TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
Location-Based Saliency Maps from a Fully Connected Layer using Multi-Shapes |
| 영문제목(English Title) |
Location-Based Saliency Maps from a Fully Connected Layer using Multi-Shapes |
| 저자(Author) |
Hoseung Kim
Seong-Soo Han
Chang-Sung Jeong
|
| 원문수록처(Citation) |
VOL 15 NO. 01 PP. 0166 ~ 0179 (2021. 01) |
한글내용
(Korean Abstract) |
|
영문내용
(English 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.
|
| 키워드(Keyword) |
Saliency Map
Contrast
Fully Connected Layer
Multi Shape
Location-Based Normalization
|
| 파일첨부 |
PDF 다운로드
|
