-
公开(公告)号：US20180122101A1
公开(公告)日：2018-05-03
申请号：US15337107
申请日：2016-10-28
申请人： Intel Corporation
CPC分类号： G06T9/00 , G06K9/00986 , G06K9/36 , G06T1/20 , G06T1/60
摘要： Methods and apparatus relating to techniques for compiler-based instruction scorecarding. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to determine whether a pixel block encoded in YCoCg format is suitable for compression, and in response to a determination that the pixel block is suitable for compression, to apply an encoding transform to the pixel block to generate an encoded YCoCg data set for the pixel block and apply a compression algorithm to the encoded YCoCg data set. Other embodiments are also disclosed and claimed.
-
公开(公告)号：US09940724B2
公开(公告)日：2018-04-10
申请号：US15263761
申请日：2016-09-13
发明人： Bin Jia , Kui Liu , Sixiao Wei , Erik Blasch , Carolyn Sheaff , Haibin Ling , Genshe Chen
CPC分类号： G06K9/4642 , G06K9/0063 , G06K9/00986 , G06K9/38 , G06K9/4671 , G06K9/6211 , G06K9/6269 , G06T3/4038 , G06T7/33 , G06T2207/10032 , G06T2207/30184 , G06T2207/30236
摘要： In accordance with various embodiments of the disclosed subject matter, a method and a system for detecting multiple objects from real-time images are provided. The method comprises: performing, using a CPU host, an image segmentation process to divide real-time input images into a plurality of image partitions; performing, by multiple GPUs, a fast block-wise registration process, a mark setting process, a background generation process, a foreground generation process based on a Hyper-Q computation infrastructure, and a support vector machine classification process; and generating, by the CPU host, visualization classification images.
-
公开(公告)号：US20180095877A1
公开(公告)日：2018-04-05
申请号：US15281288
申请日：2016-09-30
申请人： INTEL CORPORATION
发明人： Aleksandar Beric , Zoran Zivkovic
IPC分类号： G06F12/0802 , G06K9/00
CPC分类号： G06F12/0802 , G06F2212/301 , G06K9/00 , G06K9/00221 , G06K9/00986
摘要： An example apparatus for processing scattered data includes an address buffer to receive a plurality of vector addresses corresponding to input vector data comprising scattered samples to be processed. The apparatus also includes a multi-bank memory to receive the input vector data and send output vector data. The apparatus further includes a memory controller comprising an address scheduler to assign an address to each bank of the multi-bank memory.
-
公开(公告)号：US20180082138A1
公开(公告)日：2018-03-22
申请号：US15447120
申请日：2017-03-02
发明人： Yuichi ITO
CPC分类号： G06K9/03 , G06F11/07 , G06K9/00986 , G06K9/36 , G06K9/4642 , G06K9/4652 , G06K9/6201 , G06K9/64
摘要： According to one embodiment, a semiconductor device for processing image data of an image includes an image processing circuit comprising circuit elements configured to process the image data and output first image data, a processor configured to process the image data using arithmetic processing software and output second image data, and a comparison unit configured to compare the first image data and the second image data and output a detection signal indicating whether or not the first image data and the second image data match each other.
-
15.发明授权公开(公告)号：US09842253B2
公开(公告)日：2017-12-12
申请号：US15597281
申请日：2017-05-17
申请人： RetailMeNot, Inc.
发明人： Shaun F. Dubuque
CPC分类号： G06K9/00536 , G06K9/00671 , G06K9/00979 , G06K9/00986 , G06K9/3258 , G06K9/46 , G06K9/4614 , G06K9/6212 , G06K9/6227 , G06K9/6267 , G06K9/6288 , G06Q30/0207 , G06Q30/06 , H04W4/02
摘要： Provided is a process including: determining that a mobile computing device has crossed a geofence associated with a merchant store; sending, to a remote classifier server, a request for object-recognition classifiers for objects in the merchant store; receiving a set of object-recognition classifiers; receiving with the mobile computing device from user a request to search for offers; capturing an image with a camera of the mobile computing device; receiving one or more wireless beacon identifiers with the mobile computing device; based on the wireless beacon identifiers, selecting a subset of the object-recognition classifiers in the set of object-recognition classifiers; and recognizing an object in the captured image based on the selected subset of the object-recognition classifiers; and requesting, from a remote offer publisher server, offers corresponding to the recognized object; and receiving offers from the remote offer publisher server; and displaying the received offers to the user.
-
公开(公告)号：US20170330318A1
公开(公告)日：2017-11-16
申请号：US15506676
申请日：2015-08-31
发明人： Umesh Shanghvi , Rhushabh Goradia , Adarsh Jain
CPC分类号： G06T7/0012 , A61B6/463 , A61B8/463 , G06K9/00127 , G06K9/00986 , G06T2207/10024 , G06T2207/10056 , G06T2207/20016 , G06T2207/20021 , G06T2207/30024
摘要： A method and system analyzes multi-resolution medical images. The method includes receiving one or more multi-resolution medical images of one or more tissues. Each multi-resolution medical image is divided into a plurality of segments. Thereafter, each segment of the plurality of segments of each multi-resolution medical image is processed in parallel, utilizing one or more computation nodes, wherein each computation node includes one or more Graphical Processing Units (GPUs). The results corresponding to each segment of a multi-resolution medical image are collated, and a collated report is displayed.
-
公开(公告)号：US09818045B2
公开(公告)日：2017-11-14
申请号：US15617826
申请日：2017-06-08
申请人： Apple Inc.
发明人： Lorenz Kern , Norbert Stoeffler
CPC分类号： G06K9/6212 , G06K9/00986 , G06K9/4604 , G06K9/4671 , G06K9/52
摘要： An apparatus for detecting a feature in an image includes an image input section for receiving at least part of the image in the form of image data having a plurality of pixels, the plurality of pixels comprising a plurality of non-border pixels, a feature detection module adapted to attribute a feature probability value to each of the pixels of the image data, and an extremum determination module for determining at least one local extremum among the feature probability values, wherein the extremum determination module is adapted to output, for each of the plurality of pixels, a final indication if the feature probability value of the pixel in question is a local extremum. The extremum determination module is adapted to use, for each of the plurality of non-border pixels, comparison results of at least two comparison operations, with each comparison operation including a comparison of the feature probability value of the non-border pixel in question with the feature probability values of a respective subset of neighboring pixels, with the respective subsets of neighboring pixels being different subsets.
-
18.发明申请公开(公告)号：US20170263015A1
公开(公告)日：2017-09-14
申请号：US15605487
申请日：2017-05-25
申请人： PixArt Imaging Inc.
发明人： Wai-Lian TEO , Yen-Min CHANG
CPC分类号： G06K9/00986 , G06F3/0312 , G06F3/0362 , G06F3/038 , G06K9/183 , G06K9/2036 , G06K9/2063 , G06K9/3216 , G06K9/4604 , G06K9/4661 , G06K9/6202 , H04N5/2256
摘要： The present disclosure is related to an optical encoder which is configured to provide precise coding reference data by feature recognition technology. To apply the present disclosure, it is not necessary to provide particular dense patterns on a working surface. The precise coding reference data can be generated by detecting surface features of the working surface.
-
公开(公告)号：US09740918B1
公开(公告)日：2017-08-22
申请号：US14717910
申请日：2015-05-20
IPC分类号： G06K9/00
CPC分类号： G06K9/00228 , G06K9/00986 , G06K9/3241 , G06K9/6203
摘要： Subject matter disclosed herein relates to arrangements and techniques that provide for identifying objects within an image such as the face position of a user of a portable electronic device. An application specific integrated circuit (ASIC) is configured to locate objects within images. The ASIC includes an image node configured to process an image and a search node configured to search the image for an object in the image. The ASIC also includes an ensemble node configured to confirm the presence of the object in the image. The ensemble node progressively compares, using computational engines that include accumulators, the pixel values of a template with pixel values of a region of interest in the image to create comparison result values.
-
公开(公告)号：US20170221176A1
公开(公告)日：2017-08-03
申请号：US15234851
申请日：2016-08-11
申请人： FotoNation Limited
CPC分类号： G06T1/60 , G06K9/00986 , G06K9/4628 , G06K9/6272 , G06N3/0454 , G06N3/08
摘要： A convolutional neural network (CNN) for an image processing system comprises an image cache responsive to a request to read a block of N×M pixels extending from a specified location within an input map to provide a block of N×M pixels at an output port. A convolution engine reads blocks of pixels from the output port, combines blocks of pixels with a corresponding set of weights to provide a product, and subjects the product to an activation function to provide an output pixel value. The image cache comprises a plurality of interleaved memories capable of simultaneously providing the N×M pixels at the output port in a single clock cycle. A controller provides a set of weights to the convolution engine before processing an input map, causes the convolution engine to scan across the input map by incrementing a specified location for successive blocks of pixels and generates an output map within the image cache by writing output pixel values to successive locations within the image cache.
-
-
-
-
-
-
-
-
-
搜索结果
532 条记录 (耗时 0.029 秒)