/候选区域分离器（110）中的候选区域的大小，证明该区域是否是真实文本区域。
-
公开(公告)号：KR100447268B1
公开(公告)日：2004-09-07
申请号：KR1020010080719
申请日：2001-12-18
Applicant: 한국전자통신연구원
IPC: G06T7/00
Abstract: PURPOSE: A method for detecting eyes from a face image by an optimum binary threshold search is provided to increase the adaptability of an input gray level face image to an illuminating state and maximize the performance of eye detection. CONSTITUTION: A gray level face image is inputted to a computer(S100). A threshold is generated according to a threshold search direction for making the input gray level face image binary(S200). An eye pair is detected from the black and white face image(S300). If eye pair information is output, the eye pair is finally output as eyes detected from the input gray level face image(S500). If the eye pair detection fails, the threshold search direction is decided to execute threshold generation and binary process again(S400).
Abstract translation: 目的：提供一种通过最佳二值阈值搜索从面部图像中检测眼睛的方法，以增加输入灰度级面部图像对照明状态的适应性并使眼睛检测性能最大化。 构成：将灰阶面部图像输入到计算机（S100）。 根据用于使输入灰度级面部图像二值化的阈值搜索方向生成阈值（S200）。 从黑白人脸图像中检测眼睛对（S300）。 如果输出眼睛对信息，则眼睛对最终被输出为从输入灰度级面部图像检测到的眼睛（S500）。 如果眼睛对检测失败，则阈值搜索方向被决定再次执行阈值生成和二进制处理（S400）。
-
Patent Agency Ranking
公开(公告)号：KR1020020048504A
公开(公告)日：2002-06-24
申请号：KR1020000077641
申请日：2000-12-18
Applicant: 한국전자통신연구원
IPC: H04N7/18
Abstract: PURPOSE: A method of tracking a moving object using three basic points is provided to track a moving object in real time using three basic points and sixteen characteristic vectors extracted with respect to the basic points. CONSTITUTION: The positions of three basic points are determined with respect to an initial image inputted from a camera(S120). Sixteen characteristic values are detected and stored using the determined three basic points(S130). A candidate region for a new image inputted after the initial image is determined(S220). Sixteen characteristic values are detected from the determined candidate region(S230), and the positions of three points corresponding to the three basic points are decided through the detected sixteen characteristic values and a similarity measurement value(S240). The three corresponding points and basic points are transformed through Affine transform to track a moving object(S250).
Abstract translation: 目的：提供使用三个基本点跟踪移动物体的方法，以使用相对于基本点提取的三个基本点和十六个特征向量实时跟踪移动物体。 构成：关于从照相机输入的初始图像确定三个基本点的位置（S120）。 使用确定的三个基本点来检测和存储16个特征值（S130）。 确定在初始图像之后输入的新图像的候选区域（S220）。 从确定的候选区域检测出16个特征值（S230），通过检测到的16个特征值和相似度测定值来决定与三个基本点对应的3个点的位置（S240）。 通过仿射变换对三个对应点和基点进行变换，跟踪移动物体（S250）。
-
公开(公告)号：KR100315427B1
公开(公告)日：2001-11-28
申请号：KR1019990061896
申请日：1999-12-24
Applicant: 한국전자통신연구원
Abstract: 본발명은다단계지형학적특징및 점-선-면확장법에의한자막영역추출장치및 그방법과기록매체에관한것으로, 영상처리시스템에서내용기반영상처리를위해정지영상, 동영상등과같은영상에서문자의다단계지형학적특징및 점-선-면확장법을이용하여자막영역을추출하기위한자막영역추출장치및 그방법과기록매체를제공하기위하여, 입력영상으로부터일정한간격의라인샘플링에의해다단계문자의지형학적특징점을추출하는제 1 단계; 추출된특징점을선 영역, 면영역(문자후보영역)으로순차적확장하는제 2 단계; 추출된면 영역(문자후보영역)중에서중복된영역을통합하는제 3 단계; 및합병된면 영역(문자후보영역)에대한조건을조사하여자막의후보영역을추출하고, 추출된자막의후보영역을검증하여최종자막영역을추출하는제 4 단계를포함하며, 멀티미디어영상처리분야등에이용됨.
-
公开(公告)号：KR100305590B1
公开(公告)日：2001-09-29
申请号：KR1019980052945
申请日：1998-12-03
Applicant: 한국전자통신연구원
Abstract: 본 발명은 방향 윤곽선 지도를 이용한 영상 검색 방법에 관한 것으로, 디지털화되어 있는 정지영상 및 동영상을 읽어들이는 영상 입력 과정과, 입력된 영상의 수평 및 수직 방향 윤곽선을 구하고, 이를 이용하여 방향 성분을 포함하는 윤곽선 정보인 방향 윤곽선 지도를 작성하는 특징 추출 과정과, 작성된 방향 윤곽선 지도를 저장하기 위한 저장 과정과, 방향 윤곽선 지도간의 차분을 구하여 유사성을 평가한 후 원하는 데이터를 검색하는 검색 과정을 통하여 이루어지며, 영상 내에 포함된 물체에 대한 근사적인 표현이 포함되므로써, 보다 의도에 가까운 영상 검색이 가능하여 영상 데이터베이스 검색의 질을 향상시킬 수 있는 방향 윤곽선 지도를 이용한 영상 검색 방법이 개시된다.
-
公开(公告)号：KR1020010063801A
公开(公告)日：2001-07-09
申请号：KR1019990061895
申请日：1999-12-24
Applicant: 한국전자통신연구원
Abstract: PURPOSE: An original image restoration device of a captioned region using block matching and a restoring method thereof are provided to reuse the captioned image and make it possible to insert other caption by determining restoration direction and automatically restoring the captioned region to the original image. CONSTITUTION: A scene change data extractor(11) extracts a video scene change data from an external video data input. A caption data extractor(12) extracts a caption data to be restored from the video data. A restoration direction determiner(13) determines the restoration direction using the extracted video scene change data and the first and the last frame of the caption. An original image restorer(14) restores the original image through block matching the extracted caption data for each frame.
Abstract translation: 目的：提供使用块匹配的字幕区域的原始图像恢复装置及其恢复方法以重新使用字幕图像，并且可以通过确定恢复方向并自动地将字幕区域恢复到原始图像来插入其他标题。 构成：场景改变数据提取器（11）从外部视频数据输入中提取视频场景改变数据。 字幕数据提取器（12）从视频数据中提取要恢复的字幕数据。 恢复方向确定器（13）使用所提取的视频场景改变数据和标题的第一和最后一帧来确定恢复方向。 原始图像恢复器（14）通过块匹配提取的每个帧的字幕数据恢复原始图像。
-
公开(公告)号：KR1020000038083A
公开(公告)日：2000-07-05
申请号：KR1019980052945
申请日：1998-12-03
Applicant: 한국전자통신연구원
CPC classification number: G06F17/30241 , G06T2207/10
Abstract: PURPOSE: A method for searching an image using a direction outline map is provided to improve speed and efficiency of searching. CONSTITUTION: A method for searching an image using a direction outline map includes an image inputting procedure, a feature extracting procedure, a storing procedure, and a searching procedure. The image inputting procedure is to read a digitalized still image and moving image. The feature extracting procedure is to analyze the inputted image content to draw a direction outline map. The storing procedure is to store the drawn direction outline map. The searching procedure is to search required data based on the resemblance of the direction outline map to search a want data.
Abstract translation: 目的：提供一种使用方向轮廓图搜索图像的方法，以提高搜索的速度和效率。 构成：使用方向轮廓图搜索图像的方法包括图像输入过程，特征提取过程，存储过程和搜索过程。 图像输入过程是读取数字化静止图像和运动图像。 特征提取程序是分析输入的图像内容以绘制方向轮廓图。 存储过程是存储绘制的方向轮廓图。 搜索过程是根据方向轮廓图的相似性来搜索所需的数据以搜索想要的数据。
-
-
-
-
-
-
-
-
-
Search Results
34
records
(took 0.026 seconds)
