公开(公告)号：US20100278426A1

公开(公告)日：2010-11-04

申请号：US12735093

申请日：2008-12-12

申请人： Robinson Piramuthu

发明人： Robinson Piramuthu

IPC分类号： G06K9/54

CPC分类号： G06K9/00234 ,  G06T7/11 ,  G06T2207/30196 ,  G06T2207/30201

摘要： A method of labeling pixels in an image in which pixels in the image that represent human skin of one or more people are detected and one or more regions in the image are identified, where each region in the one or more regions includes all or a portion of a human face of a person in the one or people in the image. Pixels that represent each face in the image are identified using the pixels that represent skin and the regions that include faces of the people, thereby identifying a position of each face in the image. From this, a face mask for each face and a rough body map corresponding to each face is determined using the positions of the identified faces. Further still, a torso map corresponding to each face is determined using determined face positions. Then, the extracted face masks and the torso maps are used to refine a skin map. A person or people map is determined using the skin map and the rough body map.

摘要翻译： 一种标记图像中的像素的方法，其中检测到图像中表示一个或多个人的皮肤的像素，并且识别图像中的一个或多个区域，其中一个或多个区域中的每个区域包括全部或部分 一个人的人脸在一个或一个人的形象。 使用表示皮肤的像素和包括人脸的区域来识别代表图像中每个面部的像素，从而识别图像中每个面部的位置。 由此，使用所识别的面部的位置来确定每个面部的面罩和对应于每个面部的粗糙身体贴图。 此外，使用确定的脸部位置来确定对应于每个脸部的躯干图。 然后，提取的面罩和躯干图用于细化皮肤图。 使用皮肤图和粗体图确定人物或人物图。

公开(公告)号：US20090148041A1

公开(公告)日：2009-06-11

申请号：US12333293

申请日：2008-12-11

申请人： Robinson Piramuthu

发明人： Robinson Piramuthu

IPC分类号： G06K9/34

CPC分类号： G06T7/162 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10024

摘要： An initial figure mask estimation of an image is generated using a figure ground segmentation system, thereby initially assigning each pixel in the image with a first attribute value or a second attribute value. A JigCut region segmentation of the image is generated. The figure mask estimation is processed with the JigCut region segmentation by (i) classifying the pixels of the image in each respective JigCut region in the JigCut region segmentation with the first attribute value when a predetermined number or a predetermined percentage of the pixels within the respective JigCut region have been initially assigned the first attribute value by the initial figure mask estimation and (ii) classifying the pixels of the image in each respective JigCut region in the JigCut region segmentation with the second attribute value otherwise.

摘要翻译： 使用图形地面分割系统生成图像的初始图形掩模估计，从而最初以图像中的每个像素分配第一属性值或第二属性值。 生成图像的JigCut区域分割。 利用JigCut区域分割对图形掩模估计进行处理，（i）当相应的各个像素的预定数量或预定百分比的像素在预定数量或预定百分比的像素内时，使用第一属性值对在JigCut区域分割中的每个相应JigCut区域中的图像的像素进行分类 最初通过初始图形掩模估计分配JigCut区域，并且（ii）否则在第二属性值中对JigCut区域分割中的每个相应JigCut区域中的图像的像素进行分类。

公开(公告)号：US07394534B1

公开(公告)日：2008-07-01

申请号：US10717403

申请日：2003-11-19

申请人： Patrick Y. Huet ,  Robinson Piramuthu ,  Martin Plihal ,  Christopher W. Lee ,  Cho H. Teh ,  Yan Xiong

发明人： Patrick Y. Huet ,  Robinson Piramuthu ,  Martin Plihal ,  Christopher W. Lee ,  Cho H. Teh ,  Yan Xiong

IPC分类号： G01N21/00

CPC分类号： G01N21/8851 ,  G01N21/9501 ,  G01N2021/8854 ,  G01N2021/8864 ,  G06T7/0004 ,  G06T2207/30148

摘要： A method for analyzing defect information on a substrate, including logically dividing the substrate into zones, and detecting defects on the substrate to produce the defect information. The defect information from the substrate is analyzed on a zone by zone basis to produce defect level classifications for the defects within each zone. The zonal defect level classifications are analyzed according to at least one analysis method. The defect level classifications are preferably selected from a group of defect level classifications that is specified by a recipe. Preferably, the at least one analysis method includes at least one of zonal defect distribution, automatic defect classification, spatial signature analysis, and excursion detection. The defect level classifications preferably include at least one of individual defect, defect cluster, and spatial signature analysis signature. In one embodiment the defect information is logically divided into configurable zones after the defects on the substrate have been detected.

摘要翻译： 一种用于分析衬底上的缺陷信息的方法，包括将衬底逻辑划分为区域，以及检测衬底上的缺陷以产生缺陷信息。 在逐个区域的基础上分析来自基板的缺陷信息，以产生每个区域内的缺陷的缺陷水平分类。 根据至少一种分析方法分析区域缺陷水平分类。 缺陷级分类优选地从由食谱指定的一组缺陷级别分类中选择。 优选地，所述至少一个分析方法包括区域缺陷分布，自动缺陷分类，空间签名分析和偏移检测中的至少一个。 缺陷级分类优选地包括个体缺陷，缺陷簇和空间签名分析签名中的至少一个。 在一个实施例中，在检测到衬底上的缺陷之后，将缺陷信息在逻辑上划分为可配置区域。

公开(公告)号：US07006886B1

公开(公告)日：2006-02-28

申请号：US10755546

申请日：2004-01-12

申请人： Patrick Y. Huet ,  Robinson Piramuthu ,  Martin Plihal

发明人： Patrick Y. Huet ,  Robinson Piramuthu ,  Martin Plihal

IPC分类号： G06F19/00

CPC分类号： H01L21/67288

摘要： A method for analyzing defects on a substrate, including inspecting the substrate to detect the defects, identifying the defects by location, analyzing the defects to detect extended objects, and analyzing the extended objects for repetition across the substrate. Thus, the present invention extends beyond the present analysis methods, by analyzing the extended objects for repetition across the substrate. In this manner, correlation with processing problems can be more readily detected, in cases where the individual defects themselves, of which the extended objects are formed, do not appear to have repeating properties.

摘要翻译： 一种用于分析衬底上的缺陷的方法，包括检查衬底以检测缺陷，通过位置识别缺陷，分析缺陷以检测扩展对象，以及分析扩展对象以重复穿过衬底。 因此，本发明通过分析跨越衬底的重复的扩展对象来延伸超出本分析方法。 以这种方式，在形成扩展对象的各个缺陷本身似乎不具有重复性质的情况下，可以更容易地检测与处理问题的相关性。