Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshold

Han, Sheng; Xi, Shi-Qiong; Wang, Geng

doi:10.1007/s11801-017-7168-5

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The texture spectrum (He et al, 1990;Backes et al, 2013;Deng et al, 2021). Yuan et al (2018) proposed an image texture feature extraction algorithm based on the Gabor filter (Meng et al, 2021) and CS-LBP operator (Han et al, 2017) for the one-way nature of traditional texture extraction, transforming the extracted frequency components into the time domain to achieve texture extraction (Yuan et al, 2018). Luo et al (2019) proposed a new PCA-based algorithm to extract the texture features of foam images by comprehensively considering the granular texture features on the surfaces of foam particles.…”

Section: Introductionmentioning

confidence: 99%

Segmentation algorithm of coal slurry foam with double-point directional extension based on the improved FCM clustering algorithm

Wu¹,

Huang²,

Shang³

et al. 2023

Physicochem. Probl. Miner. Process.

View full text Add to dashboard Cite

In flotation production, the visual surface information of the flotation foam reflects the flotation effects, which are closely related to the flotation conditions and directly reflect the degree of mineralization of the foam layer. In this study, it was proposed a novel and efficient segmentation algorithm to extract the edge information of slime bubbles, as the boundaries are typically blurred and difficult to segment, due to the slime bubbles sticking to each other in the slime flotation foam image. First, the improved clustering algorithm and image morphology operation were used to extract the edges of the foam spots. Second, the image morphological operations were used as a starting point to look around the foam edge points. The pseudo-edge points were then removed using a region and spatial removal algorithm. Finally, the foam edges were extracted using the double-point directed expansion algorithm. A new criterion was proposed for segmentation effect determination based on the particularity of the segmented object. The feasibility and effectiveness of the foam segmentation method were investigated by comparative experiments. The experimental results showed that the proposed algorithm could obtain the foam surface properties more accurately and provide effective guidance for flotation production.

show abstract