Extraction of the focused object in an image by filtering out the defocused background

Shih Min Kao, Taikang Ning, Cheng Wen Wu, Hui Peng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Considers the problem of extracting the focused object in an image with defocused background. Such background blur is caused by the defocusing effect of the camera lens. These types of image appear quite often, such as in racing, imaging a person in a scene, imaging a close object of interest, etc... The authors propose to extract the focused object by filtering out the defocused background in those images. A filter is designed based on the optical property of the defocusing process. Such a filter together with some postprocessing techniques are applied to extract the focused objects in images with defocused background. Experiments show that the method is quite effective in doing the desired task.

Original languageEnglish
Title of host publicationISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages53-56
Number of pages4
ISBN (Electronic)078031865X, 9780780318656
DOIs
Publication statusPublished - 1994 Jan 1
Event1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994 - Hong Kong, Hong Kong
Duration: 1994 Apr 131994 Apr 16

Publication series

NameISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings

Conference

Conference1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994
CountryHong Kong
CityHong Kong
Period94-04-1394-04-16

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Extraction of the focused object in an image by filtering out the defocused background'. Together they form a unique fingerprint.

Cite this