RedCap: residual encoder-decoder capsule network for holographic image reconstruction

A capsule network, as an advanced technique in deep learning, is designed to overcome information loss in the pooling operation and internal data representation of a convolutional neural network (CNN). It has shown promising results in several applications, such as digit recognition and image segmen...

Full description

Saved in:
Bibliographic Details
Published in:Optics express 2020-02, Vol.28 (4), p.4876-4887
Main Authors: Zeng, Tianjiao, So, Hayden K-H, Lam, Edmund Y
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A capsule network, as an advanced technique in deep learning, is designed to overcome information loss in the pooling operation and internal data representation of a convolutional neural network (CNN). It has shown promising results in several applications, such as digit recognition and image segmentation. In this work, we investigate for the first time the use of capsule network in digital holographic reconstruction. The proposed residual encoder-decoder capsule network, which we call RedCap, uses a novel windowed spatial dynamic routing algorithm and residual capsule block, which extends the idea of a residual block. Compared with the CNN-based neural network, RedCap exhibits much better experimental results in digital holographic reconstruction, while having a dramatic 75% reduction in the number of parameters. It indicates that RedCap is more efficient in the way it processes data and requires a much less memory storage for the learned model, which therefore makes it possible to be applied to some challenging situations with limited computational resources, such as portable devices.
ISSN:1094-4087
1094-4087
DOI:10.1364/OE.383350