Results 121 to 130 of about 3,600 (211)

Boundary-preserving superpixel segmentation

Journal of Applied Science and Engineering
In recent years, superpixel segmentation has been widely used in image processing tasks as a preprocessing step. Superpixel segmentation aims to group pixels into homogeneous regions while maintaining edges.
Yuejia Lin, Zhao Li, Chenxun Yuan, Yi Liu   +3 more
doaj   +1 more source

SuperPatchMatch : Un algorithme de correspondances robustes de patchs de superpixels

, 2018
Les superpixels sont devenus très populaires dans de nombreuses applications de vision par ordinateur. Néanmoins, ils restent sous-exploités du fait de l'irrégularité des décompositions qui diffèrent selon les images. Dans ce travail, nous introduisons d'
GIRAUD, Rémi, COUPÉ, Pierrick, PAPADAKIS, Nicolas, BUGEAU, Aurélie, TA, Vinh-Thong   +4 more
core   +1 more source

Unsupervised instance segmentation with superpixels

Pattern Recognition
Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by training with a large number of human annotations, which are costly to collect.
openaire   +2 more sources

Computer Vision with a Superpixelation Camera

CoRR
Conventional cameras generate a lot of data that can be challenging to process in resource-constrained applications. Usually, cameras generate data streams on the order of the number of pixels in the image. However, most of this captured data is redundant for many downstream computer vision algorithms.
Sasidharan Mahalingam, Rachel Brown, Atul Ingle   +2 more
openaire   +2 more sources

Double-Branch Multilevel Skip Sparse Graph Attention Network for Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Graph neural networks (GNNs) offer a potent framework for learning and representing data with graph structures. In the context of hyperspectral images (HSIs) classification tasks, GNNs have been successfully employed. Among the diverse variations of GNNs,
Qingyan Wang, Lisong Ma, Junping Zhang, Shouqiang Kang, Yujing Wang   +4 more
doaj   +1 more source

V.: SEEDS: Superpixels extracted via energy-driven sampling

, 2020
. Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the same object. Many state-of-the-art superpixel algorithms rely on minimizing objective functions to enforce color homogeneity.
Michael Van Den Bergh, Luc Van Gool, Xavier Boix, Gemma Roig, Benjamin De Capitani   +4 more
core  

Medial Features for Superpixel Segmentation. [PDF]

, 2009
Image segmentation plays an important role in computer vision and human scene perception. Image oversegmentation is a common technique to overcome the problem of managing the high number of pixels and the reasoning among them. Specifically, a local and coherent cluster that contains a statistically homogeneous region is denoted as a superpixel. In this
Engel, D., Spinello, L., Triebel, R., Siegwart, R., Bülthoff, H., Curio, C.   +5 more
openaire   +1 more source

A novel superpixel based Vision Transformer for improving interpretability in glaucoma screening. [PDF]

Sci Rep
Hernández J, Alayón S, Sigut JF, Díaz-Alemán T.   +3 more
europepmc   +1 more source

Explainable deep learning-based lung cancer diagnosis using clinically-guided local interpretable model-agnostic explanations. [PDF]

Sci Rep
Hassan SU, Abdulkadir SJ, Alhussian HS, Fayyaz AM, Al-Selwi SM, Khan U, Ismail AOA.   +6 more
europepmc   +1 more source

Superpixel Random Selection Random Walk Multi-Branch Depthwise Convolutional Neural Network for Hyperspectral Image Classification. [PDF]

Sensors (Basel)
Zhang K, Jiang X, Cai Z.
europepmc   +1 more source