Results 71 to 80 of about 118,760 (177)

Hyperspectral Image Classification Based on Multiscale Feature Search Graph Convolutional Network With Meta Pseudolabels

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In recent years, graph convolutional networks (GCNs) have been introduced for hyperspectral image (HSI) classification due to their ability to effectively process the inherent graph structure of HSI data.
Suyi Li, Ke Wu, Huize Liu, Dandan Zhou, Ying Xu   +4 more
doaj   +1 more source

Enhanced Leaf Disease Segmentation Using U‐Net Architecture for Precision Agriculture: A Deep Learning Approach

Food Science &Nutrition, Volume 13, Issue 7, July 2025.
This study proposes a deep learning‐based approach for leaf disease identification using the U‐Net architecture for precise segmentation. By training on a dataset of 7056 annotated leaf images, the model effectively distinguishes between healthy and diseased regions, achieving 99.70% training accuracy and 98.99% validation accuracy in 40 epochs.
Gurpreet Singh, Asma A. Al‐Huqail, Ahmad Almogren, Sukhdeep Kaur, Kapil Joshi, Ajay Singh, Salil Bharany, Seada Hussen, Ateeq Ur Rehman   +8 more
wiley   +1 more source

SHCFN: Superpixel-Based Hybrid Cooperative Fusion Network for Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Graph-based methods demonstrate superior ability in capturing non-Euclidean relationships among pixels, thereby making them particularly appropriate for applications in hyperspectral image classification (HSIC). However, these methods encounter excessive
Haimiao Ge, Zhigao Xu, Haizhu Pan, Bopeng Ren, Dan Lv, Chunyu Zhang   +5 more
doaj   +1 more source

Deep‐Learning‐Enhanced Electron Microscopy for Earth Material Characterization

Journal of Geophysical Research: Machine Learning and Computation, Volume 2, Issue 2, June 2025.
Abstract Rocks, as Earth materials, contain intricate microstructures that reveal their geological history. These microstructures include grain boundaries, preferred orientation, twinning and porosity, holding critical significance in the realm of the energy transition.
Hans van Melick, Richard Taylor, Oliver Plümper   +2 more
wiley   +1 more source

Superpixel-Based Unsupervised Hyperspectral Unmixing [PDF]

, 2018
Recently, superpixel-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.
Yi, Jiarui
core   +2 more sources

Multiscale NMF based on intra-pixel and inter-pixel structure adjustment for spectral unmixing

International Journal of Applied Earth Observations and Geoinformation
Various improved nonnegative matrix factorization (NMF) methods have been widely used in spectral unmixing (SU), including nonlinear versions to counter for the lower spatial resolution and interaction between materials.
Tingting Yang, Meiping Song, Sen Li, Haimo Bao   +3 more
doaj   +1 more source

Multiscale Superpixelwise Locality Preserving Projection for Hyperspectral Image Classification

Applied Sciences, 2019
Manifold learning is a powerful dimensionality reduction tool for a hyperspectral image (HSI) classification to relieve the curse of dimensionality and to reveal the intrinsic low-dimensional manifold.
Lin He, Xianjun Chen, Jun Li, Xiaofeng Xie   +3 more
doaj   +1 more source

Sparse Representation-Based Hyperspectral Image Classification Using Multiscale Superpixels and Guided Filter

IEEE Geoscience and Remote Sensing Letters, 2019
We propose a spatial–spectral hyperspectral image classification method based on multiscale superpixels and guided filter (MSS–GF). In order to use spatial information effectively, MSSs are used to get local information from different region scales. Sparse representation classifier is used to generate classification maps for each region scale.
Tugcan Dundar, Taner Ince
openaire   +3 more sources

Superpixel-based Fast Fuzzy C-Means Clustering for Color Image Segmentation [PDF]

, 2018
A great number of improved fuzzy c-means (FCM) clustering algorithms have been widely used for grayscale and color image segmentation. However, most of them are time-consuming and unable to provide desired segmentation results for color images due to two
Nandi, A, Meng, H, Jia, X, Liu, S, Zhang, Y, Lei, T   +5 more
core   +1 more source

Learning Superpixel Relations for Supervised Image Segmentation

, 2014
In this paper we propose to extend the well known graph cut segmentation framework by learning superpixel relations and use them to weight superpixel-to-superpixel edges in a superpixel graph.
Costantino Grana, Rita Cucchiara, CUCCHIARA, Rita, MANFREDI, MARCO, GRANA, Costantino, Marco Manfredi   +5 more
core   +1 more source