-
公开(公告)号:US20190251333A1
公开(公告)日:2019-08-15
申请号:US16392270
申请日:2019-04-23
Inventor: Hao Wang , Zhifeng Li , Xing Ji , Fan Jia , Yitong Wang
CPC classification number: G06K9/00228 , G06K9/00 , G06K9/00288 , G06K9/36 , G06K9/46 , G06K9/62 , G06K9/6256 , G06K9/6262 , G06K9/6284 , G06N3/02
Abstract: An object detection training method can include receiving a training sample set in a current iteration of an object detection training process over an object detection neural network. The training sample set can include first samples of a first class and second samples of a second class. A first center loss value of each of the first and second samples can be determined. The first center loss value can be a distance between an eigenvector of the respective sample and a center eigenvector of the first or second class which the respective sample belongs to. A second center loss value of the training sample set can be determined according to the first center loss values of the first and second samples. A first target loss value of the current iteration can be determined according to the second center loss value of the training sample set.
-
公开(公告)号:US20190246040A1
公开(公告)日:2019-08-08
申请号:US16234389
申请日:2018-12-27
Applicant: GoPro, Inc.
Inventor: David A. Newman
IPC: H04N5/232 , H04N5/265 , H04N19/85 , H04N19/44 , H04N19/186 , G06K9/36 , H04N19/117 , G06F3/0484 , G06T9/00 , H04N9/04 , H04N1/64 , H04N19/136
CPC classification number: H04N5/23293 , G06F3/0484 , G06K9/36 , G06T9/00 , H04N1/648 , H04N5/23245 , H04N5/265 , H04N9/045 , H04N19/117 , H04N19/136 , H04N19/186 , H04N19/44 , H04N19/85
Abstract: A method is described to greatly improve the efficiency of and reduce the complexity of image compression when using single-sensor color imagers for video acquisition. The method in addition allows for this new image compression type to be compatible with existing video processing tools, improving the workflow for film and television production.
-
公开(公告)号:US20190171901A9
公开(公告)日:2019-06-06
申请号:US13650413
申请日:2012-10-12
Applicant: BULL HN INFORMATION SYSTEMS, INC.
Inventor: David Lowell Bowne , Shahrom Kiani , Carlos Macia , Russell W. Guenthner
CPC classification number: G06K9/36 , G06K9/00973 , G06K2209/01
Abstract: A scanning camera upgrade adaptor system provides backwards compatibility when an existing scanning camera subsystem is replaced or upgraded in automated sorting equipment with a newer camera having a different data format. The adaptor system allows sorting equipment such as mail sorting equipment to be upgraded or repaired with a new camera while providing compatibility and optional fallback to a previous mode of operation of the existing equipment. The upgrade system enables legacy equipment and newly added sorting/processing equipment to be utilized in conjunction, while reducing cost of upgrade and necessity for completely new equipment as desirable features are added.
-
公开(公告)号:US20190167104A9
公开(公告)日:2019-06-06
申请号:US15330993
申请日:2016-12-09
Applicant: Meghana Kambham
Inventor: Meghana Kambham
IPC: A61B5/00 , G16H10/60 , G16H50/20 , A61B1/05 , A61B7/04 , A61B5/1455 , A61B5/145 , A61B5/0428 , A61B5/0205
CPC classification number: A61B5/0022 , A61B1/05 , A61B5/0077 , A61B5/0205 , A61B5/021 , A61B5/0402 , A61B5/0428 , A61B5/14535 , A61B5/14551 , A61B5/4833 , A61B5/4848 , A61B5/7282 , A61B5/7445 , A61B7/04 , A61B2505/07 , A61B2560/0462 , A61B2562/22 , G06K9/209 , G06K9/344 , G06K9/36 , G06K9/78 , G06K2209/01 , G09B21/003 , G16H10/60 , G16H40/67 , G16H50/20
Abstract: Implementations described herein disclose a method for direct screening and monitoring of health parameters of multiple individual subjects in a remote location with easy access and periodic visits by such multiple individual subjects, where such remote location is not a healthcare facility. Furthermore, an apparatus disclosed herein enables remote health monitoring of individual subjects including children outside the confines of a healthcare facility.
-
公开(公告)号:US20190042817A1
公开(公告)日:2019-02-07
申请号:US16151457
申请日:2018-10-04
Applicant: International Business Machines Corporation
Inventor: Varun Bhagwan , Timothy Liu , Justin Ormont , Heather Underwood
CPC classification number: G06K7/146 , G06K9/00255 , G06K9/36 , G06K9/46 , G06K2009/363 , G06K2209/01 , G06T3/0056 , G06T3/0068 , G06T5/003 , G06T2207/10004 , G06T2207/10024
Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.
-
公开(公告)号:US20180181796A1
公开(公告)日:2018-06-28
申请号:US15842190
申请日:2017-12-14
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Biao WANG , Bing YU , Chang Kyu CHOI , Deheng QIAN , Jae-Joon HAN , Jingtao XU , Yaozu AN
CPC classification number: G06K9/00288 , G06K9/00228 , G06K9/036 , G06K9/36 , G06K9/52 , G06K9/627 , G06T7/0002 , G06T2207/20081 , G06T2207/20084 , G06T2207/30168 , G06T2207/30201
Abstract: An image processing apparatus, includes an image classifier configured to determine whether an input image is a low-quality image or a high-quality image; and an image evaluator configured to determine a first predetermined number of clearest images from a plurality of low-quality images determined by the image classifier.
-
7.
公开(公告)号:US20180011084A1
公开(公告)日:2018-01-11
申请号:US15544409
申请日:2016-01-06
Applicant: BAYER AKTIENGESELLSCHAFT
Inventor: Franco FOIS , Michael HARNAU , Klaus OCHMANN
CPC classification number: G01N33/5085 , G01N21/253 , G01N21/255 , G01N2201/0638 , G01N2333/4353 , G06K9/36 , G06T5/20 , G06T7/0012 , G06T7/254 , G06T2207/30024
Abstract: The invention relates to a device (1) and a method for determining the action of active ingredients on nematodes and other organisms in aqueous tests. The device (1) according to the invention comprises a holder (13) for a cell culture plate (30) having multiple wells (31) in which the nematodes can be filled with the active ingredients, said cell culture plate (30) having a bottom side (33), a top side (32) and also side walls extending between bottom side (33) and top side (32), a camera (11) which is used to record images of preferably the bottom side (33) of the cell culture plate (30), a lighting mechanism (14) having at least a first light source (15) which illuminates the cell culture plate (30), there being arranged between the first light source (15) and a first side wall (34) of the cell culture plate (30) in the installed state a first optical unit which directs the light of the first light source (15) through the first side wall (34) in the direction of the bottom side (33) of the cell culture plate (30). The method according to the invention makes it possible to simultaneously investigate many active ingredients within a very short time.
-
公开(公告)号:US09811753B2
公开(公告)日:2017-11-07
申请号:US14667495
申请日:2015-03-24
Applicant: FotoNation Cayman Limited
Inventor: Kartik Venkataraman , Semyon Nisenzon , Dan Lelescu
IPC: G06K9/36 , G06T9/00 , G06T9/20 , H04N19/597 , H04N13/00 , H04N13/02 , H04N19/625 , H04N19/136 , G06T3/40 , H04N19/85 , G06T15/08 , G06T7/50
CPC classification number: G06K9/36 , G06T3/4007 , G06T3/4053 , G06T7/50 , G06T7/596 , G06T9/00 , G06T9/20 , G06T15/08 , G06T2207/10052 , H04N13/128 , H04N13/161 , H04N13/243 , H04N13/271 , H04N19/136 , H04N19/597 , H04N19/625 , H04N19/85 , H04N2013/0081
Abstract: Systems and methods configured to store images synthesized from light field image data and metadata describing the images in electronic files and render images using the stored image and the metadata in accordance with embodiments of the invention are disclosed. One embodiment includes a processor and memory containing an encoding application and light field image data, where the light field image data comprises a plurality of low resolution images of a scene captured from different viewpoints. In addition, the encoding application configures the processor to synthesize a higher resolution image of the scene from a reference viewpoint using the low resolution images, where synthesizing the higher resolution image involves creating a depth map that specifies depths from the reference viewpoint for pixels in the higher resolution image; encode the higher resolution image; and create a light field image file including the encoded image and metadata including the depth map.
-
公开(公告)号:US09710910B2
公开(公告)日:2017-07-18
申请号:US14753394
申请日:2015-06-29
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sunkwon Kim , Jungwoo Chang , Won-chul Bang
CPC classification number: G06K9/6262 , G06K9/36 , G06K9/46 , G06K9/6203 , G06K9/6263 , G06K9/66 , G06T7/0012 , G06T7/32 , G06T7/33 , G06T7/35 , G06T2207/10028 , G06T2207/10072 , G06T2207/10132 , G06T2207/20084 , G06T2207/20221
Abstract: There is provided an image registration device and an image registration method. The device includes: a feature extractor configured to extract, from a first image, a first feature group and to extract, from a second image, a second feature group; a feature converter configured to convert, using a converted neural network in which a correlation between features is learned, the extracted second feature group to correspond to the extracted first feature group, to obtain a converted group; and a register configured to register the first image and the second image based on the converted group and the extracted first feature group.
-
公开(公告)号:US09697592B1
公开(公告)日:2017-07-04
申请号:US14984466
申请日:2015-12-30
Applicant: TCL RESEARCH AMERICA INC.
Inventor: Qiqin Dai , Xiaobo Ren , Haohong Wang
CPC classification number: G06T5/009 , G06K9/00979 , G06K9/36 , G06K9/4671 , G06K9/6214 , G06K9/6222 , G06K9/6223 , G06T3/0093 , G06T5/007 , G06T2207/20028 , G06T2207/20208 , G06T2207/20221
Abstract: The present invention provides a method for converting a low dynamic range (LDR) image to a high dynamic range (HDR) image, including obtaining an input LDR image; and in an HDR image database, selecting one or more HDR images that match the input LDR image as candidate images. Further, the candidate images are warped according to a spatial correspondence between the candidate images and the input LDR image. The input LDR image is decomposed to an illumination component and a texture component. The illumination component and the texture component are reconstructed respectively based on the warped candidate images. The reconstructed illumination component and the reconstructed texture component are combined to produce an output HDR image.
-
-
-
-
-
-
-
-
-