专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20230029335A1 SYSTEM AND METHOD OF CONVOLUTIONAL NEURAL NETWORK 有权
公开(公告)号：US20230029335A1
公开(公告)日：2023-01-26
申请号：US17493661
申请日：2021-10-04
申请人： TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD. , NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG , Hsiu-Pin HSU
IPC分类号： G06T3/40 , G06T1/00 , G06K9/46 , G06K9/00 , G06T1/60 , G06N3/04
摘要： A method the following operations: downscaling an input image to generate a scaled image; performing, to the scaled image, a first convolutional neural networks (CNN) modeling process with first non-local operations, to generate global parameters; and performing, to the input image, a second CNN modeling process with second non-local operations that are performed with the global parameters, to generate an output image corresponding to the input image. A system is also disclosed herein.

2. 发明公开

US20240013400A1 SYSTEM AND METHOD OF CONVOLUTIONAL NEURAL NETWORK 审中-公开
公开(公告)号：US20240013400A1
公开(公告)日：2024-01-11
申请号：US17860750
申请日：2022-07-08
申请人： TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD. , NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG , Kai-Ping LIN
IPC分类号： G06T7/174
CPC分类号： G06T7/174 , G06T2207/20021 , G06T2207/20084
摘要： A method includes: generating, by a processing device, at least one first output image block based on a first image block group; storing stored image blocks corresponding to a first part of the first image block group in the processing device; and after the at least one first output image block is generated, generating, by the processing device, at least one second output image block based on a first image block and the stored image blocks, wherein the first image block group and the first image block are arranged in order along a first direction, and the at least one first output image block and the at least one second output image block are arranged in order along the first direction. A system is also disclosed herein.

3. 发明申请

US20210383198A1 DEEP NEURAL NETWORK ACCELERATING METHOD USING RING TENSORS AND SYSTEM THEREOF 有权
公开(公告)号：US20210383198A1
公开(公告)日：2021-12-09
申请号：US17230958
申请日：2021-04-14
申请人： NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG
IPC分类号： G06N3/04
摘要： A deep neural network accelerating method using a plurality of ring tensors includes a plurality of steps. A ring tensor setting step includes setting an input feature ring tensor and a weight ring tensor of a convolutional network. A ring tensor convolution calculating step includes calculating a plurality of input feature ring elements of the input feature ring tensor and a plurality of weight ring elements of the weight ring tensor according to a ring multiplication calculating step and a ring addition calculating step to generate a plurality of convolution feature ring elements of a convolution feature ring tensor. A non-linear tensor activation function calculating step includes executing a directional non-linear activation function on one of the convolution feature ring elements of the convolution feature ring tensor to generate an output feature ring element.

4. 发明申请

US20200184332A1 CONVOLUTIONAL NEURAL NETWORK PROCESSOR AND DATA PROCESSING METHOD THEREOF 审中-公开
公开(公告)号：US20200184332A1
公开(公告)日：2020-06-11
申请号：US16701172
申请日：2019-12-03
申请人： NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG
IPC分类号： G06N3/08 , G06N3/06 , G06F9/38 , G06F9/30
摘要： A convolutional neural network processor includes an information decode unit and a convolutional neural network inference unit. The information decode unit is configured to receive a program input and weight parameter inputs and includes a decoding module and a parallel processing module. The decoding module receives the program input and produces an operational command according to the program input. The parallel processing module is electrically connected to the decoding module, receives the weight parameter inputs and includes a plurality of parallel processing sub-modules for producing a plurality of weight parameter outputs. The convolutional neural network inference unit is electrically connected to the information decode unit and includes a computing module. The computing module is electrically connected to the parallel processing module and produces an output data according to an input data and the weight parameter outputs.

5. 发明申请

US20210103793A1 BLOCK-BASED INFERENCE METHOD FOR MEMORY-EFFICIENT CONVOLUTIONAL NEURAL NETWORK IMPLEMENTATION AND SYSTEM THEREOF 有权
公开(公告)号：US20210103793A1
公开(公告)日：2021-04-08
申请号：US17064561
申请日：2020-10-06
申请人： NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG
IPC分类号： G06N3/04 , G06N5/04
摘要： A block-based inference method for a memory-efficient convolutional neural network implementation is performed to process an input image. A block-based inference step is performed to execute a multi-layer convolution operation on each of a plurality of input block data to generate an output block data and includes selecting a plurality of ith layer recomputing features according to a position of the output block data along a scanning line feed direction, and then selecting an ith layer recomputing input feature block data according to the position of the output block data and the ith layer recomputing features, and selecting a plurality of ith layer reusing features according to the ith layer recomputing input feature block data along a block scanning direction, and then combining the ith layer recomputing input feature block data with the ith layer reusing features to generate an ith layer reusing input feature block data.

6. 发明申请

US20160165206A1 DIGITAL REFOCUSING METHOD 有权
标题翻译：数字反光法
公开(公告)号：US20160165206A1
公开(公告)日：2016-06-09
申请号：US14684456
申请日：2015-04-13
申请人： NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG , Jui CHIN
IPC分类号： H04N13/00 , G06T5/30 , G06T3/40 , G06T5/50
CPC分类号： H04N13/128 , G06T3/4007 , G06T5/002 , G06T5/003 , G06T5/005 , G06T5/30 , G06T5/50 , G06T15/205 , G06T2200/21 , G06T2207/10052 , H04N13/111 , H04N2013/0081
摘要： A digital refocusing method includes: to plurality of images corresponding to multiple views in a scene are obtained, the images include a central view image and at least one non-central view image; a pixel shift or a pixel index shift is performed to the non-central view image; a line scan along a pre-determined linear path is performed to the central view image and the non-central view images to obtain corresponding pixels of the central view image and corresponding pixels of the non-central view images; view interpolation based on the disparities defined in a disparity map is performed, target pixels corresponded to a novel view image are obtained from the corresponding pixels of the central view image and the corresponding pixels of the non-central view according to a target disparity; and a refocused novel view image is obtained by averaging and compositing the target pixels of novel views.
摘要翻译：数字重新聚焦方法包括：获得对应于场景中的多个视图的多个图像，所述图像包括中央视图图像和至少一个非中心视图图像; 执行像素偏移或像素索引偏移到非中心视图图像; 对中心视图图像和非中心视图图像执行沿着预定线性路径的线扫描，以获得中心视图图像和非中心视图图像的对应像素的对应像素; 执行基于视差图中定义的差异的视图插值，根据目标视差从中心视图图像的相应像素和非中心视图的相应像素获得对应于新颖视图图像的目标像素; 并且通过对新视图的目标像素进行平均和合成来获得重新聚焦的小说观看图像。

7. 发明申请

US20160165122A1 BLOCK-BASED DIGITAL REFOCUSING SYSTEM AND METHOD THEREOF 有权
标题翻译：基于块的数字重构系统及其方法
公开(公告)号：US20160165122A1
公开(公告)日：2016-06-09
申请号：US14623466
申请日：2015-02-16
申请人： NATIONAL TSING HUA UNIVERSITY
发明人： Chao-Tsung HUANG
IPC分类号： H04N5/232 , G06T7/00 , H04N5/357 , G06K9/46
CPC分类号： H04N5/23212 , G06K9/46 , G06K2009/4666 , G06T5/003 , G06T5/50 , G06T2200/21 , G06T2207/10052 , H04N5/23229 , H04N5/262 , H04N5/357
摘要： A block-based digital refocusing method includes a capturing step, a dividing step, a selecting step, a refocusing step and a combining step. The capturing step is for capturing at least one picture datum. The dividing step is for dividing the picture datum into a plurality of block data. The selecting step is for defining a regional datum according to each of the block data. The refocusing step is for conducting a refocusing computation to obtain a refocused block datum according to each of the regional data. The combining step is for combining each of the refocused block data based on each of the regional data to form a refocused picture datum.
摘要翻译：基于块的数字重新聚焦方法包括捕获步骤，分割步骤，选择步骤，重新聚焦步骤和组合步骤。捕获步骤用于捕获至少一个图像数据。分割步骤用于将图像数据分割成多个块数据。选择步骤用于根据每个块数据定义区域数据。重新聚焦步骤用于进行重新聚焦计算，以根据每个区域数据获得重新聚焦的块基准。组合步骤用于基于每个区域数据组合每个重新聚焦的块数据以形成重新聚焦的图像数据。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式