Detection of Saliency Map as Image Feature Outliers Using Random Projections Based Method

被引：0

作者：

Damasevicius, Robertas ^{[1
]}

Maskeliunas, Rytis ^{[1
]}

Wozniak, Marcin ^{[2
]}

Polap, Dawid ^{[2
]}

Sidekerskiene, Tatjana ^{[3
]}

Gabryel, Marcin ^{[4
]}

机构：

[1] Kaunas Univ Technol, Dept Multimedia Engn, Kaunas, Lithuania

[2] Silesian Tech Univ, Inst Math, Gliwice, Poland

[3] Kaunas Univ Technol, Dept Appl Math, Kaunas, Lithuania

[4] Czestochowa Tech Univ, Inst Computat Intelligence, Czestochowa, Poland

来源：

2017 13TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO) | 2017年

关键词：

image processing; saliency; Random Projections; VISUAL-ATTENTION; COLONY;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe a novel method based on Random Projections for construction of image saliency maps. The method identifies outliers in the 2D projections of image point features as salient image points using Random Projections and kernel density estimation. We compare the method with other known methods in the area and validated on a number of benchmark images. The robustness of the method when Gaussian blurring is applied to an image is demonstrated and evaluated using F-statistics of several image quality metrics. Application of the proposed method for image processing is discussed.

引用

页码：85 / 90

页数：6

共 51 条

[1]

Achanta R, 2009, PROC CVPR IEEE, P1597, DOI 10.1109/CVPRW.2009.5206596

[2]

[Anonymous], 2001, P 20 ACM SIGMOD SIGA

[3]

[Anonymous], ADV NEURAL INFORM PR

[4]

[Anonymous], 1984, C MODERN ANAL PROBAB