Superpixel segmentation with squeeze-and-excitation networks

Wang, Jingjing; Luan, Zhenye; Yu, Zishu; Ren, Jinwen; Gao, Jun; Yuan, Kejiang; Xu, Hao

doi:10.1007/s11760-021-02066-2

Cited by 4 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deep neural networks are first used in superpixel sampling networks [13] to generate superpixels. Wang et al [14] use squeeze-and-excitation networks to generate superpixels. Yu et al [15] propose edge-aware superpixel segmentation with an unsupervised convolutional neural network (EASUCNN) to generate superpixels.…”

Section: Deep Learning-based Methodsmentioning

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: Deep Learning-based Methodsmentioning

confidence: 99%