A segment-based image saliency detection

  title={A segment-based image saliency detection},
  author={Oleg Muratov and Pamela Zontone and Giulia Boato and Francesco G. B. De Natale},
  journal={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  • O. Muratov, P. Zontone, F. D. Natale
  • Published 22 May 2011
  • Computer Science
  • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
This paper presents a novel method of visual saliency detection. The use of saliency promises benefits to multimedia applications. However, up to now just few reasonable applications of saliency exist. It is clear that limited accuracy is one of the possible reasons for this. Another reason could be that in general saliency allows us to detect salient regions of the image rather than objects. To fill this gap we study to what extend the integration of segmentation into saliency detection allows… 

Figures from this paper

Salient object detection via background contrast

A novel framework which aims to automatically identify salient regions in natural images based on two key ideas to consider the statistical spatial distribution of saliency and non-saliency regions as two complementary processes is introduced.

Visual Saliency Detection and its Application to Image Retrieval

The development of an accurate visual importance estimation method may bring a useful tool for image processing domain and that is the main goal for this work.

Context-Aware Saliency Map Generation Using Semantic Segmentation

A saliency map is proposed, based on image context detection using semantic segmentation as a high-level feature in image saliency detection, which shows acceptable results in detecting salient points.

Saliency detection via boundary and center priors

This paper proposes a novel method for saliency detection in HSL color space by dividing the traditional global contrast based saliency into background saliency and foreground saliency, and using a well-founded fusion to get the saliency map.

Salient object detection using scene layout estimation

This paper proposes a method of visual salient region detection based on depth maps estimated from 2D images that solves saliency detection problem in segment-wise domain that allows prediction of objects rather than separate pixels.

Saliency Detection for Semantic Segmentation of Videos

A contour detection-based approach for detection of salient frames for faster semantic segmentation of videos with and without passing the video input through the segmentation block is proposed.

Saliency detection as a support for image forensics

An improved version of a saliency map extractor based on segmentation is introduced and the application of a tampering detection method allowing digital composite detection is described.

Saliency detection using joint spatial-color constraint and multi-scale segmentation

Divergence Filter for Saliency

  • Dao Nam Anh
  • Computer Science
    2015 Seventh International Conference on Knowledge and Systems Engineering (KSE)
  • 2015
The proposed solution is based on an adaptive version of the bilateral filter that searches for the divergence of a pixel with its local neighbors, and can deal with texture during analysis of visual attention, and saliency detection's performance is improved.

Superiority Of Graph-Based Visual Saliency (GVS) Over Other Image Segmentation Methods

This study proposed a supervised framework which uses visual saliency detection to quantitatively evaluate image segmentation quality and uses Graph-based Visual Saliency (GVS) to compare boundary outputs for manually segmented images.



Saliency Detection: A Spectral Residual Approach

A simple method for the visual saliency detection is presented, independent of features, categories, or other forms of prior knowledge of the objects, and a fast method to construct the corresponding saliency map in spatial domain is proposed.

Learning to Detect a Salient Object

A set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, are proposed to describe a salient object locally, regionally, and globally.

Salient Region Detection and Segmentation

A novel method to determine salient regions in images using low-level features of luminance and color is presented, which is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image.

Which Colors Best Catch Your Eyes: a Subjective Study of Color Saliency

To determine Regions of Interest (ROI) in a scene, percep-tual saliency of regions has to be measured. When scenes are viewed with the same context and motivation, these ROIs are often highly

Synergism in low level vision

The edge detection and image segmentation (EDISON) system, available for download, implements the proposed technique and provides a complete toolbox for discontinuity preserving filtering, segmentation and edge detection.

Saliency Based on Information Maximization

A model of bottom-up overt attention is proposed based on the principle of maximizing information sampled from a scene and is achieved in a neural circuit, which is demonstrated as having close ties with the circuitry existent in die primate visual cortex.

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented, which breaks down the complex problem of scene understanding by rapidly selecting conspicuous locations to be analyzed in detail.

Learning to predict where humans look

This paper collects eye tracking data of 15 viewers on 1003 images and uses this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features.