Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND ELECTRONIC DEVICE FOR EFFICIENTLY REDUCING DIMENSIONS OF IMAGE FRAME
Document Type and Number:
WIPO Patent Application WO/2023/149614
Kind Code:
A1
Abstract:
Embodiments of the disclosure provide a method and device for efficiently reducing dimensions of an image frame by an electronic device. The method includes: receiving the image frame; transforming the image frame from a spatial domain comprising a first plurality of channels to a non-spatial domain comprising a second plurality of channels, where a number of the second plurality of channels is greater than a number of the first plurality of channels; removing channels comprising irrelevant information from among the second plurality of channels using an AI engine to generate a low-resolution image frame in the non-spatial domain; and providing the low-resolution image frame to a neural network for a faster and accurate inference of the image frame.

Inventors:
GOLLANAPALLI TEJPRATAP VENKATA SUBBU LAKSHMI (IN)
KUMAR RAJA (IN)
DHARKAR DEWASHISH AVINASH (IN)
Application Number:
PCT/KR2022/015277
Publication Date:
August 10, 2023
Filing Date:
October 11, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06T3/40; G06N3/08; G06N5/04; G06T5/20
Foreign References:
US10095977B12018-10-09
US20190378311A12019-12-12
US20200349673A12020-11-05
US20210019560A12021-01-21
Other References:
SHERVIN MINAEE, YURI BOYKOV, FATIH PORIKLI, ANTONIO PLAZA, NASSER KEHTARNAVAZ, AND DEMETRI TERZOPOULOS: "Image segmentation using deep leraning", ARXIV:2001.05566V5, ARXIV, 15 November 2020 (2020-11-15), pages 1 - 22, XP009540180, DOI: 10.48550/arXiv.2001.05566
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: