CN115699757A - 图像处理网络的输入预处理方法和输出后处理方法及装置 - Google Patents
图像处理网络的输入预处理方法和输出后处理方法及装置 Download PDFInfo
- Publication number
- CN115699757A CN115699757A CN202080101716.4A CN202080101716A CN115699757A CN 115699757 A CN115699757 A CN 115699757A CN 202080101716 A CN202080101716 A CN 202080101716A CN 115699757 A CN115699757 A CN 115699757A
- Authority
- CN
- China
- Prior art keywords
- matrix
- inverse
- quantization
- transformation
- precision compensation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 392
- 238000000034 method Methods 0.000 title claims abstract description 170
- 238000007781 pre-processing Methods 0.000 title claims abstract description 45
- 238000012805 post-processing Methods 0.000 title claims abstract description 40
- 239000011159 matrix material Substances 0.000 claims abstract description 1027
- 230000009466 transformation Effects 0.000 claims abstract description 567
- 238000013139 quantization Methods 0.000 claims abstract description 379
- 238000013528 artificial neural network Methods 0.000 claims description 72
- 230000008447 perception Effects 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 26
- 230000001131 transforming effect Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 abstract description 14
- 238000012549 training Methods 0.000 description 32
- 238000004364 calculation method Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 17
- 238000013527 convolutional neural network Methods 0.000 description 11
- 230000008859 change Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 5
- 230000001537 neural effect Effects 0.000 description 5
- 238000000844 transformation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
本申请公开了一种图像处理网络的输入预处理方法和输出后处理方法及装置，既可以适应于为减少图像处理网络的计算量而对输入矩阵中的元素的值占用的比特数进行约束的要求，又可以有目的地增强或压缩期望区域的信号，避免比特数变换导致的精度损失，确保图像质量。该方法包括：获取待处理的第一图像的第一像素矩阵，第一像素矩阵中的元素的值均采用第一格式表示，第一格式占用的比特数大于8；对第一像素矩阵进行非线性变换得到变换结果矩阵；对变换结果矩阵进行量化处理得到量化矩阵，量化矩阵中的元素的值均采用第二格式表示，第二格式占用的比特数小于或等于8；将量化矩阵输入图像处理网络。
Description
PCT国内申请，说明书已公开。
Claims (51)
- PCT国内申请，权利要求书已公开。
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/107425 WO2022027442A1 (zh) | 2020-08-06 | 2020-08-06 | 图像处理网络的输入预处理方法和输出后处理方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115699757A true CN115699757A (zh) | 2023-02-03 |
Family
ID=80118768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080101716.4A Pending CN115699757A (zh) | 2020-08-06 | 2020-08-06 | 图像处理网络的输入预处理方法和输出后处理方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115699757A (zh) |
| WO (1) | WO2022027442A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117915107A (zh) * | 2024-03-20 | 2024-04-19 | 北京智芯微电子科技有限公司 | 图像压缩系统、图像压缩方法、存储介质与芯片 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101742328B (zh) * | 2008-11-14 | 2013-03-27 | 北京中星微电子有限公司 | 图像残差矩阵整数变换方法及装置、反变换方法及装置 |
| CN101854526A (zh) * | 2009-03-30 | 2010-10-06 | 国际商业机器公司 | 码率控制方法和编码控制器 |
| CN103096052B (zh) * | 2011-11-04 | 2015-11-25 | 华为技术有限公司 | 一种图像编码、解码的方法和装置 |
| US20130272391A1 (en) * | 2012-04-16 | 2013-10-17 | Futurewei Technologies, Inc. | Method and Apparatus of Quantization Matrix Coding |
| KR101724555B1 (ko) * | 2014-12-22 | 2017-04-18 | 삼성전자주식회사 | 부호화 방법 및 장치와 복호화 방법 및 장치 |
| CN109388779A (zh) * | 2017-08-03 | 2019-02-26 | 珠海全志科技股份有限公司 | 一种神经网络权重量化方法和神经网络权重量化装置 |
| CN111031324A (zh) * | 2019-12-09 | 2020-04-17 | 中国电子科技集团公司第二十研究所 | 一种基于高维矩阵变换的视频数据传输方法 |
-
2020
- 2020-08-06 WO PCT/CN2020/107425 patent/WO2022027442A1/zh active Application Filing
- 2020-08-06 CN CN202080101716.4A patent/CN115699757A/zh active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117915107A (zh) * | 2024-03-20 | 2024-04-19 | 北京智芯微电子科技有限公司 | 图像压缩系统、图像压缩方法、存储介质与芯片 |
| CN117915107B (zh) * | 2024-03-20 | 2024-05-17 | 北京智芯微电子科技有限公司 | 图像压缩系统、图像压缩方法、存储介质与芯片 |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022027442A1 (zh) | 2022-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10462476B1 (en) | Devices for compression/decompression, system, chip, and electronic device | |
| CN109993707B (zh) | 图像去噪方法和装置 | |
| CN111914997B (zh) | 训练神经网络的方法、图像处理方法及装置 | |
| CN113326930B (zh) | 数据处理方法、神经网络的训练方法及相关装置、设备 | |
| CN110677651A (zh) | 一种视频压缩方法 | |
| KR20220137076A (ko) | 이미지 프로세싱 방법 및 관련된 디바이스 | |
| CN111695673B (zh) | 训练神经网络预测器的方法、图像处理方法及装置 | |
| CN114067007A (zh) | 图像处理方法与装置、神经网络训练的方法与装置 | |
| CN110753225A (zh) | 一种视频压缩方法、装置及终端设备 | |
| US20230209096A1 (en) | Loop filtering method and apparatus | |
| CN114698395A (zh) | 神经网络模型的量化方法和装置、数据处理的方法和装置 | |
| CN114071141A (zh) | 一种图像处理方法及其设备 | |
| CN114978189A (zh) | 一种数据编码方法以及相关设备 | |
| CN115699757A (zh) | 图像处理网络的输入预处理方法和输出后处理方法及装置 | |
| CN114140641A (zh) | 面向图像分类的多参数自适应异构并行计算方法 | |
| TWI826160B (zh) | 圖像編解碼方法和裝置 | |
| CN117441333A (zh) | 用于输入图像数据处理神经网络的辅助信息的可配置位置 | |
| CN117313531A (zh) | 光子能带预测透射谱模型的训练、预测方法、介质及设备 | |
| CN116095183A (zh) | 一种数据压缩方法以及相关设备 | |
| Senapati et al. | Compression and denoising of medical images using autoencoders | |
| CN116939218A (zh) | 区域增强层的编解码方法和装置 | |
| CN113554719B (zh) | 一种图像编码方法、解码方法、存储介质及终端设备 | |
| CN117321989A (zh) | 基于神经网络的图像处理中的辅助信息的独立定位 | |
| CN111770344A (zh) | 一种基于深度学习网络的激光光谱图像压缩方法及系统 | |
| KR20210097382A (ko) | 랭크 오더 코딩 기반 스파이킹 cnn 연산 방법 및 그 처리기 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |