Salient Region Detection Using Contrast-Based Saliency and Watershed Segmentation

被引：0

作者：

Ngau, Christopher Wing Hong ^{[1
]}

Ang, Li-Minn ^{[1
]}

Seng, Kah Phooi ^{[1
]}

机构：

[1] Univ Nottingham, Sch Elect & Elect Engn, Semenyih 43500, Selangor Darul, Malaysia

来源：

COMPUTING & INFORMATICS | 2009年

关键词：

Region Detection; Saliency; Watershed segmentation; ATTENTION;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Salient region detection is useful for many applications such as image segmentation, compression, image retrieval, object tracking, and machine vision systems. In this paper, an approach to detect salient regions in a visual scene using contrast-based saliency and watershed segmentation is presented. The approach allows salient objects to be detected and extracted for analysis while preserving the actual boundaries of the salient objects. The approach can be executed in parallel making it efficient for real time applications.

引用

页码：475 / 479

页数：5

共 16 条

[11]

OUERHANI N, 2003, P IWAN, P702

[12]

PARK MC, 2002, P 364 VISUALIZATION

[13]

Rajashekar U., 2002, Proceedings ETRA 2002. Eye Tracking Research and Applications Symposium, P119, DOI 10.1145/507072.507096

[14] WATERSHEDS IN DIGITAL SPACES - AN EFFICIENT ALGORITHM BASED ON IMMERSION SIMULATIONS [J].

VINCENT, L ;

SOILLE, P .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (06) :583-598

[15] Modeling attention to salient proto-objects [J].

Walther, Dirk ;

Koch, Christof .

NEURAL NETWORKS, 2006, 19 (09) :1395-1407

[16]

Won W.J., 2007, P IM VIS COMP NZ 200, P91

← 1 2 →