Autoencoder-aided measurement of concentration from a single line of speckle

Šehić, Kenan; Dammann, Bernd; Suljagić, Mirza; Karamehmedović, Mirza

doi:10.1364/oe.27.029098

Cited by 3 publications

(1 citation statement)

References 25 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the research level of deep neural network image denoising, a large number of researchers have used a variety of different technologies for research and analysis. Relevant Chinese researchers have proposed an optimized transformation algorithm to solve the “surround” problem, which is mainly based on the combination of hard threshold denoising technology and sub-band related image denoising algorithm, thus, the retention and thinning of image edge features are realized, which further improves the performance of self-encoder depth neural network technology [ 29 , 30 ]; Relevant Japanese researchers gradually threshold denoising algorithm, which mainly establishes the corresponding mathematical model for each sub block through generalized normal distribution, and adopts sparse representation algorithm for specific images [ 31 ].…”

Section: Related Research and Analysis: Analysis Of The Current Situa...mentioning

confidence: 99%

Construction of Home Product Design System Based on Self-Encoder Depth Neural Network

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The traditional home product design system mainly depends on relatively shallow learning network, relatively simple embedded technology and Internet of things technology. The traditional home design system mainly depends on the traditional self-encoder technology. When combined with the deep neural network, this technology has serious defects in the computer vision algorithm, resulting in the serious waste of the corresponding system storage and computing resources, the corresponding system learning efficiency is relatively poor and the learning ability is weak. Based on this, this paper will build a home product design system based on the deep neural network of self-encoder. By improving the sparsity of self-encoder in the process of learning and training, we can further improve the sparsity of the system and further optimize the structure of self-encoder in the design system, The performance of the deep learning model of the design system is further improved through the hierarchical features continuously learned by the self-encoder in the process of home case design. Based on the optimization of the home product design system in this paper, the system effectively improves and improves the accuracy and stability of the internal feature classifier of the system, and improves the overall performance of the furniture design system. In the specific system construction part, based on ZigBee technology and embedded technology as the design carrier, and adhering to the goal of simplicity, intelligence and convenience, this paper designs and constructs the home product design system. The experimental results show that the noise processing level of the proposed home product design system is lower than 4-5db compared with the traditional design system, and the corresponding image classification accuracy is about 4% higher than the traditional design system. Therefore, the experimental results show that the home design system proposed in this paper has obvious advantages.

show abstract

Section: Related Research and Analysis: Analysis Of The Current Situa...mentioning

confidence: 99%