Contrast-based image attention analysis by using fuzzy growing
Published 2 November 2003
Yufei Ma, Hong-Jiang Zhang
Citations949
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A feasible and fast approach to attention area detection in images based on contrast analysis is proposed and a practicable framework for image attention analysis is presented, which provides three-level attention analysis, i.e., attended view, attended areas and attended points.
Abstract
Visual attention analysis provides an alternative methodology to semantic image understanding in many applications such as adaptive content delivery and region-based image retrieval. In this paper, we propose a feasible and fast approach to attention area detection in images based on contrast analysis. The main contributions are threefold: 1) a new saliency map generation method based on local contrast analysis is proposed; 2) by simulating human perception, a fuzzy growing method is used to extract attended areas or objects from the saliency map; and 3) a practicable framework for image attention analysis is presented, which provides three-level attention analysis, i.e., attended view, attended areas and attended points. This framework facilitates visual analysis tools or vision systems to automatically extract attentions from images in a manner like human perception. User study results indicate that the proposed approach is effective and practicable.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceA model of saliency-based visual attention for rapid scene analysis
11,180 Citations1998Laurent Itti, Christof Koch +1 more
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.
Medical Entomology and ZoologyFuzzy Sets and Fuzzy Logic: Theory and Applications
6,098 Citations1995George J. Klir, Bo Yuan
Perception and Communication
4,735 Citations2016
Principles Of Gestalt Psychology
4,257 Citations2013K. Koffka
Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry
3,775 Citations1987Christof Koch, Shimon Ullman
This study addresses the question of how simple networks of neuron-like elements can account for a variety of phenomena associated with this shift of selective visual attention and suggests a possible role for the extensive back-projection from the visual cortex to the LGN.
Artificial IntelligenceModeling visual attention via selective tuning
1,165 Citations1995John K. Tsotsos, Scan M. Culhane +4 more
This model is a hypothesis for primate visual attention, but it also outperforms existing computational solutions for attention in machine vision and is highly appropriate to solving the problem in a robot vision system.
PMLA/Publications of the Modern Language Association of AmericaOxford University Press
592 Citations1968
A user attention model for video summarization
564 Citations2002Yufei Ma, Lie Lu +2 more
A generic framework of video summarization based on the modeling of viewer's attention is presented, which takes advantage of computational attention models and eliminates the needs of complex heuristic rules inVideo summarization.
Multimedia SystemsA visual attention model for adapting images on small displays
422 Citations2003Li‐Qun Chen, Xing Xie +4 more
A generic and extensible image attention model is introduced based on three attributes (region of interest, attention value, and minimal perceptible size) associated with each attention object and a branch-and-bound algorithm is developed to find the optimal adaptation efficiently.
Lecture notes in computer scienceStatistical Learning of Multi-view Face Detection
400 Citations2002Stan Z. Li, Long Zhu +4 more
FloatBoost incorporates the idea of Floating Search into AdaBoost to solve the non-monotonicity problem encountered in the sequential search of AdaBoost and leads to the first real-time multi-view face detection system in the world.
Cold Spring Harbor Symposia on Quantitative BiologySome Reflections on Visual Awareness
334 Citations1990Francis Crick, Christof Koch
Peer group filtering and perceptual color image quantization
205 Citations2003Yining Deng, Charles Kenney +2 more
Peer group filtering (PGF) is used as a preprocessing step for color quantization and results show that very coarse quantization can be obtained while preserving the color information in the original images.
Proceedings - International Conference on Image ProcessingA model of motion attention for video skimming
153 Citations2003Yufei Ma, Hong-Jiang Zhang
A new computational model of motion attention and the approach to applying this model in video skimming is presented and the effectiveness of the architecture and model is demonstrated by user studies of visual skimming experiments.
Optical EngineeringAttentive mechanisms for dynamic and static scene analysis
90 Citations1995Ruggero Milanese
An alerting system that extracts moving objects in a sequence through the use of multiresolution representations, and a detection system that detects regions in still images that are likely to contain objects of interest.
Robotics and Autonomous SystemsExpectation-based selective attention for visual monitoring and control of a robot vehicle
65 Citations1997Shumeet Baluja, Dean Pomerleau
An artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system and a mechanism for achieving task-specific focus of attention by exploiting temporal coherence are presented.
An effective region-based image retrieval framework
60 Citations2002Jing Feng, Mingjing Li +2 more
A region-based image retrieval framework that integrates efficient region- based representation in terms of storage and retrieval and effective on-line learning capability and supports relevance feedback based on the vector model with a weighting scheme is presented.
Optical EngineeringThreshold selection using a minimal histogram entropy difference
51 Citations1997Prasanna K. Sahoo
The proposed gray-level threshold selection method is similar to the maximum entropy method proposed by Kapur et al. (1985), however, the new method provided a good threshold value in many instances where the previous method did not.
Salient region detection and tracking in video
33 Citations2003Ying Li, Yufei Ma +1 more
A new approach to automatically detect and track salient regions in generic videos is presented, which could be used to evaluate the frame importance so as to provide guidance in keyframe extraction for video summarization purpose.
VISIT: A Neural Model of Covert Visual Attention
24 Citations1991Subutai Ahmad
This paper concentrates on the biological plausibility of the model and its relationship to the primary visual cortex, pulvinar, superior colliculus and posterior parietal areas.