DocumentCode :
3748467
Title :
Generic Promotion of Diffusion-Based Salient Object Detection
Author :
Peng Jiang;Nuno Vasconcelos;Jingliang Peng
Author_Institution :
Shandong Univ., Jinan, China
fYear :
2015
Firstpage :
217
Lastpage :
225
Abstract :
In this work, we propose a generic scheme to promote any diffusion-based salient object detection algorithm by original ways to re-synthesize the diffusion matrix and construct the seed vector. We first make a novel analysis of the working mechanism of the diffusion matrix, which reveals the close relationship between saliency diffusion and spectral clustering. Following this analysis, we propose to re-synthesize the diffusion matrix from the most discriminative eigenvectors after adaptive re-weighting. Further, we propose to generate the seed vector based on the readily available diffusion maps, avoiding extra computation for color-based seed search. As a particular instance, we use inverse normalized Laplacian matrix as the original diffusion matrix and promote the corresponding salient object detection algorithm, which leads to superior performance as experimentally demonstrated.
Keywords :
"Object detection","Eigenvalues and eigenfunctions","Laplace equations","Image color analysis","Visualization","Computer vision","Algorithm design and analysis"
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2015 IEEE International Conference on
Electronic_ISBN :
2380-7504
Type :
conf
DOI :
10.1109/ICCV.2015.33
Filename :
7410390
Link To Document :
بازگشت