Results 191 to 200 of about 16,201 (241)
TurboPixels: Fast Superpixels Using Geometric Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009 Alex Levinshtein +2 more
exaly +2 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
European Conference on Computer Vision, 2020Few-shot semantic segmentation (FSS) has great potential for medical imaging applications. Most of the existing FSS techniques require abundant annotated semantic classes for training.
C. Ouyang +5 more
semanticscholar +1 more source
Segmentation of breast ultrasound image with semantic classification of superpixels
Medical Image Anal., 2020Breast cancer is a great threat to females. Ultrasound imaging has been applied extensively in diagnosis of breast cancer. Due to the poor image quality, segmentation of breast ultrasound (BUS) image remains a very challenging task.
Qinghua Huang +4 more
semanticscholar +1 more source
Fast Generation of Superpixels With Lattice Topology
IEEE Transactions on Image Processing, 2022Serving as an essential step for many applications of image processing, superpixel generation has attracted a lot of attentions. Most existing superpixel generation algorithms focus on the boundary adherence and compactness of the superpixels, but ignore
Xiao Pan +3 more
semanticscholar +1 more source
Constrained Superpixel Tracking
IEEE Transactions on Cybernetics, 2018In this paper, we propose a constrained graph labeling algorithm for visual tracking where nodes denote superpixels and edges encode the underlying spatial, temporal, and appearance fitness constraints. First, the spatial smoothness constraint, based on a transductive learning method, is enforced to leverage the latent manifold structure in feature ...
Lijun Wang, Huchuan Lu, Ming-Hsuan Yang
openaire +2 more sources
Linear Spectral Clustering Superpixel
IEEE Transactions on Image Processing, 2017In this paper, we present a superpixel segmentation algorithm called linear spectral clustering (LSC), which is capable of producing superpixels with both high boundary adherence and visual compactness for natural images with low computational costs. In LSC, a normalized cuts-based formulation of image segmentation is adopted using a distance metric ...
Jiansheng Chen, Zhengqin Li, Bo Huang
openaire +2 more sources
2011 International Conference on Computer Vision, 2011
While numerous algorithms have been proposed for object tracking with demonstrated success, it remains a challenging problem for a tracker to handle large change in scale, motion, shape deformation with occlusion. One of the main reasons is the lack of effective image representation to account for appearance variation.
null Shu Wang +3 more
openaire +1 more source
While numerous algorithms have been proposed for object tracking with demonstrated success, it remains a challenging problem for a tracker to handle large change in scale, motion, shape deformation with occlusion. One of the main reasons is the lack of effective image representation to account for appearance variation.
null Shu Wang +3 more
openaire +1 more source
2021 International Russian Automation Conference (RusAutoCon), 2021
This paper offers the simplest understanding of superpixels as maximal pixel clusters providing error-free obtaining of a limited sequence of accessible optimal piecewise constant image approximations with the minimum achievable approximation error (total squared error) E for each number of pixel clusters.
openaire +1 more source
This paper offers the simplest understanding of superpixels as maximal pixel clusters providing error-free obtaining of a limited sequence of accessible optimal piecewise constant image approximations with the minimum achievable approximation error (total squared error) E for each number of pixel clusters.
openaire +1 more source
2015 IEEE International Conference on Image Processing (ICIP), 2015
As a pre-processing tool, superpixel algorithms have been popular used in many computer-vision applications. High efficiency is a desired property of superpixel algorithms, especially in real-time vision systems. In this paper, a novel high-efficient superpixel algorithm is developed based on the watershed algorithm, namely the spatial-constrained ...
Zhongwen Hu, Qin Zou, Qingquan Li
openaire +1 more source
As a pre-processing tool, superpixel algorithms have been popular used in many computer-vision applications. High efficiency is a desired property of superpixel algorithms, especially in real-time vision systems. In this paper, a novel high-efficient superpixel algorithm is developed based on the watershed algorithm, namely the spatial-constrained ...
Zhongwen Hu, Qin Zou, Qingquan Li
openaire +1 more source
IEEE Geoscience and Remote Sensing Letters, 2021
Low-rank subspace representations have been observed to be well-suited to hyperspectral imagery, which tends to have a global structure composed of a small number of ground-cover signatures, and additional graph-based regularization can further ...
Jinhuan Xu, J. Fowler, Liang Xiao
semanticscholar +1 more source
Low-rank subspace representations have been observed to be well-suited to hyperspectral imagery, which tends to have a global structure composed of a small number of ground-cover signatures, and additional graph-based regularization can further ...
Jinhuan Xu, J. Fowler, Liang Xiao
semanticscholar +1 more source