-
公开(公告)号：KR1020030011987A
公开(公告)日：2003-02-12
申请号：KR1020010045802
申请日：2001-07-30
Inventor： 김회율
IPC: G06K9/62
Abstract: PURPOSE: A method for the high recognizable and readable OCR(Optical Character Recognition) input of Korean notes is provided to minimize an input error of a user and to enhance the recognition by separating a dual consonant and a dual vowel into each unit character element. CONSTITUTION: An OCR input format is configured by respectively separating an initial sound, a vowel and a final consonant into a pair of rectangles(S1). Each character element is written in each rectangle(S2). The entire character element format is configured by placing two initial sound regions to a left upper side, placing two vowels regions to the middle under the initial sound region and a right upper side, and placing two final consonant regions to a lower side of the vowel regions(S3). A guide line to increase the recognition for each character element is formed(S4).
Abstract translation: 目的：提供韩国笔记的高可识别和可读的OCR（光学字符识别）输入的方法，以最小化用户的输入错误，并通过将双辅音和双元音分隔成每个单位字符元素来增强识别。 构成：通过分别将初始声音，元音和最终辅音分成一对矩形来配置OCR输入格式（S1）。 每个字符元素都写入每个矩形（S2）。 通过将两个初始声音区域放置在左上侧，将两个元音区域放置在初始声音区域和右上侧的中间，并将两个最终辅音区域放置在元音的下侧来配置整个字符元素格式 区域（S3）。 形成用于增加每个字符元素的识别的引导线（S4）。
-
公开(公告)号：KR100353798B1
公开(公告)日：2002-09-26
申请号：KR1019990054300
申请日：1999-12-01
Applicant: 김회율 , 주식회사 팬택앤큐리텔 , 주식회사 코난테크놀로지
IPC: G06T1/00
CPC classification number: G06K9/4609 , G06F17/30259 , G06K9/52 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99943
Abstract: 1. 청구범위에기재된발명이속한기술분야본 발명은영상객체모양정보추출방법및 그를이용한내용기반이미지검색시스템및 그방법과, 상기방법을실현시키기위한프로그램을기록한컴퓨터로읽을수 있는기록매체에관한것임. 2. 발명이해결하려고하는기술적과제본 발명은, 영상객체의모양을정량적인특징값으로기술하고그 유사도를역시정량적으로정의함으로써객관적인모양의유사도를측정할수 있는 ART 모양기술자를정의하며, 이를이용하여대용량의이미지에대하여자동화된모양특징추출및 검색이가능하도록하기위한영상객체모양정보추출방법및 그를이용한내용기반이미지검색시스템및 그방법과, 상기방법을실현시키기위한프로그램을기록한컴퓨터로읽을수 있는기록매체를제공하고자함. 3. 발명의해결방법의요지본 발명은, 내용기반이미지검색시스템에있어서, 데이터베이스구축용영상(기준영상)을입력받기위한기준영상입력수단; 상기기준영상입력수단을통해입력된기준영상객체의모양을기저함수들의조합으로표현하고, 각기저함수가직교성을갖도록정의한후, 상기기준영상과임의의기저함수의내적을구하여, 상기기준영상에대한제1 회전불변모양기술자로서의해당 ART(Angular Radial Transform) 기저함수의계수를구하기위한제1 모양기술자추출수단; 상기기준영상과상기제1 회전불변모양기술자를매칭시켜저장시키기위한영상저장수단; 사용자가검색하고자하는질의영상객체의모양을기저함수들의조합으로표현하고, 각기저함수가직교성을갖도록정의한후, 상기질의영상과임의의기저함수의내적을구하여, 상기질의영상에대한제2 회전불변모양기술자로서의해당 ART 기저함수의계수를구하기위한제2 모양기술자추출수단; 및상기질의영상에대한제2 회전불변모양기술자와상기기준영상에대한제1 회전불변모양기술자의유사도를비교하여, 유사도가높은상기제1 회전불변모양기술자에매칭되는상기기준영상을출력제어하기위한모양기술자비교및 제어수단을포함함. 4. 발명의중요한용도본 발명은내용기반이미지검색등에이용됨.
-
公开(公告)号：KR1020010053788A
公开(公告)日：2001-07-02
申请号：KR1019990054300
申请日：1999-12-01
Applicant: 김회율 , 주식회사 팬택앤큐리텔 , 주식회사 코난테크놀로지
IPC: G06T1/00
CPC classification number: G06K9/4609 , G06F17/30259 , G06K9/52 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99943
Abstract: PURPOSE: A contents based image retrieval system and a method are provided to be capable of rapidly retrieving a desired image by editing and deforming an inquiry image input by a user or an image output by the retrieve to reuse the image in inquiry. CONSTITUTION: An image input part(100) receives images for structuring an image descriptor database. An image extraction part(101) extracts an ART(Angular Radial Transform) image descriptor of images input to the image input part(100). Images input from the image input part(100) are stored in an image database(102). Image descriptors extracted from the image extraction part(101) are stored in an image descriptor database(103). Images to be retrieved from a remote user web browser are input to an image inquiry part(104). An inquiry image extraction part(105) extracts an image descriptor from the inquiry images. An image descriptor similarity comparator(106) compares the similarity between the image descriptor of the inquiry image and the image descriptor of a database image recorded in the image descriptor database(103). An image output part(107) outputs an image similar to the inquiry image retrieved by the comparator(106).
Abstract translation: 目的：提供一种基于内容的图像检索系统和方法，其能够通过编辑和变形由用户输入的查询图像或通过检索输出的图像来快速检索所需图像以便重新使用查询中的图像。 构成：图像输入部分（100）接收用于构造图像描述符数据库的图像。 图像提取部（101）提取输入到图像输入部（100）的图像的ART（角径向变换）图像描述符。 从图像输入部（100）输入的图像被存储在图像数据库（102）中。 从图像提取部（101）提取的图像描述符存储在图像描述符数据库（103）中。 要从远程用户web浏览器检索的图像被输入到图像查询部分（104）。 查询图像提取部分（105）从查询图像中提取图像描述符。 图像描述符相似性比较器（106）比较查询图像的图像描述符和记录在图像描述符数据库（103）中的数据库图像的图像描述符之间的相似度。 图像输出部（107）输出与比较器（106）检索出的查询图像相似的图像。
-
公开(公告)号：KR1020010038800A
公开(公告)日：2001-05-15
申请号：KR1019990046916
申请日：1999-10-27
Applicant: 김회율
CPC classification number: G06T7/66
Abstract: PURPOSE: A Zernike/Pseudo Zernike moment extraction method is provided to rapidly extract the moment and reduce a memory in the extraction step by using the symmetric characteristics of the basis function of the Zernike/Pseudo Zernike moment. CONSTITUTION: The method comprises steps of obtaining a basis function of the Zernike/Pseudo Zernike moment on the first quadrant(101), obtaining a pixel value on an input image(102), and extracting the Zernike/Pseudo Zernike moment by multiplying the basis function value by the pixel value(103). The basis function obtaining step includes steps of obtaining real number polynomials of the Zernike moment and real number polynomials of the Pseudo Zernike moment(104), checking if a repetition number is even(105), and obtaining the basis function by using the symmetry of y=x in the case that the repetition number is even(106,107). The pixel value obtaining step(102) includes steps of calculating a center of the image, and projecting the points, in the second, the third and the fourth quadrant, on the first quadrant(108,109).
Abstract translation: 目的：提供Zernike /伪Zernike矩提取方法，通过使用Zernike /伪Zernike矩的基函数的对称特征，快速提取时刻并减少提取步骤中的记忆。 构成：该方法包括以下步骤：获得第一象限（101）上的泽尼克/假Zernike矩的基函数，获得输入图像（102）上的像素值，以及通过将基准乘以基准来提取Zernike /伪Zernike矩 函数值乘以像素值（103）。 基本函数获取步骤包括以下步骤：获得Zernike矩的实数多项式和伪Zernike矩（104）的实数多项式，检查重复数是否均匀（105），以及通过使用对称性来获得基函数 在重复数为偶数（106,107）的情况下，y = x。 像素值获取步骤（102）包括以下步骤：计算图像的中心，并且在第一象限（108,109）上投影第二，第三和第四象限中的点。
-
-
Patent Agency Ranking
公开(公告)号：KR2020160000569U
公开(公告)日：2016-02-17
申请号：KR2020140005966
申请日：2014-08-08
Applicant: 김회율
Inventor： 김회율
Abstract: 방수마스크가제공된다. 상기방수마스크는, 투명또는반투명소재로형성되어사용자의안면에물 등의용액이침투하는것을차단하는방수필름및 상기방수필름의상부및 양측면의가장자리에부착되어, 상기방수필름을사용자의안면에부착시키는점착부를포함하고, 상기점착부는외측의제1 점착부및 내측의제2 점착부의 2중구조인것을특징으로한다.
Abstract translation: 提供防水面罩。 防水面罩可以包括由透明或半透明材料形成的防水膜，以防止诸如水的溶液渗透到用户的脸部中，以及附接到防水膜和防水膜的边缘的防水膜， 并且粘合部分是外侧上的第一粘合部分和内侧上的第二粘合部分的双接头。
-
公开(公告)号：KR100718361B1
公开(公告)日：2007-05-14
申请号：KR1019990054286
申请日：1999-12-01
Applicant: 주식회사 팬택앤큐리텔 , 김회율
IPC: G06F17/30
Abstract: 본 발명의 목적은 복잡한 모양정보를 외부 모양정보 및 내부 모양정보로 분리하여 표현하여 정확하고 신속한 멀티미디어 데이터 검색을 할 수 있도록 하는 내부 및 외부 모양정보의 특징정보를 이용한 멀티미디어 검색장치 및 그 방법을 제공하는 데에 있다. 이와같은 목적을 달성하기 위한 본 발명은 질의 영상의 모양정보와 멀티미디어 데이터베이스내의 영상의 모양정보의 외부 모양정보로부터 각각 추출된 특징정보를 사용하여 유사도를 계산하고, 이를 이용하여 멀티미디어 데이터를 검색하는 제1 유사도 계산부와, 상기 두 모양정보의 내부 모양정보로부터 추출된 각각 특징정보를 사용하여 유사도를 계산하고, 이를 이용하여 멀티미디어 데이터를 검색하는 제2 유사도 계산부와, 상기 두 모양정보의 내부/외부 모양정보로부터 각각 추출된 특징정보를 사용하여 유사도를 계산하고, 이를 이용하여 멀티미디어 데이터를 검색하는 제3 유사도 계산부와, 상기 두 모양정보에서 각각 추출된 특징정보가 서로 다르고, 그 중 하나의 특징정보가 내부/외부 모양정보로부터 추출된 특징정보이고, 다른 하나의 특징정보가 내부 모양정보로부터 추출된 특징정보 또는 외부 모양정보로부터 추출된 특징정보인 경우에는, 그 내부 모양정보로부터 추출된 특징정보 또는 외부 모양정보로부터추출된 특징정보에 대해서만 유사도를 계산하고, 이를 이용하여 멀티미디어 데이터를 검색하는 제4 유사도 계산부를 포함하여 구성된다.
-
公开(公告)号：KR100406671B1
公开(公告)日：2003-11-21
申请号：KR1020000042346
申请日：2000-07-24
IPC: G06F17/30
Abstract: PURPOSE: A sentence plagiarism search method is provided to extract sentence patterns or code patterns included in a document, and to automatically search for plagiarized sentences by comparing the sentence or code patterns included in the documents. CONSTITUTION: The method comprises steps of searching for new web documents by using a robot agent(201), extracting morphologic characteristic vectors from new searched web documents(202), making a database from the extracted morphologic characteristic vectors(203), enabling a remote user to send a query of requesting a plagiarism on a specific sentence by using a query input interface connected to an application server(204), the application server extracting characteristic vectors from the input sentence and checking a similarity by comparing with the characteristic vectors stored in the database(205), and the server transmitting the compared result to the user over a network.
Abstract translation: 目的：提供句子抄袭搜索方法来提取包含在文档中的句子或代码模式，并通过比较包含在文档中的句子或代码模式来自动搜索抄袭的句子。 构成：该方法包括以下步骤：通过使用机器人代理（201）搜索新的web文档，从新搜索的web文档（202）中提取形态特征向量，根据提取的形态特征向量（203）制作数据库，启用远程 用户通过使用连接到应用服务器（204）的查询输入接口来发送请求关于特定句子的抄袭的查询，应用服务器从输入语句中提取特征向量，并通过与存储在 数据库（205）以及服务器通过网络向用户发送比较结果。
-
公开(公告)号：KR100397752B1
公开(公告)日：2003-09-13
申请号：KR1020000039221
申请日：2000-07-10
Applicant: 김회율
IPC: H04N21/83 , H04N21/8358
Abstract: PURPOSE: A water marking method using block-based wavelet conversion, which does not requires the original image before insertion of watermark in detection of watermark of multimedia image data and accurately detects a changed portion, is provided to effectively protect CONSTITUTION: A watermark that people cannot recognize is generated(S1) and inserted into the original image data in order to protect
Abstract translation: 目的：提供一种使用基于块的小波变换的水印方法，该方法在插入水印之前不需要原始图像来检测多媒体图像数据的水印并准确检测变化的部分，以有效地保护CONSTITUTION： 生成不能识别（S1）并插入到原始图像数据中以保护
-
公开(公告)号：KR100397750B1
公开(公告)日：2003-09-13
申请号：KR1020000015128
申请日：2000-03-24
Applicant: 김회율
IPC: G06K9/00
Abstract: PURPOSE: A method for detecting pupils of eyes is provided to perform an accurate iris recognition which is insensitive to an influence of an illumination for reflecting an eyeball image for realizing an iris detection having an enhanced calculating amount and velocity. CONSTITUTION: In an iris recognizing system including an illumination, a video camera for obtaining an eyeball image of a human body, and a PC having a frame grabber, a basic point is searched firstly by an eyeball image reduced as a predetermined rate for decreasing a calculating amount of a photographed actual eyeball image(S1). A basic point in an eye pupil is detected from the reduced eyeball image(S2), and boundary reserved areas between an iris and an eye pupil of the reduced eyeball image is decided(S3). A radius and a center of a circle most near to a boundary reserved area are calculated using more than three boundary reserved points distanced most out of the boundary reserved areas, a position and a size of an eye pupil are decided, and an eye pupil area is detected(S4).
Abstract translation: 目的：提供一种用于检测眼睛瞳孔的方法，以执行精确的虹膜识别，该虹膜识别对用于反射眼球图像的照明的影响不敏感，以实现具有增强的计算量和速度的虹膜检测。 构成：在包括照明的虹膜识别系统，用于获得人体的眼球图像的摄像机和具有图像采集卡的PC中，首先通过以预定速率减小的眼球图像来搜索基点， 计算拍摄的实际眼球图像的量（S1）。 根据缩小的眼球图像（S2）检测眼睛瞳孔中的基点，并且确定缩小的眼球图像的虹膜与眼睛瞳孔之间的边界保留区域（S3）。 使用边界保留区域中距离最远的三个以上的边界保留点，确定眼睛瞳孔的位置和大小，并且计算出眼睛瞳孔区域的最近的边界保留区域的半径和中心 （S4）。
-
-
-
-
-
-
-
-
-
Search Results
137
records
(took 0.026 seconds)
