An Adaptive Computational Model for Salient Object Detection

Zhang, Wei; Wu, Qi; Wang, Guanghui; Yin, Haibing

doi:10.1109/tmm.2010.2047607

Cited by 48 publications

(19 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [47] proposed a Bayesian framework based approach to classify a pixel into salient object or background object by taking position, area and intensity saliencies and a maximum saliency difference technique into consideration. Goferman et al [19] proposed a context-aware saliency detection algorithm by exploiting four principles: local low level, global, visual organization rules and high-level factors.…”

Section: Top-down Methodsmentioning

confidence: 99%

A novel hybrid approach for salient object detection using local and global saliency in frequency domain

Arya

Singh

Agrawal

2015

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, we introduce a fast and novel biologically plausible frequency domain approach to detect salient object which incorporates both local and global salient features. The proposed approach involves three phases. In the first phase, locally salient features are obtained as suggested in the research work of Bian and Zhang. Globally salient features are computed in the second phase using fast Walsh-Hadamard transform since it is computationally more efficient and faster than fast Fourier transform. Finally the saliency map is generated in terms of linear weighted combination of local and global saliency maps where the weights are determined using entropy measure. The performance is evaluated both qualitatively and quantitatively on two publicly available datasets and one new dataset derived from a publicly available dataset. Experiments show that the proposed model significantly outperforms other relevant existing state-of-the-art methods in both spatial and frequency domain. The proposed method is also computationally less expensive to detect salient object accurately.

show abstract

Section: Top-down Methodsmentioning

confidence: 99%

A novel hybrid approach for salient object detection using local and global saliency in frequency domain

Arya

Singh

Agrawal

2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The graph is natural to model the image, and the saliency of each region is measured based on its relevance to queries of background and foreground using the graph-based manifold ranking [27]. On the basis of image clustering, the Gaussian mixture models (GMM) for salient object and background are constructed and used to classify pixels into salient object or background under the Bayesian framework [26]. Besides, image border based background prior [28,29], boundary based appearance divergence and spatial distribution via absorbing Markov chain [30], background templates based reconstruction error propagation [31], and object-level closed shape prior [32] are effectively used for saliency detection.…”

Section: Salient Object Segmentation Via Effectivementioning

confidence: 99%

Salient Object Segmentation via Effective Integration of Saliency and Objectness

et al. 2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper proposes an effective salient object segmentation method via the graph-based integration of saliency and objectness. Based on the superpixel segmentation result of the input image, a graph is built to represent superpixels using regular vertex, background seed vertex with the addition of a terminal vertex. The edge weights on the graph are defined by integrating the difference of appearance, saliency and objectness between superpixels. Then the object probability of each superpixel is measured by finding the shortest path from the corresponding vertex to the terminal vertex on the graph, and the resultant object probability map can generally better highlight salient objects and suppress background regions compared to both saliency map and objectness map. Finally, the object probability map is used to initialize salient object and background, and effectively incorporated into the framework of graph cut to obtain the final salient object segmentation result. Extensive experimental results on three public benchmark datasets show that the proposed method consistently improves the salient object segmentation performance and outperforms the state-of-the-art salient object segmentation methods. Furthermore, experimental results also demonstrate that the proposed graph-based integration method is more effective than other fusion schemes and robust to saliency maps generated using various saliency models.

show abstract

“…A number of computational models measure the saliency based on global, local and regional contrasts with different forms [6]- [11]. A variety of theories and methods, including information theory [12], [13], graph theory [14], [15], machine learning [16], [17], statistical model [18]- [20], Bayesian model [21], tree analysis [22] and frequency domain analysis [23]- [25], have been exploited to build saliency models. Recently, some saliency models such as [7], [11], [18], [22], and [26]- [28] benefit from measuring the saliency on the basis of region segmentation to effectively incorporate global information at region level, in order to improve the performance of salient region detection.…”

Section: A Saliency Detectionmentioning

confidence: 99%

Unsupervised Joint Salient Region Detection and Object Segmentation

Zou

Kpalma

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper presents a novel unsupervised algorithm to detect salient regions and to segment out foreground objects from background. In contrast to previous unidirectional saliency-based object segmentation methods, in which only the detected saliency map is used to guide the object segmentation, our algorithm mutually exploits detection/segmentation cues from each other. To achieve this goal, an initial saliency map is generated by the proposed segmentation driven low-rank matrix recovery model. Such a saliency map is exploited to initialize object segmentation model, which is formulated as energy minimization of Markov random field. Mutually, the quality of saliency map is further improved by the segmentation result, and serves as a new guidance for the object segmentation. The optimal saliency map and the final segmentation are achieved by jointly optimizing the defined objective functions. Extensive evaluations on MSRA-B and PASCAL-1500 datasets demonstrate that the proposed algorithm achieves the state-of-the-art performance for both the salient region detection and the object segmentation.

show abstract

An Adaptive Computational Model for Salient Object Detection

Cited by 48 publications

References 37 publications

A novel hybrid approach for salient object detection using local and global saliency in frequency domain

A novel hybrid approach for salient object detection using local and global saliency in frequency domain

Salient Object Segmentation via Effective Integration of Saliency and Objectness

Unsupervised Joint Salient Region Detection and Object Segmentation

Contact Info

Product

Resources

About