公开(公告)号：KR100825725B1

公开(公告)日：2008-04-29

申请号：KR1020060076734

申请日：2006-08-14

Applicant: 한국전자통신연구원

Inventor： 김원겸 ,  서용석 ,  이선화 ,  유원영 ,  이상광 ,  이성환 ,  이승재 ,  정혜원 ,  윤영석 ,  오원근 ,  서영호 ,  서진수

IPC: H04N5/913

Abstract: 2개 이상의 서로 다른 양자화 스탭 사이즈로 워터마크를 삽입/추출하는 방법 및 장치가 개시된다. 본 발명은 워터마크를 삽입할 이미지의 에지 성분 값을 산출하는 단계와, 임의의 기준 값을 기준으로 하여 에지 성분 값에 따라 서로 다른 양자화 스탭 사이즈를 적용할 2개 이상의 영역으로 이미지를 구분하는 단계 및 구분된 영역에 해당하는 양자화 계수를 적용하여 워터마크를 삽입하는 단계를 포함한다. 본 발명에 따르면, 이미지의 영역에 따라 워터마크가 적응적으로 삽입되어 비가시성과 강인성을 극대화하는 효과가 있다.
디지털 워터마킹, digital watermarking, QIM, 핑거프린팅, fingerprinting, 양자화, 저작권 보호

公开(公告)号：KR100523978B1

公开(公告)日：2005-10-27

申请号：KR1020020053904

申请日：2002-09-06

Applicant: 한국전자통신연구원

Inventor： 서용석 ,  주상현 ,  오원근

IPC: H04N21/83 ,  H04N21/8358

CPC classification number: G06T1/0057 ,  G06T1/0028 ,  G06T2201/0052 ,  G06T2201/0083 ,  G06T2201/0202

Abstract: 본 발명은 웨이블릿 기반에서의 디지털 워터마킹에 관한 것이다. 즉, 인간의 시각 시스템이 저주파성분의 변화에 민감하게 반응하며, 고주파 성분에서는 여러 가지 신호처리 공격에 쉽게 변형될 수 있다는 점을 고려하여 본 발명에서는 저작권 보호를 위한 워터마크 삽입 및 추출에 있어서 원 데이터에 대한 웨이블릿 변환 영역 중 DC성분 영역에 양자화와 역양자화 과정을 통해 워터마크를 삽입함으로써 압축 등과 같은 외부 공격에도 삽입된 워터마크가 견고성을 유지할 수 있는 이점이 있다. 또한, 본 발명에서는 워터마크의 추출 시 원 화상을 필요로 하지 않는 블라인드방식으로 정지화상뿐만아니라 실시간 삽입/추출이 요구되는 오디오/비디오분야 등과 같은 관련 응용분야로의 확장이 용이한 이점이 있다.

公开(公告)号：KR100426305B1

公开(公告)日：2004-04-08

申请号：KR1020010074151

申请日：2001-11-27

Applicant: 한국전자통신연구원

Inventor： 주상현 ,  서용석 ,  서영호 ,  오원근

IPC: H04N5/913

CPC classification number: G06T1/0057 ,  G06T2201/0052 ,  G06T2201/0083

Abstract: An apparatus and method for embedding and extracting digital watermarks using a blind mode based on wavelet transform which is robust to external attacks while being capable of minimizing a degradation in picture quality caused by embedding of the watermarks. In accordance with the invention, watermarks protection of the copyright for desired data are embedded in DC component domains of wavelet-transformed domains. In accordance with the invention, embedding of watermarks in a target image corresponding to a target domain in which the watermarks are to be embedded, is achieved by generating a data stream of the watermarks in accordance with a key value selected by the user, generating index information representing positions where the watermarks are to be embedded, in accordance with a key value selected by the ser, and reflecting the watermark data stream on data values of pixels in the target image at the positions based on the index information.

Abstract translation: 一种用于使用基于小波变换的盲模式嵌入和提取数字水印的设备和方法，该设备和方法对外部攻击具有鲁棒性，同时能够最小化由嵌入水印引起的图像质量下降。 根据本发明，用于期望数据的版权的水印保护被嵌入到小波变换域的DC分量域中。 根据本发明，通过根据用户选择的关键值生成水印的数据流，实现将水印嵌入到与要嵌入水印的目标域相对应的目标图像中，从而生成索引 根据由ser选择的关键值，表示水印将被嵌入的位置的信息，并且在基于索引信息的位置处的目标图像中的像素的数据值上反映水印数据流。

公开(公告)号：KR1020030043133A

公开(公告)日：2003-06-02

申请号：KR1020010074151

申请日：2001-11-27

Applicant: 한국전자통신연구원

Inventor： 주상현 ,  서용석 ,  서영호 ,  오원근

IPC: H04N5/913

CPC classification number: G06T1/0057 ,  G06T2201/0052 ,  G06T2201/0083

Abstract: PURPOSE: A system and method for inserting/extracting a digital watermark using a wavelet based blind watermarking technique are provided to minimize deterioration of picture quality due to insertion of the watermark. CONSTITUTION: A system for inserting/extracting a digital watermark using a wavelet based blind watermarking technique includes a radio-frequency component removal unit(302), an index information generator(308), a watermark generator(306), and a watermark insertion unit(304). The radio-frequency component removal unit removes a radio-frequency component of an image of an area designated as a watermark insertion region from the entire image wavelet-transformed. The index information generator generates index information for designating a pixel position into which watermark data is inserted. The watermark generator generates a watermark data stream to be inserted into the image of the watermark insertion region. The watermark insertion unit inserts the watermark data into the pixel position within the watermark insertion region according to the index information.

Abstract translation: 目的：提供一种使用基于小波的盲水印技术来插入/提取数字水印的系统和方法，以最小化由于插入水印造成的图像质量的恶化。 构成：使用基于小波的盲水印技术来插入/提取数字水印的系统包括射频分量去除单元（302），索引信息生成器（308），水印生成器（306）和水印插入单元 （304）。 射频分量去除单元从小波变换的整个图像中去除指定为水印插入区域的区域的图像的射频分量。 索引信息生成器生成用于指定插入水印数据的像素位置的索引信息。 水印生成器生成要插入到水印插入区域的图像中的水印数据流。 水印插入单元根据索引信息将水印数据插入水印插入区域内的像素位置。

公开(公告)号：KR100317653B1

公开(公告)日：2002-02-19

申请号：KR1019980052019

申请日：1998-11-30

Applicant: 한국전자통신연구원

Inventor： 지수영 ,  장대근 ,  오원근

IPC: G06K9/46

Abstract: 본 발명은 다국어 문서 내에 포함된 모든 문자에 대하여 문자 영상의 변형과 크기에 무관한 대용량 인쇄체 문자인식에 적합한 특징 추출 방법에 관한 것으로서, 망(mesh) 값의 위치변형에 대한 누적빈도와 해밍 디스턴스(Hamming distance)의 누적 값의 조합에 의해 문자의 특징을 추출하는 대용량 인쇄체 문자인식을 위한 특징 추출 방법에 관한 것이다.
본 발명은 문자영상 획득 과정에서 광학 스캐너로 대용량 인쇄체 문자영상을 입력하는 단계와, 상기 문자영상 획득 과정에서 입력된 문자영상의 글자 크기가 각기 다른 문자들에 대해 전처리 과정에서 일정한 크기의 패턴으로 문자들을 정규화 하는 단계와, 상기 전처리 과정을 통해 정규화된 문자들에 대해 특징 추출 과정에서 특징별로 추출하는 단계와, 상기 특징 추출 과정을 통해 특징별로 추출된 문자들에 대해 대분류 과정에서 특징별로 재분류 하는 단계로 이루어진 대용량 인쇄체 문자인식을 위한 특징 추출 방법을 제시한다.

公开(公告)号：KR1020010055119A

公开(公告)日：2001-07-04

申请号：KR1019990056196

申请日：1999-12-09

Applicant: 한국전자통신연구원

Inventor： 박창준 ,  김현진 ,  오원근

IPC: G01B11/24

CPC classification number: G06T7/0008 ,  G01N21/88 ,  G01N21/8851 ,  G01N2021/8887 ,  G06T7/68

Abstract: PURPOSE: A surface inspecting apparatus and a method thereof are provided to detect a stain or a foreign matter existing on a surface of an object having unequal intensity or a pattern. CONSTITUTION: A surface inspecting apparatus includes an image obtaining element for obtaining a surface image of an object to be inspected, and a control element detecting a stain or a foreign matter by empathizing symmetry of the stain or the foreign matter with using the magnitude of the intensity gradient or the orientation of the intensity gradient related to the surface image of the object. A surface inspecting method includes the steps of receiving the surface image for obtaining the magnitude of the intensity gradient and the orientation of the intensity gradient of pixels by using a gradient operator(21-22), obtaining a symmetry magnitude map in which symmetry of the stain or the foreign matter is embossed, by using the obtained intensity information(23), and detecting the stain or the foreign matter by using the obtained symmetry magnitude map(24).

Abstract translation: 目的：提供表面检查装置及其方法，以检测存在于具有不同强度或图案的物体的表面上的污渍或异物。 构成：表面检查装置包括用于获得待检查对象的表面图像的图像获取元件，以及通过使用所述检查对象的大小来感知污点或异物的对称性来检测污点或异物的控制元件 强度梯度或与物体的表面图像相关的强度梯度的方向。 表面检查方法包括以下步骤：通过使用梯度算子（21-22）接收用于获得强度梯度的大小和像素的强度梯度的方向的表面图像，获得对称幅度图，其中对称度 通过使用所获得的强度信息（23），通过使用所获得的对称幅度图（24）来检测污点或异物，从而将污物或异物压印。

公开(公告)号：KR1020000037703A

公开(公告)日：2000-07-05

申请号：KR1019980052352

申请日：1998-12-01

Applicant: 한국전자통신연구원

Inventor： 이인호 ,  김현진 ,  박창준 ,  오원근

IPC: G06F19/00

Abstract: PURPOSE: A method for matching the location of thin film printed matter using distortion and the apparatus thereby are provided so that the image of an object of inspection can be matched with a reference image, even though a deformed image is inputted, by carry out deformation compensation for image deformation as well as location compensation for the location movement of the inspection object image. CONSTITUTION: An image of an object of inspection is inputted from the external by an image input part(301). After more than 2 characteristic points of a reference image are set up at a characteristic point location measurement part(302), the characteristic point location of the inspection object image is measured(303). A first location compensation part and a deformation compensation part distort the inspection object image by the difference of the characteristic points(304).

Abstract translation: 目的：提供使用失真的薄膜印刷品的位置与由此设备匹配的方法，使得即使输入变形图像，检查对象的图像也可以与参考图像匹配，通过进行变形 对图像变形的补偿以及检查对象图像的位置移动的位置补偿。 构成：通过图像输入部（301）从外部输入检查对象的图像。 在特征点位置测量部分（302）上设置参考图像的超过2个特征点之后，测量检查对象图像的特征点位置（303）。 第一位置补偿部分和变形补偿部分通过特征点的差异使检查对象图像失真（304）。

公开(公告)号：KR1020000037702A

公开(公告)日：2000-07-05

申请号：KR1019980052351

申请日：1998-12-01

Applicant: 한국전자통신연구원

Inventor： 이인호 ,  김현진 ,  박창준 ,  오원근

IPC: G06K9/00

Abstract: PURPOSE: A position recognition method of a pattern is proposed to recognize the position of a pattern and apply to all patterns with no affection of feature or structure of a pattern. CONSTITUTION: A position recognition method of a pattern with no affection of feature or structure of a pattern is composed of image input step(101), relative position movement step(102), pixel area extraction step(103), similarity calculation step(104), and maximum similarity calculation step(105). At image input step, a source and target image are inputted using camera or image input device. The relative position movement step moves pixels of target image by one pixel with i and C direction to get a degree of similarity between source and target image. The pixel area extraction step extracts a pixel area, in the target image, with the same size to the source image executing the relative position movement step. If a pixel area with the same size to the source image is extracted, the similarity calculation step calculates the degree of similarity between source and target image. The similarity degree is from 0 to 1. If the degree is 0, source and target image are not similar at all. If the degree is 1, the two images are same.

Abstract translation: 目的：提出了一种模式的位置识别方法来识别图案的位置，并适用于不受图案特征或结构影响的所有图案。 构成：不影响图案的特征或结构的图案的位置识别方法由图像输入步骤（101），相对位置移动步骤（102），像素区域提取步骤（103），相似度计算步骤（104） ）和最大相似度计算步骤（105）。 在图像输入步骤中，使用相机或图像输入装置输入源图像和目标图像。 相对位置移动步骤通过i和C方向将目标图像的像素移动一个像素，以获得源图像和目标图像之间的相似程度。 像素区域提取步骤将目标图像中的像素区域以相同的大小提取到执行相对位置移动步骤的源图像。 如果提取与源图像具有相同大小的像素区域，则相似度计算步骤计算源图像和目标图像之间的相似度。 相似度为0到1.如果度数为0，则源图像和目标图像根本不相似。 如果度数为1，则两张图像相同。

公开(公告)号：KR1020000037700A

公开(公告)日：2000-07-05

申请号：KR1019980052349

申请日：1998-12-01

Applicant: 한국전자통신연구원

Inventor： 이인호 ,  오원근

IPC: G06F17/50

Abstract: PURPOSE: A method for generating automatically in a Technical Illustration(TI) is provided to automatically generate a set of parts according to five rules, such as a nest inhibit, a parallel movement, a same interval, a hiding inhibit by a different connected part of a part hole, and a minimum dimension rule, by being inputted a three-dimensional Computer-Aided Design(CAD) data of machine parts almost assembled. CONSTITUTION: A method for generating automatically in a Technical Illustration(TI) comprises the steps of: being inputted a three-dimensional Computer-aided design(CAD) data of machinery parts; generating a hole-parts relation, which examines other parts of an inside hole in a completed step of the parts; generating a directed graph, which appears a relative directional relation of the parts against each axis'(X,Y,Z axis) direction in the technical TI from the hole-part relation; generating a part setting graph, which makes an order relation regarding a set of the parts generated in the TI from the relative directional graph generated; and executing a numeric value constraining process, which deciding each part's interval from the part setting graph.

Abstract translation: 目的：提供在技术图（TI）中自动生成的方法，以根据五个规则自动生成一组零件，如嵌套禁止，平行运动，相同间隔，不同连接部件的隐藏抑制 通过输入几乎组装的机器零件的三维计算机辅助设计（CAD）数据，以及最小尺寸规则。 构成：在技术图（TI）中自动生成的方法包括以下步骤：输入机械部件的三维计算机辅助设计（CAD）数据; 产生一个孔部分关系，其在零件的完成步骤中检查内孔的其它部分; 产生有向图，其在技术TI中从孔部分关系出现部件相对于每个轴线（X，Y，Z轴）方向的相对方向关系; 生成部件设置图，其从生成的相对方向图形成与TI中生成的部分的集合的顺序关系; 并执行数值约束处理，其从零件设置图决定每个零件的间隔。

公开(公告)号：KR1020000037587A

公开(公告)日：2000-07-05

申请号：KR1019980052214

申请日：1998-12-01

Applicant: 한국전자통신연구원

Inventor： 박창준 ,  김현진 ,  이인호 ,  오원근

IPC: G01B11/16

Abstract: PURPOSE: A method for detecting protrusion by using shadow is provided to automatically and visually check an existence, position, and angle of a protrusion or concave/convex portion of an object by taking a photograph of the object put on the floor. CONSTITUTION: A method for detecting protrusion by using shadow includes the steps of radiating a light beam on an object by a lighting element and inputting a reflected image by an image input element, analyzing a shadow shape of the input image and determinating existence of a protrusion, and measuring a position and angle of the protrusion by a maximum length in an internal blank of an ellipse due to the protrusion in the shadow shape if the protrusion is exist, wherein the lighting element is a diffused light source of ring illuminator or a spot light source, a radiating angle of the lighting element is perpendicular or inclined by a predetermined angle with relation to the object, and the existence of the protrusion is determined by comparing the length of the inner blank of the protrusion and the length of the protrusion.

Abstract translation: 目的：提供通过使用阴影来检测突起的方法，通过拍摄放置在地板上的物体的照片来自动和目视地检查物体的突起或凹/凸部分的存在，位置和角度。 构成：通过使用阴影检测突起的方法包括以下步骤：通过照明元件将光束照射在物体上并通过图像输入元件输入反射图像，分析输入图像的阴影形状并确定突起的存在 并且如果存在突起，则由于阴影形状的突起而在椭圆形的内部坯件中测量突起的位置和角度的最大长度，其中照明元件是环形照明器的漫射光源或点 光源，照明元件的照射角度相对于物体垂直或倾斜预定角度，并且突起的存在通过比较突起的内部坯件的长度和突起的长度来确定。