-
公开(公告)号：US10025977B2
公开(公告)日：2018-07-17
申请号：US14878837
申请日：2015-10-08
Applicant: MORPHO
Inventor： Alain Rouh , Jean Beaudet , Laurent Rostaing
Abstract: This invention relates to a method for identifying a sign on an image of a document that can be deformed comprising: an acquisition (E1) of said digital image of said document; a determination (E2) in the acquired image of at least one candidate sign region using an image segmentation algorithm, for each candidate sign region, a calculation (E3) of a signature comprising a piece of information concerning the location in the acquired image of said candidate sign region and a region descriptor concerning the local characteristics of the image in said region, an identification (E4) of a sign on the image of the document using the calculated signatures comprising jointly a comparison (E41) of the calculated signatures with reference signatures concerning sign regions of document models, said comparison being carried out according to a geometric deformation model of said document, and an estimation (E42) according to said comparison of said geometric deformation model.
-
公开(公告)号：US10262398B2
公开(公告)日：2019-04-16
申请号：US15080176
申请日：2016-03-24
Applicant: MORPHO
Inventor： Alain Rouh , Jean Beaudet , Jeremy Dura , Laurent Rostaing
Abstract: An image correction method includes: estimating a 3D model of an object as when an imaging device takes an image of the object; calculating the light intensity of each point of a simulated image as it would be taken by the imaging device, using the estimated 3D model of the object, a model of illumination of the object illuminated by a lighting system that illuminates the object, a model of reflection on a surface of the object, and a model of the imaging device, to obtain a simulated image of the object; and correcting the taken image by modifying the light intensity of each point on the taken image or on at least one area of interest of the taken image, according to the light intensity of the corresponding point in the simulated image or the respective light intensities of points adjacent to the corresponding point in the simulated image.
-
公开(公告)号：US20160104039A1
公开(公告)日：2016-04-14
申请号：US14878837
申请日：2015-10-08
Applicant: MORPHO
Inventor： Alain Rouh , Jean Beaudet , Laurent Rostaing
CPC classification number: G06K9/00442 , G06K9/00463 , G06K9/2063 , G06K9/3275 , G06K9/36 , G06K9/6202 , G06K9/6215 , G06K2009/363 , G06T7/11 , G06T7/60
Abstract: This invention relates to a method for identifying a sign on an image of a document that can be deformed comprising:an acquisition (E1) of said digital image of said document;a determination (E2) in the acquired image of at least one candidate sign region using an image segmentation algorithm,for each candidate sign region, a calculation (E3) of a signature comprising a piece of information concerning the location in the acquired image of said candidate sign region and a region descriptor concerning the local characteristics of the image in said region,an identification (E4) of a sign on the image of the document using the calculated signatures comprising jointly a comparison (E41) of the calculated signatures with reference signatures concerning sign regions of document models, said comparison being carried out according to a geometric deformation model of said document, and an estimation (E42) according to said comparison of said geometric deformation model.
Abstract translation: 本发明涉及一种用于识别能够变形的文档的图像上的符号的方法，包括：所述文档的所述数字图像的获取（E1）; 对于每个候选符号区域，使用图像分割算法获取的至少一个候选符号区域的图像的确定（E2）包括关于所获取的所述图像的图像中的位置的一条信息的签名的计算（E3） 候选符号区域和关于所述区域中的图像的局部特征的区域描述符，使用所计算的签名的文档的图像上的符号的标识（E4），包括计算出的签名与参考签名的比较（E41） 关于文件模型的符号区域，所述比较是根据所述文档的几何变形模型进行的，以及根据所述几何变形模型的所述比较的估计（E42）。
-
公开(公告)号：US09934445B2
公开(公告)日：2018-04-03
申请号：US15030993
申请日：2014-11-12
Applicant: MORPHO
Inventor： Alain Rouh , Jean Beaudet , Jérémy Dura , Laurent Rostaing
CPC classification number: G06K9/2027 , G06K9/00201
Abstract: Provided is a method/system for taking, by an imaging device, one or more images of an object or a part of an object presented at a distance in front of the imaging device, the object being illuminated by a lighting system. The method/system may include: estimating a 3D model of the object as it will be at a predetermined time when taking the image by the imaging device; simulating, using the estimated 3D model, the illumination of the object as it will be at said time to obtain estimated images of the object in respectively a plurality of envisaged lighting modes of the lighting system; selecting a lighting mode of the lighting system from the estimated images; and controlling the lighting system to be in the selected lighting mode; and controlling the imaging device, at the time of the taking of the image of the object, to effect the taking.
-
-
-
Search Results
4
records
(took 0.007 seconds)
