Semiconductor Optoelectronics, Volume. 43, Issue 3, 585(2022)
An Adaptive Initializing Superpixel Seed Points Method Based on Kmeans++
As a preprocessing step of target segmentation, superpixel can greatly reduce the amount of subsequent data processing, and plays a vital role in image segmentation. In most superpixel algorithms, seed points are sampled on a regular grid or initialized randomly, which easily leads to undersegmentation. In order to obtain a good distribution of seed point and avoid undersegmentation, an adaptively initializing superpixel seeds method based on Kmeans++ is proposed and used to improve the algorithms of SNIC. The experimental results show that the improved SNIC algorithm can get higher boundary recall rate and lower undersegmentation error rate than that of the traditional algorithm without a lot of computational cost.
Get Citation
Copy Citation Text
YANG Zhili, ZHANG Dong. An Adaptive Initializing Superpixel Seed Points Method Based on Kmeans++[J]. Semiconductor Optoelectronics, 2022, 43(3): 585
Category:
Received: Jan. 13, 2022
Accepted: --
Published Online: Aug. 1, 2022
The Author Email: