-
公开(公告)号：KR1020130078130A
公开(公告)日：2013-07-10
申请号：KR1020110146905
申请日：2011-12-30
Applicant: 전남대학교산학협력단
IPC: G06T7/00
CPC classification number: G06K9/00577 , G06T7/10
Abstract: PURPOSE: An object dividing method using a gaussian mixture model and an RGB clustering is provided to automatically divide an object domain of an object material on an input image without a direct handling by a user. CONSTITUTION: A first sub image generator leads a computer equipment to calculate normal distributions of pixels of each input image, and to produce a first sub image generator (S1200). A second sub image generator leads the computer equipment to calculate color mean values of each candidate area, to calculate Euclidean distance between the each pixel and the each color mean value, and to produce a second sub image (S1300). An object divider leads the computer equipment to produce a result image comprising the object division area comprising the pixels which are positioned on an overlapped spot among each pixel of the first and second object candidate area (S1400). [Reference numerals] (S1100) Output image format is converted to RGB color format; (S1200) First sub image generator leads a computer equipment to calculate normal distributions of pixels of each input image, and to produce a first sub image generator; (S1300) Second sub image generator leads the computer equipment to calculate color mean values of each candidate area, to calculate Euclidean distance between the each pixel and the each color mean value, and to produce a second sub image; (S1400) Object divider leads the computer equipment to produce a result image comprising the object division area comprising the pixels which are positioned on an overlapped spot among each pixel of the first and second object candidate area; (S1500) Result images are converted into a divided binary area, a largest binary area is set as an object area, other areas are set as noises and removed; (S1600) Pixels matched with each pixel coordiate of an object area are created as an object block
Abstract translation: 目的：提供使用高斯混合模型和RGB聚类的对象分割方法，用于在用户直接处理的情况下，自动划分输入图像上的对象材料的对象域。 构成：第一子图像生成器引导计算机设备计算每个输入图像的像素的正态分布，并产生第一子图像生成器（S1200）。 第二子图像生成器引导计算机设备计算每个候选区域的颜色平均值，以计算每个像素与每个颜色平均值之间的欧几里德距离，并产生第二子图像（S1300）。 对象分割器引导计算机设备产生包括包括位于第一和第二对象候选区域的每个像素之间的重叠点上的像素的对象分割区域的结果图像（S1400）。 （附图标记）（S1100）输出图像格式被转换为RGB颜色格式; （S1200）第一子图像生成器引导计算机设备来计算每个输入图像的像素的正态分布，并产生第一子图像生成器; （S1300）第二子图像生成器引导计算机设备计算每个候选区域的颜色平均值，计算每个像素之间的欧几里德距离和每个颜色平均值，并产生第二子图像; （S1400）对象分割器引导计算机设备产生包括对象分割区域的结果图像，该对象分割区域包括位于第一和第二对象候选区域的每个像素之间的重叠点上的像素; （S1500）将结果图像转换为分割二进制区域，将最大二进制区域设置为对象区域，其他区域设置为噪声并移除; （S1600）创建与对象区域的每个像素协调匹配的像素作为对象块
-
公开(公告)号：KR101271694B1
公开(公告)日：2013-06-05
申请号：KR1020120002509
申请日：2012-01-09
Applicant: 전남대학교산학협력단
IPC: G06F19/00 , G06F17/10 , A61B5/0476
CPC classification number: A61B5/0476 , G06Q50/22
Abstract: PURPOSE: A system for replacing continuous missing value of time series data and a method thereof are provided to guarantee the accuracy of replacement and to replace and detect a long-interval missing value by using a kalman filter-based linear dynamic system. CONSTITUTION: A concealment variable generating unit(100) generates a concealment variable including continuous missing value pattern features by considering a correlation between time series data including the missing value. A time series data replacing unit(200) replaces new time series data for old time series data by using the concealment variable. A parameter updating unit(300) updates an old parameter into a new parameter by using the concealment variable and the new time series data. A parameter comparing unit(400) compares the old parameter with the new parameter to determine the repetition of parameter update. [Reference numerals] (100) Concealment variable generating unit; (110) Correlation modeling module; (120) Temporal continuity modeling module; (200) Time series data replacing unit; (300) Parameter updating unit; (400) Parameter comparing unit
Abstract translation: 目的：提供一种用于替代时间序列数据的连续缺失值的系统及其方法，以保证更换的准确性，并通过使用基于卡尔曼滤波器的线性动态系统来代替和检测长间隔缺失值。 构成：隐藏变量生成单元（100）通过考虑包括缺失值的时间序列数据之间的相关性，生成包括连续缺失值图案特征的隐藏变量。 时间序列数据替换单元（200）通过使用隐藏变量来代替旧的时间序列数据的新的时间序列数据。 参数更新单元（300）通过使用隐藏变量和新的时间序列数据将旧参数更新为新的参数。 参数比较单元（400）将旧参数与新参数进行比较，以确定参数更新的重复。 （附图标记）（100）隐藏变量生成单元; （110）相关建模模块; （120）时间连续性建模模块; （200）时间序列数据替换单元; （300）参数更新单元; （400）参数比较单元
-
公开(公告)号：KR1020120041468A
公开(公告)日：2012-05-02
申请号：KR1020100102937
申请日：2010-10-21
Applicant: 전남대학교산학협력단
Abstract: PURPOSE: A system and a method for detecting interstitial lung diseases at a CT image are provided to automatically detect and quantify the initial interstitial lung disease using the CT image. CONSTITUTION: A lung dividing unit(10) divides and extracts a lung area from a CT image. A texture feature point extracting unit(20) extracts one or more texture features in an interest region. A classifying unit(30) classifies corresponding pixel into positivity or negativity with regard to interstitial lung diseases. A detection volume calculating unit(40) calculates the volume of all areas which are classified into positivity. A classification score calculating unit(50) calculates a volume ratio of a positive area to the whole area of a lung.
Abstract translation: 目的：提供一种用于CT图像检测间质性肺疾病的系统和方法，以使用CT图像自动检测和量化初始间质性肺病。 构成：肺分裂单元（10）从CT图像中分离并提取肺部区域。 纹理特征点提取单元（20）提取兴趣区域中的一个或多个纹理特征。 分类单元（30）将相应像素分类为间质性肺疾病的阳性或阴性。 检测量计算单元（40）计算分类为阳性的所有区域的体积。 分类分数计算单元（50）计算正面积与肺的整个面积的体积比。
-
公开(公告)号：KR1020100092778A
公开(公告)日：2010-08-23
申请号：KR1020090012070
申请日：2009-02-13
Applicant: 삼성전자주식회사 , 전남대학교산학협력단
CPC classification number: G06K9/32 , G06K9/342 , G06K2009/363 , G06K2209/01
Abstract: PURPOSE: A method for revising distortion of character recognition is provided to normally recognize the characteristic area even if an image including characteristic area is photographed distortedly, thereby preventing decline of the recognition rate of the character recognition. CONSTITUTION: A control unit extracts character area from an image(S202). The control unit presumes the figure of upper side of the extracted character area(S203). The control unit presumes the figure of lower side of the extracted character area(S204). The control unit presumes the figure of the left/right sides of the extracted characteristic area(S205). The control unit presumes the figure(S206). The figure comprises the characteristic area in the minimum area. The control unit converts the characteristic area into rectangular figure through affine transform(S207).
Abstract translation: 目的：提供一种用于修改字符识别失真的方法，即使包含特征区域的图像被失真地拍摄，从而防止字符识别的识别率的下降，也可以正常识别特征区域。 构成：控制单元从图像中提取字符区域（S202）。 控制单元假设提取的字符区域的上侧的图形（S203）。 控制单元假设提取的字符区域的下侧的图形（S204）。 控制单元假设提取的特征区域的左/右侧的图形（S205）。 控制单元假定该图（S206）。 该图包括最小区域中的特征区域。 控制单元通过仿射变换将特征区域转换成矩形图（S207）。
-
-
Patent Agency Ranking
公开(公告)号：KR1020160144250A
公开(公告)日：2016-12-16
申请号：KR1020150080821
申请日：2015-06-08
Applicant: 주식회사 셀바스에이아이 , 전남대학교산학협력단
Abstract: 본발명은스트로크입력순서의복원방법및 장치에관한것으로서, 본발명에따른스트로크입력순서의복원방법은입력된스트로크를세선화하여스켈레톤그래프를생성하는단계, 스켈레톤그래프로부터노드및 세그먼트을추출하는단계, 동일한노드를공유하는인접세그먼트가이루는각도에기초하여인접세그먼트사이의이동에대응하는코스트를산출하는단계, 코스트의합이최소화되도록스켈레톤그래프의모든세그먼트를통과하는경로를탐색하는단계및 경로에기초하여스트로크의입력방향및 입력순서를판단하는단계를포함하고, 서로인접하는 2개의세그먼트를통과하기위해소비되는에너지의크기에대응하는코스트를산출함으로써, 스트로크를입력하기위해소비되는에너지가최소화되는경로를탐색할수 있다.
-
公开(公告)号：KR1020160087423A
公开(公告)日：2016-07-22
申请号：KR1020150005983
申请日：2015-01-13
Applicant: 전남대학교산학협력단
CPC classification number: G06K9/00355 , G06F3/017
Abstract: 전자기기에서의동작인식시스템및 방법이제공된다. 본발명의일 실시예에따른전자기기에서의동작인식시스템은, 복수개의전위계차센서를이용하여사용자의동작에따른동작신호를추출하는신호추출부; 칼만필터(Kalman Filter)를이용하여상기동작신호에포함된잡음을제거하는잡음제거부; PCA(Principle Component Analysis) 알고리즘을이용하여, 잡음이제거된상기동작신호의차원을축소시키는특징추출부; 및 DTW(Dynamic Time Warping) 알고리즘및 K-NN(K-Nearest Neighbors) 분류기를이용하여, 차원이축소된상기동작신호를인식하는동작인식부를포함한다.
Abstract translation: 提供了一种用于能够去除手势信号中的小噪声，平滑手势信号以及提高手势信号的识别率的电子装置的手势识别系统及其方法。 根据本发明的实施例，电子设备的手势识别系统包括：信号提取单元，其使用多个位错传感器从用户的手势中提取手势信号; 噪声去除单元，其使用卡尔曼滤波器去除所述手势信号中的噪声; 特征提取单元，其使用主成分分析（PCA）算法来减少从中去除噪声的手势信号的尺寸; 以及手势识别单元，其使用动态时间扭曲（DTW）算法和K-最近邻（KNN）分类器来识别具有减小尺寸的手势信号。
-
公开(公告)号：KR101384627B1
公开(公告)日：2014-04-11
申请号：KR1020120119574
申请日：2012-10-26
Applicant: 전남대학교산학협력단
IPC: G06T7/00
CPC classification number: G06K9/6261 , G06K9/40 , G06K9/4676 , G06K9/6223 , G06K9/6247
Abstract: The present invention relates to an automatic segmentation method of an object area in an image and, more specifically, to an automatic segmentation method of an object area in an image which quickly segments an object containing a flower from an image by a probability distribution estimation algorithm. According to an embodiment of the present invention, a time required for segmentation can be minimized as a mobile terminal automatically segments a target object and a background from an input image when the input image of flower or plant is obtained. [Reference numerals] (S1000) Step of converting an image format of input images; (S2000) Step of estimating a predetermined area estimated in which the candidate object is located in the input images as a candidate area; (S3000) Step of extracting each feature information to the candidate object and a background in the candidate area; (S4000) Step of dividing the images in the input image by using the feature information; (S5000) Step of removing the noise of the divided object n the input images
Abstract translation: 本发明涉及图像中的对象区域的自动分割方法，更具体地，涉及图像中的对象区域的自动分割方法，其通过概率分布估计算法从图像中快速地分割包含花朵的对象 。 根据本发明的实施例，当获取花或植物的输入图像时，移动终端可以最小化分割所需的时间，因为移动终端自动地从输入图像中分割目标对象和背景。 （参考数字）（S1000）转换输入图像的图像格式的步骤; （S2000）将所述候选对象所位于的预定区域估计为所述输入图像作为候选区域的步骤; （S3000）向所述候选对象提取每个特征信息和所述候选区域中的背景的步骤; （S4000）使用所述特征信息来分割输入图像中的图像的步骤; （S5000）去除分割对象在输入图像上的噪声的步骤
-
公开(公告)号：KR101296734B1
公开(公告)日：2013-08-20
申请号：KR1020110146905
申请日：2011-12-30
Applicant: 전남대학교산학협력단
IPC: G06T7/00
Abstract: 본 발명은 가우시안 혼합 모델 및 알지비 클러스터링을 이용한 오브젝트 분할방법에 관한 것으로, 구체적으로는 이미지 내에 꽃과 같이 불특정한 모양을 갖는 오브젝트가 있는 경우, 사용자가 별도의 조작이 없이도 자동으로 상기 오브젝트를 인식하고 자동으로 분할할 수 있는 가우시안 혼합 모델 및 알지비 클러스터링을 이용한 오브젝트 분할방법에 관한 것이다.
-
公开(公告)号：KR101281511B1
公开(公告)日：2013-07-03
申请号：KR1020120014646
申请日：2012-02-14
Applicant: 전남대학교산학협력단
CPC classification number: G06F19/10 , C12Q1/68 , G06T7/0012
Abstract: PURPOSE: A method for automatically analyzing a DNA fingerprint image and a system thereof are provided to divide and analyze the DNA fingerprint image into various small images when bending of a lane is generated, thereby accurately detecting the lane. CONSTITUTION: Image data of gel electrophoresis of polymerase chain reaction (PCR) is inputted and stored in a memory unit (120). When an analysis controller (100) reads the image data, an average lane width calculation unit (200) calculates average lane width for the read image data. A continuous area image processing unit (300) reads data which is calculated by the average lane width calculation unit; calculates data of a local maximum point among the image data; and removes a local maximum point which is wrongly calculated and detected. Lanes are detected by connecting local maximum points which the local maximum point, which is wrongly detected, is removed. [Reference numerals] (100) Analysis controller; (120) Memory unit; (200) Average lane width calculation unit; (210) Vertical projection profile processing unit; (220) K-means processing unit; (230) Lane width calculation unit; (300) Continuous area image processing unit; (310) Horizontal projection profile processing unit; (320) Image division processing unit; (330) Divided image vertical projection processing unit; (340) Local maximum point search unit; (350) Error local removal processing unit; (360) Lane configuration processing unit; (370) False lane removal processing unit; (400) Accuracy-reproductivity calculation unit
Abstract translation: 目的：提供一种自动分析DNA指纹图像的方法及其系统，用于在生成车道弯曲时将DNA指纹图像分割并分析成各种小图像，从而准确地检测车道。 构成：聚合酶链反应（PCR）的凝胶电泳图像数据被输入并存储在存储单元（120）中。 当分析控制器（100）读取图像数据时，平均车道宽度计算单元（200）计算读取的图像数据的平均车道宽度。 连续区域图像处理单元（300）读取由平均车道宽度计算单元计算的数据; 计算图像数据中的局部最大点的数据; 并删除错误计算和检测到的局部最大点。 通过连接本地最大点（错误检测到的局部最大点）被去除来检测车道。 （参考号）（100）分析控制器; （120）存储单元; （200）平均车道宽度计算单位; （210）垂直投影轮廓处理单元; （220）K-means处理单元; （230）车道宽度计算单位; （300）连续区域图像处理单元; （310）水平投影轮廓处理单元; （320）图像分割处理单元; （330）分割图像垂直投影处理单元; （340）本地最大点搜索单位; （350）错误本地删除处理单元; （360）车道配置处理单元; （370）虚假车道拆除处理单元; （400）精度 - 再现性计算单位
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.029 seconds)
