Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

An End-to-End Learning Approach for Subpixel Feature Extraction

Not Accessible

Your library or personal account may give you access

Abstract

We propose a feature extraction method based on Fourier image encoding and a multiscale convolutional neural network, training end-to-end. Our experiments show the method can localize subpixel feature locations from density fields to subpixel accuracy.

© 2023 The Author(s)

PDF Article
More Like This
Depth invariant feature extraction using deep learning in strong scattering

Yangyundou Wang, Zhaosu Lin, Yiming Li, Chuanfei Hu, Hui Yang, Yongxiong Wang, and Min Gu
ETh3C.6 European Conference on Biomedical Optics (ECBO) 2021

Scatter Removal in Dynamic X-Ray Tomography using Learned Robust Features

Siddhant Gautam, Marc L. Klasky, and Saiprasad Ravishankar
JTu4A.12 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2023

Phase Retrieval Method Based on Deep Learning with Single Image Training in Holographic Data Storage

Jianying Hao, Ruixian Chen, Xiao Lin, Tsutomu Shimura, and Xiaodi Tan
IPDP_01 International Symposium on Imaging, Sensing, and Optical Memory (ODS) 2022

Poster Presentation

Media 1: PDF (3434 KB)     
Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.