Results 11 to 20 of about 16,201 (241)
Rooted Spanning Superpixels [PDF]
International Journal of Computer Vision, 2020 This paper proposes a new approach for superpixel segmentation. It is formulated as finding a rooted spanning forest of a graph with respect to some roots and a path-cost function.
Dengfeng Chai
semanticscholar +2 more sources
Iterative Boundaries Implicit Identification for Superpixels Segmentation: A Real-Time Approach
IEEE Access, 2021 Superpixel algorithms group visually coherent pixels and form an alternative representation of the regular structure of the pixel grid. This fundamental low-level computer vision preprocessing step greatly reduces the complexity of subsequent image ...
Serge Bobbia +5 more
doaj +2 more sources
Automatic Image Segmentation With Superpixels and Image-Level Labels
IEEE Access, 2019 Automatically and ideally segmenting the semantic region of each object in an image will greatly improve the precision and efficiency of subsequent image processing.
Xinlin Xie +4 more
doaj +2 more sources
Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels [PDF]
Pattern Recognition Letters, 2022 Prior studies using graph neural networks (GNNs) for image classification have focused on graphs generated from a regular grid of pixels or similar-sized superpixels.
V. Vasudevan +3 more
semanticscholar +1 more source
TSSP-UNet: A Two-Stage Weakly Supervised Pathological Image Segmentation With Point Annotations. [PDF]
IET Syst BiolDeep convolutional neural networks excel at image segmentation but face challenges with complex instance training and high‐precision annotation acquisition. This study proposes TSSP‐UNet, a two‐stage weakly supervised segmentation approach: the first stage trains a segmentation network with constraint and attention mechanisms plus a feature aggregation
Wang S +5 more
europepmc +2 more sources
Unsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels [PDF]
Remote Sensing Applications Society and Environment, 2022 In this paper, we propose an unsupervised method for hyperspectral remote sensing image segmentation. The method exploits the mean-shift clustering algorithm that takes as input a preliminary hyperspectral superpixels segmentation together with the ...
Mirko Paolo Barbato +3 more
semanticscholar +1 more source
Pseudo-Label Refinement Using Superpixels for Semi-Supervised Brain Tumour Segmentation [PDF]
IEEE International Symposium on Biomedical Imaging, 2021 Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are especially ...
Bethany H. Thompson +2 more
semanticscholar +1 more source
Temporally Consistent Superpixels [PDF]
2013 IEEE International Conference on Computer Vision, 2013 Super pixel algorithms represent a very useful and increasingly popular preprocessing step for a wide range of computer vision applications, as they offer the potential to boost efficiency and effectiveness. In this regards, this paper presents a highly competitive approach for temporally consistent super pixels for video content. The approach is based
Reso M. +3 more
openaire +2 more sources
Dynamic spectral residual superpixels [PDF]
Pattern Recognition, 2021 We consider the problem of segmenting an image into superpixels in the context of $k$-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects. Our novel approach builds upon the widely used Simple Linear Iterative Clustering (SLIC), and incorporate a measure of objects' structure ...
Zhang, Jianchao +5 more
openaire +2 more sources
Point Label Aware Superpixels for Multi-Species Segmentation of Underwater Imagery [PDF]
IEEE Robotics and Automation Letters, 2022 Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images.
Scarlett Raine +4 more
semanticscholar +1 more source