Global Contrast of Superpixels Based Salient Region Detection

Wang, Jie; Zhang, Caiming; Zhou, Yuanfeng; Yu, Wei; Liu, Yi

doi:10.1007/978-3-642-34263-9_17

Cited by 8 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Superpixel is an important image preprocessing technology that improves speed by reducing the number of processing units. It has been widely used in such fields as image classification [1] , target tracking [2] , object recognition [3] , and others. The concept of superpixel was first proposed by Ren and Malik [4] .…”

Section: Introductionmentioning

confidence: 99%

Image segmentation with texture-oriented superpixel

Song

Huang

Zhang

2023

Second International Symposium on Computer Applications and Information Systems (ISCAIS 2023)

View full text Add to dashboard Cite

Superpixel segmentation is an image preprocessing technique that uses pixel blocks instead of pixels to improve the efficiency of subsequent image tasks. Existing methods are not sensitive to image texture. To solve this problem, a texture-oriented superpixel (TOS) segmentation method is proposed. Firstly, an adaptive parameter function based on pixel boundary probability is used to calculate the distance. Secondly, a gradual merging strategy is used for merging. And finally, a loop iterative framework is used to optimize the seeds. The experimental results show that TOS can effectively preserve the smaller texture information, generate seeds that are more consistent with image texture, and better detect image texture.

show abstract

Section: Introductionmentioning

confidence: 99%

Image segmentation with texture-oriented superpixel

Song

Huang

Zhang

2023

Second International Symposium on Computer Applications and Information Systems (ISCAIS 2023)

View full text Add to dashboard Cite

show abstract

“…Superpixels segmentation is defined as a pixel clustering method which gathers image pixels with the same or similar properties into one superpixel region. It can be used as a preprocessing in some image applications, such as segmentation [2], saliency detection [3] and recognition [4]. An ideal superpixels oversegmentation should have three properties: (1) pixels in each region have uniform intensity; (2) the shape of each region is regular; (3) the boundary of each region is smooth and adheres to the image boundary.…”

Section: Introductionmentioning

confidence: 99%

Flooding based superpixels generation with color, compactness and smoothness constraints

Pan¹,

Zhou²,

Zhang³

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Superpixel generation is widely used in image segmentation. In this paper, we present an efficient flooding based superpixel generation algorithm. A new distance metric is defined for estimating pixels and seeds' similarity with COLOR, COM-PACTNESS and SMOOTHNESS constraints. A seeds update strategy based on Lloyd's algorithm is adopted for optimizing seeds and superpixels' contour regions. Experimental results show our algorithm outperforms the existing methods. Boundaries of superpixels generated by our algorithm can fit the original image boundaries better.

show abstract

Saliency detection based on superpixels clustering and stereo disparity

Gao

Chi

et al. 2016

Appl. Math. J. Chin. Univ.

View full text Add to dashboard Cite

Global Contrast of Superpixels Based Salient Region Detection

Cited by 8 publications

References 12 publications

Image segmentation with texture-oriented superpixel

Image segmentation with texture-oriented superpixel

Flooding based superpixels generation with color, compactness and smoothness constraints

Saliency detection based on superpixels clustering and stereo disparity

Contact Info

Product

Resources

About