公开(公告)号：US20150003698A1

公开(公告)日：2015-01-01

申请号：US14283077

申请日：2014-05-20

Applicant: Digimarc Corporation

Inventor： Bruce L. Davis ,  Tony F. Rodriguez ,  Alastair M. Reed ,  John Stach ,  Geoffrey B. Rhoads ,  William Y. Conwell ,  Shankar Thagadur Shivappa ,  Ravi K. Sharma ,  Richard F. Gibson

IPC: G06T7/00 ,  G06T5/40 ,  G06T7/40

CPC classification number: A61B5/441 ,  A61B5/0075 ,  A61B5/0077 ,  A61B5/1032 ,  A61B5/1034 ,  A61B5/444 ,  A61B5/445 ,  A61B5/4806 ,  A61B5/6898 ,  A61B5/7246 ,  A61B5/7278 ,  A61B5/7282 ,  A61B5/7425 ,  A61B5/743 ,  A61B5/7485 ,  A61B2576/02 ,  G06F16/245 ,  G06F16/248 ,  G06F19/00 ,  G06F19/3418 ,  G06T5/40 ,  G06T7/0012 ,  G06T2207/30088 ,  G10L19/018 ,  G16H40/67 ,  G16H50/20 ,  G16H50/70 ,  Y02A90/26

Abstract: Computer-aided dermatological analysis requires accurate color data. Color accuracy can be improved by compensating captured imagery based on reference color data. In one particular arrangement, reference color data is acquired from blood. In another arrangement, imagery captured from a banknote is used as reference data. A great variety of other features and arrangements are also detailed.

Abstract translation: 计算机辅助皮肤病学分析需要准确的色彩数据。 可以通过基于参考颜色数据补偿捕获的图像来提高颜色精度。 在一种特定布置中，从血液获取参考颜色数据。 在另一种布置中，将从钞票拍摄的图像用作参考数据。 还详细介绍了各种各样的其他功能和安排。

公开(公告)号：US20140378810A1

公开(公告)日：2014-12-25

申请号：US14276578

申请日：2014-05-13

Applicant: Digimarc Corporation

Inventor： Bruce L. Davis ,  Tony F. Rodriguez ,  Alastair M. Reed ,  John Stach ,  Geoffrey B. Rhoads ,  William Y. Conwell ,  Shankar Thagadur Shivappa ,  Ravi K. Sharma ,  Richard F. Gibson

IPC: A61B5/00

CPC classification number: A61B5/441 ,  A61B5/0075 ,  A61B5/0077 ,  A61B5/1032 ,  A61B5/1034 ,  A61B5/444 ,  A61B5/445 ,  A61B5/4806 ,  A61B5/6898 ,  A61B5/7246 ,  A61B5/7278 ,  A61B5/7282 ,  A61B5/7425 ,  A61B5/743 ,  A61B5/7485 ,  A61B2576/02 ,  G06F16/245 ,  G06F16/248 ,  G06F19/00 ,  G06F19/3418 ,  G06T5/40 ,  G06T7/0012 ,  G06T2207/30088 ,  G10L19/018 ,  G16H40/67 ,  G16H50/20 ,  G16H50/70 ,  Y02A90/26

Abstract: The availability of high quality imagers on smartphones and other portable devices facilitates creation of a large, crowd-sourced, image reference library that depicts skin rashes and other dermatological conditions. Some of the images are uploaded with, or later annotated with, associated diagnoses or other information (e.g., “this rash went away when I stopped drinking milk”). A user uploads a new image of an unknown skin condition to the library. Image analysis techniques are employed to identify salient similarities between features of the uploaded image, and features of images in this reference library. Given the large dataset, statistically relevant correlations emerge that identify to the user certain diagnoses that may be considered, other diagnoses that may likely be ruled-out, and/or anecdotal information about similar skin conditions from other users. Similar arrangements can employ audio and/or other physiologically-derived signals. A great variety of other features and arrangements are also detailed.

Abstract translation: 在智能手机和其他便携式设备上提供高质量的成像器有助于创建一个大型，大量来源的图像参考库，描述皮肤疹和其他皮肤病学条件。 一些图像与相关联的诊断或其他信息（例如，“当我停止喝牛奶时这种皮疹消失”）上传或稍后注释。 用户将未知皮肤状况的新图像上传到库。 图像分析技术用于识别上传图像的特征与本参考库中图像的特征之间的突出相似性。 鉴于大数据集，出现统计学上相关的相关性，以向用户识别可能被考虑的某些诊断，可能被排除的其他诊断和/或来自其他用户的类似皮肤状况的轶事信息。 类似的布置可以使用音频和/或其他生理来源的信号。 还详细介绍了各种各样的其他功能和安排。

公开(公告)号：US20140071268A1

公开(公告)日：2014-03-13

申请号：US13969422

申请日：2013-08-16

Applicant: Digimarc Corporation

Inventor： John D. Lord ,  Alastair M. Reed

IPC: G01B11/00 ,  H04N5/225

CPC classification number: G01B11/002 ,  G06T7/74 ,  G06T2207/10048 ,  H04N5/2256

Abstract: In an illustrative embodiment, the free space attenuation of illumination with distance, according to a square law relationship, is used to estimate the distance between a light source and two or more different areas on the surface of a product package. By reference to these distance estimates, the angular pose of the product package is determined. Plural frames of imagery, captured both with and without illumination from the light source, can be processed to mitigate the effects of ambient lighting.

Abstract translation: 在说明性实施例中，根据平方律关系，使用距离的照明的自由空间衰减用于估计光源与产品包装表面上的两个或更多个不同区域之间的距离。 通过参考这些距离估计，确定产品包的角姿势。 可以处理多个具有和不具有来自光源的照明的图像，以减轻环境照明的影响。

公开(公告)号：US20140037131A1

公开(公告)日：2014-02-06

申请号：US13936766

申请日：2013-07-08

Applicant: Digimarc Corporation

Inventor： Alastair M. Reed ,  Ravi K. Sharma ,  Tony F. Rodriguez

IPC: G06T1/00

CPC classification number: G06T1/005 ,  G06T1/0021 ,  G06T11/001 ,  G06T2201/0083 ,  H04N1/32144 ,  H04N1/32267 ,  H04N1/32309 ,  H04N1/6005 ,  H04N1/6008 ,  H04N2201/3228 ,  H04N2201/3233 ,  H04N2201/327

Abstract: This patent document relates generally to steganography and digital watermarking. One claim recites, in a watermark encoder, a method of encoding auxiliary information in an image or video comprising: using a programmed electronic processor, computing a change in an attribute of an image or video sample to encode auxiliary information in the image or video; and changing color values of the image or video sample to effect the change in the attribute, in which changes to color values are determined based at least in part on both: i) visibility of the changes, and ii) anticipated watermark detection. Of course, other claims are provided too.

Abstract translation: 该专利文献一般涉及隐写术和数字水印。 一个权利要求在水印编码器中叙述了在图像或视频中对辅助信息进行编码的方法，包括：使用编程的电子处理器，计算图像或视频样本的属性的改变以对图像或视频中的辅助信息进行编码; 以及改变图像或视频样本的颜色值以实现属性的变化，其中至少部分地基于以下两者来确定对颜色值的改变：i）改变的可视性，以及ii）预期的水印检测。 当然，也提供其他索赔。

公开(公告)号：US20130336522A1

公开(公告)日：2013-12-19

申请号：US13971607

申请日：2013-08-20

Applicant: Digimarc Corporation

Inventor： Alastair M. Reed ,  Ravi K. Sharma ,  Tony F. Rodriguez

IPC: G06T1/00

CPC classification number: G06T1/005 ,  G06T1/0021 ,  G06T11/001 ,  G06T2201/0083 ,  H04N1/32144 ,  H04N1/32267 ,  H04N1/32309 ,  H04N1/6005 ,  H04N1/6008 ,  H04N2201/3228 ,  H04N2201/3233 ,  H04N2201/327

Abstract: This patent document relates generally to steganography and digital watermarking. One claim recites, in a watermark encoder, a method of encoding auxiliary information in an image or video comprising: using a programmed electronic processor, computing a change in an attribute of an image or video sample to encode auxiliary information in the image or video; and changing color values of the image or video sample to effect the change in the attribute, in which changes to color values are determined based at least in part on both: i) visibility of the changes, and ii) anticipated watermark detection. Of course, other claims are provided too.

Abstract translation: 该专利文献一般涉及隐写术和数字水印。 一个权利要求在水印编码器中叙述了在图像或视频中对辅助信息进行编码的方法，包括：使用编程的电子处理器，计算图像或视频样本的属性的改变以对图像或视频中的辅助信息进行编码; 以及改变所述图像或视频样本的颜色值以实现所述属性的改变，其中至少部分地基于以下两者来确定对颜色值的改变：i）所述改变的可视性，以及ii）预期的水印检测。 当然，也提供其他索赔。

公开(公告)号：US20130223673A1

公开(公告)日：2013-08-29

申请号：US13750752

申请日：2013-01-25

Applicant: Digimarc Corporation

Inventor： Bruce L. Davis ,  Tony F. Rodriguez ,  Geoffrey B. Rhoads ,  John D. Lord ,  Alastair M. Reed ,  Eric D. Evans ,  Rebecca L. Gerlach ,  Yang Bai ,  John Stach ,  Tomas Filler ,  Marc G. Footen ,  Sean Calhoon

IPC: G06K9/78 ,  G06K7/14 ,  G06Q30/00

CPC classification number: G06K9/78 ,  G06F3/147 ,  G06K7/10861 ,  G06K7/1456 ,  G06K2017/0051 ,  G06K2017/0093 ,  G06Q10/08 ,  G06Q10/087 ,  G06Q20/201 ,  G06Q20/208 ,  G06Q30/00 ,  G06Q30/0601 ,  G07G1/0045

Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.

Abstract translation: 在一些安排中，产品包装在其大部分程度上以数字水印方式，以促进零售结算处的高通量物品识别。 可以通过传统或全光照相机拍摄的图像（例如，通过GPU）来处理几个不同的透视变换视图 - 进一步最小化手动重新定位项目以进行识别的需要。 产品包装中的皱纹和其他变形可以光学感测，允许这些表面几乎变平，以帮助识别。 物品堆可以3D建模，并将其虚拟分割成几何图元，以帮助识别，并发现隐藏物品的位置。 可以使用其他数据（例如，包括来自在通道中的传感器的数据，架子和推车以及关于视觉显着性的线索的凝视跟踪）来评估关于物品的识别假设。 还详细介绍了各种各样的其他功能和安排。