Data compression method, system and electronic device

By combining a trained encoder and an entropy encoder with a generator model and a virtual coil converter, high-channel line data is compressed and reconstructed, solving the problems of long data transmission time and high disk usage, and achieving efficient and accurate data compression and image reconstruction.

CN116152362BActive Publication Date: 2026-06-12UNITED IMAGING RES INST OF INNOVATIVE MEDICAL EQUIP
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
UNITED IMAGING RES INST OF INNOVATIVE MEDICAL EQUIP
Filing Date
2022-09-28
Publication Date
2026-06-12

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The application relates to a data compression method, system and electronic device, wherein the data compression method comprises the following steps: obtaining original high-channel line data; inputting the original high-channel line data into a trained complete encoder model for encoding processing and outputting latent feature variables; wherein the encoder model is generated by iterative training according to at least to-be-trained line data, training parameters and a preset generator model; and using a preset entropy encoder to perform entropy encoding processing on the latent feature variables and generating high-channel line data compression results. Through the application, the problem that high-channel line data transmission is time-consuming and occupies a large amount of disk space is solved, and an accurate and efficient data compression method is realized.
Need to check novelty before this filing date? Find Prior Art