Optimized initial weight in quantum-inspired neural network for compressing computer-generated holograms

Hou, Shenhua; Yang, Gen; Xie, Haiyan

doi:10.1117/1.oe.58.5.053105

Cited by 3 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To estimate the compression and recovery image quality of CGH under different processing methods, we used CR, 17 MSE, 1 , 2 , 9 peak signal-to-noise (PSNR), 1 , 2 , 9 , 11 , 17 and structural similarity index measure (SSIM) 17 , 33 , 36 as our evaluation criteria: CR=SoSc,MSE=1W×H∑r=1W∑c=1H|f(r,c)−f¯(r,c)|2,PSNR=10 log10MAXI2MSE,SSIM(f,f¯)=(2ufuf¯+c1)(2δ…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…To estimate the compression and recovery image quality of CGH under different processing methods, we used CR, 17 MSE, 1,2,9 peak signal-to-noise (PSNR), 1,2,9,11,17 and structural similarity index measure (SSIM) 17,33,36 as our evaluation criteria: E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 5 ; 1 1 6 ; 6 5 6…”

Section: Objective Quality Metricsmentioning

confidence: 99%

“…In computer holography, a computer-generated hologram (CGH) contains a large quantity of information, including the amplitude and phase information of an object, which requires a large amount of space for storage and bandwidth for transmission 1 , 2 and becomes an obstacle to develop the holographic applications 3 , 4 . Therefore, it is necessary to find an efficient method to compress the holographic data while considering the reconstructed image quality of the compressed and transmitted CGH.…”

Section: Introductionmentioning

confidence: 99%

“…In Refs. 1 and 2, QINN is used to compress CGH that has shown the better quality of the reconstructed CGH compared to the convolutional neural network (CNN) while using fewer learning iterations. However, as far as we know, the current methods cannot properly reconstruct CGH when the compression ratio (CR) is higher and hence restrict the fast transmission of CGH.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast transmission of computer-generated hologram with compressed sensing and quantum-inspired neural network

2023

View full text Add to dashboard Cite

A two-stage compression framework for computer-generated hologram (CGH) with compressed sensing (CS) and quantum-inspired neural network (QINN) is proposed. A deep learning-based CS model is applied to sample the CGH at sub-Nyquist rates to generate measurements, and its more compact and representative information using interblock information is further extracted by QINN. With two-stage compression framework, the CGH is greatly compressed and suitable for storage and transmission. Experimental results demonstrate that our proposed two-stage compression framework can preserve more important holographic information during the compression, thus significantly improving the overall quality of reconstructed images compared to only using CS or QINN.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

“…To estimate the compression and recovery image quality of CGH under different processing methods, we used CR, 17 MSE, 1,2,9 peak signal-to-noise (PSNR), 1,2,9,11,17 and structural similarity index measure (SSIM) 17,33,36 as our evaluation criteria: E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 5 ; 1 1 6 ; 6 5 6…”

Section: Objective Quality Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast transmission of computer-generated hologram with compressed sensing and quantum-inspired neural network

2023

View full text Add to dashboard Cite

show abstract

“…When comparing the previous QNNs to Res-HQCNN, that notice the trace value of the input state 𝜌 𝑘+1 𝑖𝑛 for some k changes as a result of the addition operation in the residual block structure [14]. Indicate k=2, 𝜌 2 𝑖𝑛 = �𝜌 1 𝑖𝑛 ⨂�0⟩ 𝑢 1 −𝑢 0 ⟨0�� + 𝜌 1 𝑜𝑢𝑡 , and 𝜌 3 𝑖𝑛 = �𝜌 2 𝑖𝑛 ⨂�0⟩ 𝑢 2 −𝑢 1 ⟨0�� + 𝜌 2 𝑜𝑢𝑡 , next trace values of the 𝜌 2 𝑖𝑛 and 𝜌 3 𝑖𝑛 are the 2 and 4, respectively.…”

Section: A Architecture Model Of Res-hqcnnmentioning

confidence: 99%

Modified Deep Residual Quantum Computing Optimization Technique for IoT Platform

El-Aziz¹,

Rayan²,

Shahin³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Internet of Things (IoT) is defined as millions of interconnections between wireless devices to obtain data globally. The multiple data are targeting to observe the data through a common platform, and then it becomes essential to investigate accuracy for realizing the best IoT platform. To address the growing demand for time-sensitive data analysis and real-time decision-making, accuracy in IoT data collecting has become critical. The Res-HQCNN is a hybrid quantum-classical neural network with deep residual learning. The model is qualified in an end-to-end analog method in a traditional neural network, backpropagation is used. To discover the Res-HQCNN efficiency to perform on the classical computer, there has been a lot of investigation into quantum data with or without noise. Then focus on the application of the artificial neural network to analyze the dangers to these IoT networks. For data recording purposes, to undertake in-depth analysis on the threat severity, kind, and source, a model is trained using recurrent and convolutional neural networks. The intrusion detection system (IDS) explored in this study has a success rate of 99% based on the empirical data supplied to the model. Due to irregularly distributed robust execution, larger affectability for the introduction of authority dimension, steadiness, and the extremely large crucial area, a quantum hash function work has been proposed as an amazing method for secure communication between the IoT and cloud.

show abstract

3D information transmission of a computer-generated hologram using a quantum compensation hybrid neural network

Hu,

Yang,

Xie

2024

Opt. Express

View full text Add to dashboard Cite

A computer-generated hologram compression and transmission system is designed. The system uses a hybrid neural network based on quantum compensation to compress and decompress computer-generated holograms and uses a quantization method and Huffman coding to encode the compressed holograms for transmission. The receiving side decodes and decompresses the data stream to obtain the recovered hologram, which can be used to reconstruct the original object information for 3D image display. Our numerical experiments show that quantum compensation can improve the quality of the reconstructed image. Furthermore, we introduce a quantum compensation factor to describe the strength of quantum compensation and verify experimentally that the quantum compensation module may drive the conventional neural network to converge in fewer training epochs.

show abstract

Optimized initial weight in quantum-inspired neural network for compressing computer-generated holograms

Cited by 3 publications

References 13 publications

Fast transmission of computer-generated hologram with compressed sensing and quantum-inspired neural network

Fast transmission of computer-generated hologram with compressed sensing and quantum-inspired neural network

Modified Deep Residual Quantum Computing Optimization Technique for IoT Platform

3D information transmission of a computer-generated hologram using a quantum compensation hybrid neural network

Contact Info

Product

Resources

About