Salient Object Detection: A Benchmark

Borji, Ali; Sihite, Dicky N.; Itti, Laurent

doi:10.1007/978-3-642-33709-3_30

Cited by 634 publications

(775 citation statements)

References 55 publications

Supporting

Mentioning

770

Contrasting

Order By: Relevance

“…1 as suggested in the research work of Bian and Zhang [4]. This decomposition scheme separates the amplitude spectrum of the input image into feature maps in four scales with 16,8,4, and 1 orientations from the highest scale to the lowest, which result in total 29 sub-bands corresponding to the 29 feature maps. Then normalization term for i th sub-band, E i is calculated as…”

Section: Local Saliency Computationmentioning

confidence: 98%

“…Visual Attention is a cognitive process that helps humans and primates to rapidly select the highly relevant information from a scene [7]. This information is then further processed by high-level visual processes such as scene understanding and object detection.…”

mentioning

confidence: 99%

“…Most of research works mostly focused on the bottom-up aspect of visual attention. Currently researchers started distinguishing the two very similar terms with the advancement of bottom-up approaches: fixation prediction and salient object detection [8,11,35]. The main objective of the fixation prediction models is to find the fixation points in a given scene.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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: Local Saliency Computationmentioning

confidence: 98%

mentioning

confidence: 99%

See 1 more Smart Citation

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

“…In this section, we only briefly introduce the methods and datasets that we used in the experiments. Please refer to [30] and [31,32] for good surveys of saliency analysis and image denoising, respectively.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of visual saliency analysis algorithms in noisy images

Niu

Liang

Guo

2016

Machine Vision and Applications

View full text Add to dashboard Cite

Most existing visual saliency analysis algorithms assume that the input image is clean and does not have any disturbances. However, this situation is not always the case. In this paper, we provide an extensive evaluation of visual saliency analysis algorithms in noisy images. We analyze the noise immunity of saliency analysis algorithms by evaluating the performances of the algorithms in noisy images with increasing noise scales and by studying the effects of applying different denoising methods before performing saliency analysis. We use 10 state-of-the-art saliency analysis algorithms and 7 typical image denoising methods on 4 eye fixation datasets and 2 salient object detection datasets. Our experiments show that the performances of saliency analysis algorithms decrease with increasing image noise scales in general. An exception is that the nonlinear features (NF) integrated algorithm shows good noise immunity. We also find that image denoising methods can greatly improve the noise immunity of the algorithms. Our results show that the combination of NF and Median denoising method works best on eye fixation datasets and the combination of saliency optimization (SO) and color block-matching and 3D filtering (C-BM3D) method works best on salient object detection datasets. The combination of SO and Average denoising method works best for applications wherein time efficiency is a major concern for both types of datasets.

show abstract

“…At present, there are approximately two categories of existing bottom-up saliency detection methods: local and global approaches. The local method is very time-consuming, which computes visual features in parallel, such as color, intensity, motion, and orientation [7][8][9]. By comparison, global methods, less time-consuming, detect the saliency map under a full resolution based on the object level and can uniformly highlight entire object.…”

Section: Introductionmentioning

confidence: 99%

Saliency detection based on global color and space contrast

Zeng¹,

Li²,

Chai³

2017

Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016)

View full text Add to dashboard Cite

Abstract. Saliency detection acts as an important role in many computer vision tasks. We propose a novel bottom-up, object-level saliency detection method based on global color and space contrast. The proposed method not only considers the global color contrast of the image but also takes the space information into account, leading to an advanced multi-feature combined saliency detection model. Through qualitative and quantitative evaluation, our method consistently outperformed 4 global color (or intensity)-based saliency detection methods, resulting in higher precision.

show abstract

Salient Object Detection: A Benchmark

Cited by 634 publications

References 55 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

Evaluation of visual saliency analysis algorithms in noisy images

Saliency detection based on global color and space contrast

Contact Info

Product

Resources

About