Title:
IMAGE COMPRESSION SYSTEM AND METHOD BASED ON FLASH STORAGE AND CALCULATION ARRAY
Document Type and Number:
WIPO Patent Application WO/2021/027238
Kind Code:
A1
Abstract:
The present disclosure provides an image compression system and method based on a FLASH storage and calculation array. The image compression system comprises a coding convolutional neural network based on a FLASH storage and calculation array, a decoding convolutional neural network based on a FLASH storage and calculation array, and a quantization module. The coding convolutional neural network based on a FLASH storage and calculation array codes an original image to obtain a feature image; the quantization module quantizes the feature image to obtain a quantized image; the decoding convolutional neural network based on a FLASH storage array decodes the quantized image to obtain a compressed image.
Inventors:
KANG JINFENG (CN)
XIANG YACHEN (CN)
HUANG PENG (CN)
LIU XIAOYAN (CN)
HAN RUNZE (CN)
XIANG YACHEN (CN)
HUANG PENG (CN)
LIU XIAOYAN (CN)
HAN RUNZE (CN)
Application Number:
PCT/CN2019/130472
Publication Date:
February 18, 2021
Filing Date:
December 31, 2019
Export Citation:
Assignee:
UNIV BEIJING (CN)
International Classes:
G06N3/08; H04N19/42
Foreign References:
CN110475119A | 2019-11-19 | |||
CN110062231A | 2019-07-26 | |||
CN106843809A | 2017-06-13 | |||
CN106971372A | 2017-07-21 | |||
CN108805270A | 2018-11-13 | |||
CN108701236A | 2018-10-23 | |||
TW201706917A | 2017-02-16 |
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: