Attention-driven salient edge(s) and region(s) extraction with application to CBIR

Feng, Songhe; Xu, De; Yang, Xu

doi:10.1016/j.sigpro.2009.05.017

Cited by 76 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two manners in salient region detection: the bottom-up manner [1][2][3][4] and the top-down manner [14][15][16][17], and also some methods combine the two manners together for context-aware saliency detection [21]. The bottom-up manner can find the salient regions without any priori-knowledge.…”

Section: Introductionmentioning

confidence: 99%

“…In Itti's model, a center-surround difference operator on different image features was used to compute the multi-scale feature maps, and then the obtained feature maps over different scales were combined and normalized to form a final salience map. Similar methods of saliency computation were used in [3][4][5][6]10]. The model Peng Wang, Wei Liu and Hong Qiao are with Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China (e-mail: peng_wang@ia.ac.cn).…”

Section: Introductionmentioning

confidence: 99%

“…presented in [3] also constructed the feature map of color by local contrast, and they introduced new feature maps of edges and symmetry. S. Feng et al [4] used a linear combination of contrasts in the Gaussian image pyramid to simply define the multi-scale contrast features. Ma [5] generated the saliency map by local neighborhood contrast of the LUV image based on contrast and fuzzy growing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Salient region detection based on local and global saliency

Wang

Zhou

Liu

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

a new and effective salient region detection method based on local and global saliency information is proposed. To keep the completeness of salient regions, the input image is segmented into several regions firstly. Then for each region, local saliency and global saliency are generated respectively. The local saliency is computed by multi-scale neighborhood contrast, and the global saliency is measured according to global spatial distribution and inter-region isolation of features. Based on the local saliency and global saliency, the final saliency can be obtained by the weighted combination of them. The comparison experiment results demonstrate the effective performance of the proposed algorithm on salient region detection.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Salient region detection based on local and global saliency

Wang

Zhou

Liu

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…In recent years, TinEye website retrieval has found similar query images on the Internet [5]. According to human perception, simple statistics can be used to extract low-level features (color [6,7] and textures [8]) and high-level features (shape [9] and region [10,11] from most CBIR (content-based image retrieval) systems. The users input the specific keyword in the search engine.…”

Section: Introductionmentioning

confidence: 99%

Building Specified Web-Searching Image Database Using Quantization-Color-Size Histogram

Hsueh

2012

2012 International Symposium on Computer, Consumer and Control

View full text Add to dashboard Cite

Users usually search images in different web image search engines by inputting a specified keyword. However, the true images, drawing images, sometimes contemporary images exist in search results. To solve this problem, this paper proposed a simple color feature by using the histogram method for building image databases. First, after removing the smaller size and clipart of images from the database, the proposed method uses color quantization and calculates the sum of continuous intervals from the quantization-color-size histogram to get the global color feature. If the image is conformed to the global feature then the image can be saved in the database. As a result, our proposed method has the high accuracy and effectively filters the web-searching results to form the desired image database.

show abstract

“…Walther and Koch's method has high computational complexity, and Ma et al's method usually produces low saliency inside a salient object. To resolve the two problems, Feng 16 proposed to define the multiscale contrast futures as a linear combination of contrasts in the Gaussian image pyramid. Then, he used a maximum entropy-based algorithm to produce salient regions on segmented images.…”

Section: Introductionmentioning

confidence: 99%

Edge-based method for detecting salient objects

Deng

Luo

2011

Opt. Eng

View full text Add to dashboard Cite

A novel edge based method for detecting a salient object in an image is proposed. The core idea of our work is that the problem of detecting a salient object is transformed to the problem of finding closed curves in the edge map. It requires only edge detection and "closed curve" detection. The novelty lies in two aspects: first, when producing an edge map, the number of edge pixels is limited to make sure that edges detected in the background are relatively little; second, when detecting a salient object from an edge map, the contour of the salient object is detected in a simple way to decrease the effect of edges in the background. Experiments conducted on Liu et al.'s [Proc. CVPR, pp. 1-8, Minneapolis, MN (2007)] dataset of 5000 images show that the method is comparable with several popular methods from literature. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

show abstract

Attention-driven salient edge(s) and region(s) extraction with application to CBIR

Cited by 76 publications

References 19 publications

Salient region detection based on local and global saliency

Salient region detection based on local and global saliency

Building Specified Web-Searching Image Database Using Quantization-Color-Size Histogram

Edge-based method for detecting salient objects

Contact Info

Product

Resources

About