Location-based saliency maps from a fully connected layer using multi-shapes

Hoseung Kim, Seong Soo Han, Chang Sung Jeong

Research output: Contribution to journalArticlepeer-review

Abstract

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

Original languageEnglish
Pages (from-to)166-179
Number of pages14
JournalKSII Transactions on Internet and Information Systems
Volume15
Issue number1
DOIs
Publication statusPublished - 2021 Jan

Keywords

  • Contrast
  • Fully Connected Layer
  • Location-Based Normalization
  • Multi Shape
  • Saliency Map

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Location-based saliency maps from a fully connected layer using multi-shapes'. Together they form a unique fingerprint.

Cite this