2022 Vol.5 Dec.No4

• Title: Fast defogging method of sea surface image based on deep learning
• Name: Pingping Zeng1，FangJuan Xie2
• Company: 1.Nanchang University College of Science and Technology,Gong Qing,332020, China 2.Department of Physics and Electronic Information Nanchang Normal University Nanchang, 330032, China
• Abstract:

  Aiming at the problem of poor resolution of sea surface image due to the influence of fog, a fast fog removal method based on deep learning is proposed. Feature collection and recognition of sea surface image are realized by combining with deep learning principle, denoising processing is carried out according to the recognition results, and color brightness is adjusted according to the transmission of ocean image, initial image gray histogram parameters are obtained as the basis for haze removal correction, and image haze removal and sharpening processing are carried out based on gray value. Finally, through experiments, it is proved that the fast fog removal method based on deep learning image has high effectiveness, can better improve the clarity of the ocean image, and fully meets the research requirements.

  
  

• Keyword: deep learning; Sea surface image; Image defogging
• DOI: 10.12250/jpciams2022090501
• Citation form: Pingping Zeng.Fast defogging method of sea surface image based on deep learning [J]. Computer Informatization and Mechanical System,2022,Vol.5,pp.1-5

[1] B D K J A ,  B Z Z A ,  B K H A. 2020, Multi angle optimal pattern-based deep learning for automatic facial expression recognition - ScienceDirect. Pattern Recognition Letters, 139(4):157-165.

[2] ZHONG Xiao-li, FAN Ji-liang, Mass Characteristics of Cloud Data Filtering Probability Calculation Model for the Simulation[J]. Computer Simulation, 2019, 36(7):419-422.

[3] Awan FM，Saleem Y，Minerva R，Crespi N. 2020, A Comparative Analysis of Machine/Deep Learning Models for Parking Space Availability Prediction. Sensors, 20(1):322.

[4] Sengupta S，Singh A，Leopold HA， Gulati T，Lakshminarayanan V. 2020, Ophthalmic diagnosis using deep learning with fundus images - A critical review. Artificial intelligence in medicine, 102(Jan.):101758.1-101758.13.

[5] Hossain，MZ Sohel F，Shiratuddin MF，Laga H. 2019,A Comprehensive Survey of Deep Learning for Image Captioning. Acm Computing Surveys, 51(6):1-36.

[6] Graffieti G ,  Maltoni D . 2021,Artifact-Free Single Image Defogging. Atmosphere, 12(5):577.