Results 41 to 50 of about 5,165 (221)
Superpixels: An evaluation of the state-of-the-art [PDF]
Computer Vision and Image Understanding, 2018 Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003. By today, publicly available superpixel algorithms have turned into standard tools in
David Stutz +2 more
openaire +2 more sources
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingMost of the existing superpixel segmentation-based synthetic aperture radar (SAR) target detection algorithms cannot keep the independence of small targets under complex background, especially when the size of the targets varies greatly.
Shichao Chen +5 more
doaj +1 more source
Image Segmentation of Brain MRI Based on LTriDP and Superpixels of Improved SLIC
Brain Sciences, 2020 Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI).
Yu Wang, Qi Qi, Xuanjing Shen
doaj +1 more source
Remote Sensing, 2022 Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a ...
Chunhui Zhao +3 more
doaj +1 more source
Superpixel Sampling Networks [PDF]
, 2018 Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel algorithms are not differentiable, making them difficult to integrate into otherwise end-to-end trainable deep neural networks.
Varun Jampani +4 more
openaire +2 more sources
Salient Object Segmentation Based on Superpixel and Background Connectivity Prior
IEEE Access, 2018 Salient object segmentation is well known for detecting and segmenting objects using saliency map as input. In this paper, we propose a salient object segmentation method which integrates saliency, superpixel, and background connectivity prior.
Yuzhen Niu, Chaoran Su, Wenzhong Guo
doaj +1 more source
Superpixel-based color transfer [PDF]
2017 IEEE International Conference on Image Processing (ICIP), 2017 In this work, we propose a fast superpixel-based color transfer method (SCT) between two images. Superpixels enable to decrease the image dimension and to extract a reduced set of color candidates. We propose to use a fast approximate nearest neighbor matching algorithm in which we enforce the match diversity by limiting the selection of the same ...
Rémi Giraud +2 more
openaire +2 more sources
Superpixel Optimization Using Higher Order Energy
, 2016 A novel superpixel extraction algorithm using a higher order energy optimization framework is proposed in this paper. We first adopt the k-means clustering technique to quickly get an initial superpixel result.
Li, Xuelong +3 more
core +1 more source
Updated Homogeneity Criteria Based Low-Dimensional Representation for Hyperspectral Unmixing
IEEE AccessSuperpixel-based approaches have been proposed for hyperspectral unmixing. The basic assumption of this approach is that the superpixel over-segmentation segments the image into small homogeneous areas.
Jiarui Yi, Huiyi Gao
doaj +1 more source
Near‐Infrared Polarimetric Imaging With Nonlinear Flat‐Optics
Laser &Photonics Reviews, EarlyView.ABSTRACT A compact and broadband polarimetric imaging platform is presented, based on second‐harmonic generation (SHG) in nonlinear flat‐optics. The system employs periodic all‐dielectric AlGaAs gratings to induce polarization‐dependent SH emission, enabling pixel by pixel direct retrieval of the full Stokes vector from an input intensity distribution ...
Evgenii Menshikov +6 more
wiley +1 more source