Patent · US Active

Image region segmentation method and system using self-spatial adaptive normalization

US11605167B2 · kind B2 · utility

0Cited by
0References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 18, 2020
Grant dateMar 14, 2023
Priority date
Expiry dateJun 25, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.