Finding the Secret of Image Saliency in the Frequency Domain
Authors:
- 20 April 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (12) , 2428-2440
Abstract
There are two sides to every story of visual saliency modeling in the frequency domain. On the one hand, image saliency can be effectively estimated by applying simple operations to the frequency spectrum. On the other hand, it is still unclear which part of the frequency spectrum contributes the most to popping-out targets and suppressing distractors. Toward this end, this paper tentatively explores the secret of image saliency in the frequency domain. From the results obtained in several qualitative and quantitative experiments, we find that the secret of visual saliency may mainly hide in the phases of intermediate frequencies. To explain this finding, we reinterpret the concept of discrete Fourier transform from the perspective of template-based contrast computation and thus develop several principles for designing the saliency detector in the frequency domain. Following these principles, we propose a novel approach to design the saliency detector under the assistance of prior knowledge obtained through both unsupervised and supervised learning processes. Experimental results on a public image benchmark show that the learned saliency detector outperforms 18 state-of-the-art approaches in predicting human fixations.Keywords
Funding Information
- National Natural Science Foundation of China (61370113, 61325011, 61390515, 61421003)
- National Hightech R&D Program of China (2015AA016302)
- Supervisor Award Funding for Excellent Doctoral Dissertation of Beijing (20128000103)
This publication has 48 references indexed in Scilit:
- Video Saliency Incorporating Spatiotemporal Cues and Uncertainty WeightingIEEE Transactions on Image Processing, 2014
- Guest Editor’s Introduction to the Special Issue on Domain Adaptation for Vision ApplicationsInternational Journal of Computer Vision, 2014
- Saliency Detection: A Boolean Map Approach2013
- Efficient Salient Region Detection with Soft Image Abstraction2013
- What/Where to Look Next? Modeling Top-Down Visual Attention in Complex Interactive EnvironmentsIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2013
- Spatio-Temporal Saliency Perception via Hypercomplex Frequency Spectral ContrastSensors, 2013
- Saliency filters: Contrast based filtering for salient region detection2012
- Learning visual saliency by combining feature maps in a nonlinear manner using AdaBoostJournal of Vision, 2012
- Global contrast based salient region detection2011
- Visual attention detection in video sequences using spatiotemporal cues2006