Results 51 to 60 of about 9,167 (192)

Superpixel Classification Based Optic Cup Segmentation [PDF]

, 2013
In this paper, we propose a superpixel classification based optic cup segmentation for glaucoma detection. In the proposed method, each optic disc image is first over-segmented into superpixels. Then mean intensities, center surround statistics and the location features are extracted from each superpixel to classify it as cup or non-cup.
Jun, Cheng, Jiang, Liu, Dacheng, Tao, Fengshou, Yin, Damon Wing Kee, Wong, Yanwu, Xu, Tien Yin, Wong   +6 more
openaire   +2 more sources

Rethinking Unsupervised Neural Superpixel Segmentation

2022 IEEE International Conference on Image Processing (ICIP), 2022
ICIP ...
Eliasof, Moshe, Zikri, Nir Ben, Treister, Eran   +2 more
openaire   +2 more sources

Semi-Supervised Hierarchical Semantic Object Parsing

, 2017
Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features.
Amindavar, Hamidreza, Mirakhorli, Jalal
core   +1 more source

A Semantic Segmentation Algorithm Using FCN with Combination of BSLIC

Applied Sciences, 2018
An image semantic segmentation algorithm using fully convolutional network (FCN) integrated with the recently proposed simple linear iterative clustering (SLIC) that is based on boundary term (BSLIC) is developed.
Wei Zhao, Haodi Zhang, Yujin Yan, Yi Fu, Hai Wang   +4 more
doaj   +1 more source

Semantic Segmentation of High-Resolution Remote Sensing Imagery via an End-to-End Graph Attention Network With Superpixel Embedding

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Semantic segmentation of high-resolution remote sensing images is crucial in ecological evaluation, natural resource surveys, etc. Compared with CNN-based and transformer-based methods, graph neural networks (GNNs) have drawn increasing attention because
Ying Tang, Xiangyun Hu, Tao Ke, Mi Zhang
doaj   +1 more source

Superpixel Convolutional Networks using Bilateral Inceptions

, 2016
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new 'bilateral inception' module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between ...
A Adams, ES Gastal, J Domke, JB Tenenbaum, K He, M Kiefel, R Achanta, S Gould, S He, S Nowozin, S Paris, T-Y Lin   +11 more
core   +1 more source

Monitoring of Crustose Coralline Algae Using Low‐Altitude Unmanned Aerial Vehicles in Intertidal Reefs

Remote Sensing in Ecology and Conservation, EarlyView.
High‐resolution visible‐light imagery from low‐altitude unmanned aerial vehicles, combined with superpixel segmentation and a Random Forest classifier, provides an efficient and scalable framework for mapping and monitoring crustose coralline algae and reef habitats.
Po‐Chien Lin, Han‐Yang Yeh, Zhi‐Cheng Huang   +2 more
wiley   +1 more source

Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

, 2017
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving.
David, Philip, Gong, Boqing, Zhang, Yang
core   +1 more source

Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments

Small, EarlyView.
This study presents an interpretable, lightweight hybrid deep learning model for real‐time analysis of breast cancer histopathology in IoMT‐enabled diagnostic systems. By integrating MobileNetV2 and EfficientNet‐B0 with a novel contextual recurrent attention module (CRAM), the framework achieves near‐perfect accuracy while providing transparent Grad ...
Roseline Oluwaseun Ogundokun, Rotimi‐Williams Bello, Pius Adewale Owolawi, Rytis Maskeliūnas, Abdulsatar Abduljabbar Sultan   +4 more
wiley   +1 more source

A deep learning‐enabled toolkit for the 3D segmentation of ventricular cardiomyocytes

The Journal of Physiology, EarlyView.
Abstract figure legend 3D cardiomyocyte segmentation enables comprehensive analyses of myocardial microstructure in health and disease; however, it is technically demanding. We present an open‐source toolkit for this task, which reduces challenges associated with sample preparation, image restoration, segmentation and proofreading.
Joachim Greiner, Fabio Frangiamore, Frédéric Sonak, Josef Madl, Thomas Seidel, Peter Kohl, Eva A. Rog‐Zielinska   +6 more
wiley   +1 more source