Abstract:
본 발명은 Block Clustering 알고리즘을 이용하여 객체를 자동으로 배경으로부터 분할하는 것으로, 본 발명에 의해서 종래의 GrabCut 실시에서 사용자에 의해 객체에 대한 정보를 제공하는 단점을 보완하여 자동화시킴으로써 사용자의 편의성 및 효율성을 증대시키는 Block Clustering 을 이용한 자동객체분할방법에 관한 것이다. 이와 같은 본 발명의 특징은 배경과 객체의 분할정보를 포함한 영상정보에 대해서 객체의 관심영역을 추정하는 객체관심영역추정단계를 포함하는데, 상기 객체관심영역추정단계는, 영상의 군집분산정보를 분석하여 분산영역의 크기에 따라 군집을 분별하고, 영상을 소정 개수의 블록으로 분할하고 개별 블록 내의 객체면적과 배경면적, 그리고 블록의 색상평균값에 따라서 객체군집과 배경군집으로 판별하는 것을 특징으로 한다.
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:
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.
Abstract:
The present invention relates to an automatic object segmentation method for automatically segmenting an object from a background using a block clustering algorithm. The automatic object segmentation method is capable of improving user′s convenience and efficiency by automation to supplement the weakness of providing information on the object by a user in the existing GrabCut implementation. The automatic object segmentation method of the present invention comprises an object interest region estimation step of estimating an interest region of an object for image information including segmentation information of a background and the object. In the object interest region estimation step, cluster dispersion information of an image is analyzed to distinguish the cluster according to the size of a dispersion region, and the image is segmented into the predetermined number of blocks and is determined as an object cluster and a background cluster depending on the object area and the background area within an individual block, and a color mean value of the block.
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