A Novel CS 2G-starlet denoising method for high noise astronomical image

Zhang, Jie; Wang, Fengxian; Zhang, Huanlong; Shi, Xiaoping

doi:10.1016/j.optlastec.2023.109334

Cited by 8 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enhance the accuracy of information retrieval from images, researchers have developed various processing methods. When the noise intensity is lower than the image signal intensity, the noise can be eliminated as a perturbation of the original image data using image-processing algorithms based on filtering technology [1][2][3][4] or wavelet analysis [5][6][7][8][9][10] . Wavelet analysis, known for its good localization properties in both time and frequency domains, has made it the most effective among various image de-noising techniques.…”

Section: Introductionmentioning

confidence: 99%

Enhancement of laser noise image based on photorefractive nonlinearity of lithium niobate crystals

Gao,

Han

et al. 2024

Preprint

View full text Add to dashboard Cite

Enhancement of laser noise image based on stochastic resonance process in lithium niobate crystals is studied theoretically and experimentally in this paper. A noise function based on the refractive change in crystal is proposed for the numerical simulation. The simulation results show that the presence of noise can induce the optical nonlinearity in lithium niobate crystals to change from self-defocusing to self-focusing. Under an appropriate noise intensity, the strongest stochastic resonance process can occur, resulting in restored the image signal submerged by noise eventually. There is a good agreement between the experimental and numerical results. When a single noise image is transmitting in a nonlinear crystal system, the stochastic resonance process is considered to be the result of the self-coupling between the scattered noise and the transmitted signal when the noise and signal are scattered simultaneously in the crystal. The research results in this paper can provide theoretical and experimental guidance for the early acquisition and post-processing of images containing inherent noise, and will promote the industrialization of noise information sensing technology largely.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancement of laser noise image based on photorefractive nonlinearity of lithium niobate crystals

Gao,

Han

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning (Kumar et al, 2022 ; Lin et al, 2022 ; Zhang et al, 2023 ; Han et al, 2024a , b ; Lakatos et al, 2024 ) and neural network techniques (Sun et al, 2023 , 2024a , b ) have flourished in the field of computer vision, and object detection methods based on these techniques have been widely used in industrial scenarios (Qi et al, 2020 ). Compared to traditional computer vision methods deep learning uses multiple layers of complex nonlinear mapping (Nagamine et al, 2016 ), these methods can learn more complex features and improve the accuracy and speed of detection.…”

Section: Introductionmentioning

confidence: 99%

A new online detection method of tobacco impurities for tobacco robot

Zhang,

Li,

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

In the tobacco industry, impurity detection is an important prerequisite for ensuring the quality of tobacco. However, in the actual production process, the complex background environment and the variability of impurity shapes can affect the accuracy of impurity detection by tobacco robots, which leads to a decrease in product quality and an increase in health risks. To address this problem, we propose a new online detection method of tobacco impurities for tobacco robot. Firstly, a BCFormer attention mechanism module is designed to effectively mitigate the interference of irrelevant information in the image and improve the network's ability to identify regions of interest. Secondly, a Dual Feature Aggregation (DFA) module is designed and added to Neck to improve the accuracy of tobacco impurities detection by augmenting the fused feature maps with deep semantic and surface location data. Finally, to address the problem that the traditional loss function cannot accurately reflect the distance between two bounding boxes, this paper proposes an optimized loss function to more accurately assess the quality of the bounding boxes. To evaluate the effectiveness of the algorithm, this paper creates a dataset specifically designed to detect tobacco impurities. Experimental results show that the algorithm performs well in identifying tobacco impurities. Our algorithm improved the mAP value by about 3.01% compared to the traditional YOLOX method. The real-time processing efficiency of the model is as high as 41 frames per second, which makes it ideal for automated inspection of tobacco production lines and effectively solves the problem of tobacco impurity detection.

show abstract