-
公开(公告)号：KR100556832B1
公开(公告)日：2006-03-10
申请号：KR1020037005476
申请日：2001-10-18
Applicant: 한국전자통신연구원
IPC: G06F17/30 , H04N21/232 , G06T5/40 , G06T1/00
CPC classification number: G06F17/30259 , H04N19/98
Abstract: 본 발명은, 다수의 영상을 대표하는 영상정보를 갖는 데이터 베이스 구축 방법에 있어서, 대상 영상에 대하여, 각각 5개의 정규화 에지 히스토그램 빈을 포함하고 부영상에 포함된 4개의 방향성 에지와 하나의 비방향성 에지로 이루어진 5개의 기준 에지들의 공간분포를 나타내는 L (L은 양의 정수)개의 에지 히스토그램을 생성하기 위해 Lx5 개의 정규화 에지 히스토그램 빈을 계산하는 제 a단계; 상기 대상 영상에 대하여 Lx5 개의 양자화 색인값을 생성하기 위해 상기 Lx5 개의 정규화 에지 히스토그램 빈을 비선형적으로 양자화하는 제 b단계; 상기 Lx5 개의 양자화 색인값을 데이터베이스에 저장하는 제 c단계; 및 상기 영상정보를 갖는 데이터베이스를 구성하기위해 저장된 모든 영상들이 처리될 때까지 상기 제 a 내지 c단계를 반복하는 제 d단계로 이루어 지는 것을 특징으로 하는 다수의 영상을 대표하는 영상정보를 갖는 데이터 베이스 구축 방법.
영상검색, 비선형, 양자화, 유사도, 매칭, 데이터베이서, 대상 영상-
公开(公告)号：KR1020040028658A
公开(公告)日：2004-04-03
申请号：KR1020037005476
申请日：2001-10-18
Applicant: 한국전자통신연구원
IPC: G06F17/30 , H04N21/232 , G06T5/40 , G06T1/00
CPC classification number: G06F17/30259 , H04N19/98
Abstract: PURPOSE: A non-linear quantization and similarity matching methods for retrieving image data is provided to construct a database to store image information representing a plurality of images with fewer bits, and to retrieve corresponding images in response to a query image based on a database with a high retrieval speed and accuracy. CONSTITUTION: L.times.5 number of normalized edge histogram bins are calculated to generate L number of edge histograms of a target image, wherein L is a positive integer and each edge histogram has five normalized edge histogram bins and represents a spatial distribution of five reference edges in a sub-image, wherein the reference edges include four directional edges and a non-directional edge(S101). The L.times.5 number of normalized edge histogram bins are non-linearly quantized to generate L.times.5 number of quantization index values for the target image(S103). The L.times.5 number of quantization index values are stored in the database(S105). And the steps S101 to S105 are repeated until all of the stored images are processed to construct the database having the image information(S107).
Abstract translation: 目的：提供用于检索图像数据的非线性量化和相似性匹配方法，以构建数据库以存储表示具有较少位的多个图像的图像信息，并且基于具有 检索速度快，准确度高。 规定：数量5的归一化边缘直方图区块被计算以生成目标图像的L个边缘直方图，其中L是正整数，并且每个边缘直方图具有五个标准化的边缘直方图区段，并且表示五个空间分布 参考边缘在子图像中，其中参考边缘包括四个方向边缘和非方向边缘（S101）。 第5次归一化边缘直方图区间被非线性量化，以产生目标图像的数量5个量化索引值（S103）。 将数量为5的量化索引值存储在数据库中（S105）。 并且重复步骤S101至S105，直到所有存储的图像被处理以构成具有图像信息的数据库（S107）。
-
公开(公告)号：KR100369370B1
公开(公告)日：2003-01-24
申请号：KR1019990043779
申请日：1999-10-11
Applicant: 한국전자통신연구원
IPC: G06T5/40
Abstract: PURPOSE: A method of generating block-based image histogram is provided to be capable of extracting specific information from a pixel group of a block unit by use of a block of plural pixels by a basic unit of generating histogram. CONSTITUTION: A coefficient 'k' is set to '0', and pixels of an image are grouped to set a block size of a level '0'(S101). Specific information of the image is extracted by a block unit with regard to all blocks of the level '0' to update a corresponding histogram(S102-S105). After extracting the specific information with regard to all blocks of the level '0', the coefficient 'k' indicating the level is increased by '1'(S106). Specific information of a level '1' is generated by merging specific information of the level '0'(S107), updating a corresponding histogram(S108). Operations of extracting the specific information with regard to all blocks of the level '1' and updating a corresponding histogram are repeated(S109,S110). If the operation of generating specific information with regard to all levels is not completed(S111), the procedure goes to the step(S106) of increasing the coefficient. If the operation of generating specific information with regard to all levels is completed(S111), the procedure is ended.
Abstract translation: 目的：提供一种生成基于块的图像直方图的方法，以便能够通过生成直方图的基本单元通过使用多个像素块来从块单元的像素组提取特定信息。 构成：系数'k'被设置为'0'，并且图像的像素被分组以设置级别'0'的块大小（S101）。 图像的特定信息由块单元针对级别'0'的所有块提取以更新对应的直方图（S102-S105）。 在提取关于等级'0'的所有块的特定信息之后，指示等级的系数'k'增加'1'（S106）。 通过合并级别'0'的特定信息生成级别'1'的特定信息（S107），更新对应的直方图（S108）。 重复关于级别'1'的所有块提取特定信息并更新相应直方图的操作（S109，S110）。 如果没有完成关于所有级别的特定信息的生成操作（S111），则程序进入增加系数的步骤（S106）。 如果完成关于所有级别的生成特定信息的操作（S111），则过程结束。
-
公开(公告)号：KR100360773B1
公开(公告)日：2002-11-13
申请号：KR1019990022154
申请日：1999-06-15
Applicant: 한국전자통신연구원
IPC: G06T11/00
Abstract: 이발명은동영상에서추출된대표영상을메모리자원을고갈시킴이없이실시간적으로클러스터링결과를확인하면서클러스터링하는방법을제공하기위한것이다. 이발명에따른영상클러스터링방법은시간축을따라이동하면서 1차할당을수행하는단계와, 1차할당개시후일정시간마다주기적으로각각의클러스터의유효기간을조사하고수명이다한클러스터를메모리에서삭제하는단계및, 삭제되는클러스터에 1차할당된영상들중에서편향(bias)된대표영상들에대하여다시 2차할당을수행하는단계를포함한다. 상기 1차할당단계는, 할당될영상들에대해시간축상에서최근거리에있는클러스터를탐색하는단계(S03)와, 해당영상과탐색된클러스터사이의거리가임계치(TH1) 이내인지의여부를판단하는단계(S04)와, 판단결과에따라, 해당영상을탐색된클러스터에할당(S05)하거나새로운클러스터를생성(S02)하여할당하는단계를포함하며, 상기 2차할당단계는, 상기클러스터삭제단계에서삭제되는클러스터에할당되어있는대표영상에대해시간축상의최근거리에있는클러스터를탐색하는단계와, 해당클러스터에해당대표영상을재할당함과아울러해당클러스터의기준시간및 수명을갱신하는단계를포함한다.
-
公开(公告)号：KR100240655B1
公开(公告)日：2000-01-15
申请号：KR1019970053937
申请日：1997-10-21
Applicant: 한국전자통신연구원
IPC: H04N19/59
Abstract: 본 발명은 압축된 영상 정보의 내용 추출 방법에 관한 것으로, 영상 정보가 여러 가지 변수를 내포하고 있어 특징 정보로 규정하기 위한 알고리즘 및 하드웨어가 복잡해 지고 영상 정보 추출을 위해 많은 계산량이 요구되는 문제점을 해결하기 위하여, 허프만 디코딩 과정 이전의 부호화된 이산적 여현 변환(DCT) 계수로부터 디코딩을 수행하지 않고 직접 영상 정보의 내용을 추출하므로써 보다 빠르게 압추고딘 디지털 영상 정보를 처리할 수 있는 압축된 영상 정보의 내용 추출 방법이 제시된다.
-
Patent Agency Ranking
公开(公告)号：KR1020020031015A
公开(公告)日：2002-04-26
申请号：KR1020000062137
申请日：2000-10-21
Applicant: 한국전자통신연구원
IPC: G06T5/40
CPC classification number: G06F17/30259 , H04N19/98
Abstract: PURPOSE: A method for calculating non-linear quantization and a similarity of an edge histogram bin is provided to use a non-linear quantizer, and to encode a histogram bin value generated by 5 directional edge information, so as to reduce a bit amount necessary for storing and improve a similarity calculation speed for search. CONSTITUTION: Images are divided into 4x4 areas(S201). A directional edge histogram is generated(S203). A non-linear quantization table is calculated(S205). The calculated table is stored in a database(S207). An index is normalized(S209). A global and a semi-global histograms are generated(S211). And data are matched(S213). When generating the directional edges, features are extracted by the unit of block for the images divided into 4x4 areas, that is, 16 areas thereby generating 5 edges. The images are divided into sub-images that are not overlapped, and the edge histogram for each sub-image is generated as in the step of (S203).
Abstract translation: 目的：提供一种用于计算非线性量化的方法和边缘直方图bin的相似度，以使用非线性量化器，并且对由5个方向边缘信息生成的直方图bin值进行编码，以便减少必要的比特量 用于存储和提高搜索的相似度计算速度。 构成：图像分为4x4区域（S201）。 生成方向边缘直方图（S203）。 计算非线性量化表（S205）。 将所计算的表存储在数据库中（S207）。 索引被归一化（S209）。 生成全局和半全局直方图（S211）。 数据匹配（S213）。 当产生方向边缘时，通过块的单位提取特征，用于分成4×4区域的图像，即16个区域，从而产生5个边缘。 图像被划分为不重叠的子图像，并且如（S203）的步骤中生成每个子图像的边缘直方图。
-
公开(公告)号：KR100314654B1
公开(公告)日：2001-11-15
申请号：KR1019990008383
申请日：1999-03-12
Applicant: 한국전자통신연구원
IPC: G06T5/40
Abstract: 본발명은 JPEG, MPEG-1, 2의표준을따르는압축된영상데이터로부터수퍼픽셀단위선형양자화를이용하여컬러, 밝기, 그리고에지성분을갖는히스토그램을생성하는방법에관한것이다. 기존의히스토그램생성방법은히스토그램의빈과빈 사이에서발생하는양자화오차의영향에의해정확한특징을반영할수 없었다. 또한, 무채색과유채색을구분하는방법에있어서도경계영역에서오차가발생하였다. 또한, 여러종류의특징정보를동시에사용할경우에는정규화시키는기준이없기때문에다양한특징정보를반영하기가어려웠다. 본발명에서는히스토그램을생성하는기본단위를픽셀들의집합인수퍼픽셀단위로수행하여영상내색상과밝기특징뿐만아니라에지성분의분포까지나타낼수 있도록한다. 또한, 히스토그램의빈과빈 사이에선형적가중치를적용함으로써실수영역에서의연산을통한히스토그램카운터를구현하여히스토그램생성시발생하는오차를감소시킨다. 그리고, 컬러와밝기, 에지에대한특징정보를영상의내용에따라정규화된하나의히스토그램상에표현하여다양한특징정보를반영한다.
-
公开(公告)号：KR1020010036671A
公开(公告)日：2001-05-07
申请号：KR1019990043779
申请日：1999-10-11
Applicant: 한국전자통신연구원
IPC: G06T5/40
Abstract: PURPOSE: A method of generating block-based image histogram is provided to be capable of extracting specific information from a pixel group of a block unit by use of a block of plural pixels by a basic unit of generating histogram. CONSTITUTION: A coefficient 'k' is set to '0', and pixels of an image are grouped to set a block size of a level '0'(S101). Specific information of the image is extracted by a block unit with regard to all blocks of the level '0' to update a corresponding histogram(S102-S105). After extracting the specific information with regard to all blocks of the level '0', the coefficient 'k' indicating the level is increased by '1'(S106). Specific information of a level '1' is generated by merging specific information of the level '0'(S107), updating a corresponding histogram(S108). Operations of extracting the specific information with regard to all blocks of the level '1' and updating a corresponding histogram are repeated(S109,S110). If the operation of generating specific information with regard to all levels is not completed(S111), the procedure goes to the step(S106) of increasing the coefficient. If the operation of generating specific information with regard to all levels is completed(S111), the procedure is ended.
Abstract translation: 目的：提供一种生成基于块的图像直方图的方法，以便能够通过使用多个像素的块通过生成直方图的基本单位从块单元的像素组中提取特定信息。 构成：将系数“k”设置为“0”，并且将图像的像素分组以设置水平“0”的块大小（S101）。 针对电平“0”的所有块，通过块单位提取图像的特定信息，以更新对应的直方图（S102〜S105）。 在提取关于电平“0”的所有块的特定信息之后，指示电平的系数“k”增加“1”（S106）。 通过合并电平“0”的特定信息（S107），更新对应的直方图（S108）来生成电平“1”的具体信息。 重复提取关于电平“1”的所有块的特定信息和更新对应的直方图的操作（S109，S110）。 如果关于所有级别生成特定信息的操作没有完成（S111），则过程进行到增加系数的步骤（S106）。 如果关于所有级别生成特定信息的操作完成（S111），则过程结束。
-
公开(公告)号：KR1020010002385A
公开(公告)日：2001-01-15
申请号：KR1019990022154
申请日：1999-06-15
Applicant: 한국전자통신연구원
IPC: G06T11/00
Abstract: PURPOSE: A method for clustering an image with a duplicate allocation type is provided to perform an image clustering without a drain of memory resource and identify the progress of the clustering in real time. The method performs the clustering to an exemplary image extracted from moving pictures. CONSTITUTION: The method for clustering an image with a duplicate allocation type includes following processes. In a first allocating process, since a newly inputted image(S01) has no the existing cluster, a new cluster is produced(S02) and allocated to the newly inputted image. To the clusters inputted under the second order, a cluster existing the shortest distance to the time axis is searched(S03). Thereafter, a process is to perform whether the distance between the corresponding image and the searched cluster is within a critical value(TH1) or not(S04). If the result is "yes", the corresponding image is allocated to the searched cluster(S05). If the result is "no", a new cluster is produced(S02) and allocated the corresponding image to the cluster.
Abstract translation: 目的：提供一种用于对具有重复分配类型的图像进行聚类的方法，以执行图像聚类，而不会消耗内存资源，并实时识别聚类的进度。 该方法对从运动图像提取的示例性图像执行聚类。 构成：使用重复分配类型对图像进行聚类的方法包括以下过程。 在第一分配处理中，由于新输入的图像（S01）不存在现有的簇，所以产生新的簇（S02）并将其分配给新输入的图像。 对于按二次输入的群集，搜索存在与时间轴的最短距离的群集（S03）。 此后，处理是执行对应图像和搜索到的簇之间的距离是否在临界值（TH1）内（否）（S04）。 如果结果为“是”，则将相应的图像分配给搜索到的集群（S05）。 如果结果为“否”，则生成新的集群（S02），并将相应的映像分配给集群。
-
公开(公告)号：KR1020000060248A
公开(公告)日：2000-10-16
申请号：KR1019990008383
申请日：1999-03-12
Applicant: 한국전자통신연구원
IPC: G06T5/40
Abstract: PURPOSE: A method for forming a multiple histogram using a super pixel and a linear quantization is provided to reduce errors occurring at the edge of colors. CONSTITUTION: The method for forming a multiple histogram using a super pixel and a linear quantization includes following steps. The color, brightness and edge histograms are generated by using color information(Cr, Cb) and brightness information(Y) of compressed image data. The histogram is formed by grouping pixels of the image in one group, that is on a super pixel basis. A macro block is specified on the super pixel basis(S101) in the compressed image and a direct current value of discrete cosine transformation block four brightness(Y) is extracted. Then, whether an edge exists is determined(S102). Finally, a histogram component corresponding to the edge pattern is increased(S104) when an edge exists.
Abstract translation: 目的：提供一种使用超像素和线性量化形成多重直方图的方法，以减少颜色边缘发生的错误。 构成：使用超像素和线性量化形成多个直方图的方法包括以下步骤。 通过使用压缩图像数据的颜色信息（Cr，Cb）和亮度信息（Y）来生成颜色，亮度和边缘直方图。 该直方图是通过将一组中的图像的像素分组，即在超像素的基础上形成的。 在压缩图像中基于超像素（S101）指定宏块，并提取离散余弦变换块四亮度（Y）的直流值。 然后，确定边缘是否存在（S102）。 最后，当边缘存在时，对应于边缘图案的直方图分量增加（S104）。
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.033 seconds)
