Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

Abstract

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of {\it non-saliency}. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space analysis of the amplitude spectrum of natural images. We show that the convolution of the {\it image amplitude spectrum} with a low-pass Gaussian kernel of an appropriate scale is equivalent to such an image saliency detector. The saliency map is obtained by reconstructing the 2-D signal using the original phase and the amplitude spectrum, filtered at a scale selected by minimizing saliency map entropy. A Hypercomplex Fourier Transform performs the analysis in the frequency domain. Using available databases, we demonstrate experimentally that the proposed model can predict human fixation data. We also introduce a new image database and use it to show that the saliency detector can highlight both small and large salient regions, as well as inhibit repeated distractors in cluttered images. In addition, we show that it is able to predict salient regions on which people focus their attention.

Cited by in corpus (28)

• Salient Object Detection: A Benchmark
• Salient Object Detection: A Survey
• What is a salient object? A dataset and a baseline model for salient object detection
• A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification
• Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features
• Salient Structure Detection by Context-Guided Visual Search
• Real-world plant species identification based on deep convolutional neural networks and visual attention
• Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency
• Saliency Detection with Spaces of Background-based Distribution
• Saliency Integration: An Arbitrator Model
• Contextual Hypergraph Modelling for Salient Object Detection
• A Psychophysically Oriented Saliency Map Prediction Model
• Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency
• Visual Language Modeling on CNN Image Representations
• Human Attention Estimation for Natural Images: An Automatic Gaze Refinement Approach
• Learning a Saliency Evaluation Metric Using Crowdsourced Perceptual Judgments
• A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection
• Benchmark 3D eye-tracking dataset for visual saliency prediction on stereoscopic 3D video
• Exploiting Color Name Space for Salient Object Detection
• Few-Shot Abstract Visual Reasoning With Spectral Features
• Saliency detection based on structural dissimilarity induced by image quality assessment model
• The Secrets of Salient Object Segmentation
• Ultrafast Video Attention Prediction with Coupled Knowledge Distillation
• Multi-Scale Saliency Detection using Dictionary Learning
• Deriving Explanation of Deep Visual Saliency Models
• Model-guided Multi-path Knowledge Aggregation for Aerial Saliency Prediction
• Visual Attention on the Sun: What Do Existing Models Actually Predict?
• Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery