Numerical computation of ocean HABs image enhancement based on empirical mode decomposition and wavelet fusion

Most of the microscopic images of Harmful Algae Blooms (HABs) acquired in marine engineering are subject to blurred cell textures and poor overall clarity due to the effects of seawater impurities, unknown suspended particle deposits and high-speed cell motions. To solve the above problems, a micros...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied intelligence (Dordrecht, Netherlands) Ročník 53; číslo 16; s. 19338 - 19355
Hlavní autori: Wu, Geng-Kun, Zhang, Bei-Ping, Xu, Jie
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.08.2023
Springer Nature B.V
Predmet:
Accuracy
Algae
Artificial Intelligence
Clarity
Computer Science
Edge detection
Feature maps
Filtration
Histograms
Identification
Image acquisition
Image contrast
Image enhancement
Machines
Manufacturing
Marine engineering
Mechanical Engineering
Neural networks
Numerical analysis
Processes
Seawater
Water quality
Harmful algal blooms
Empirical mode decomposition
Dual-image wavelet fusion
Contrast enhancement
ISSN:0924-669X, 1573-7497
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Most of the microscopic images of Harmful Algae Blooms (HABs) acquired in marine engineering are subject to blurred cell textures and poor overall clarity due to the effects of seawater impurities, unknown suspended particle deposits and high-speed cell motions. To solve the above problems, a microscopic image enhancement method based on the recursive-overlapped contrast limited adaptive histogram specification (CLAHS) and dual-image wavelet fusion (RO-CLAHS and DIWF) is proposed in this paper. It combines three main steps: homomorphic filtering, empirical modal feature map extraction, and dual-image wavelet fusion. This method firstly adopts homomorphic filtering to strengthen the illumination uniformity of the entire HABs image, and then obtains an empirical modal feature map of algal cells by an improved empirical modal decomposition method, which highlights the detailed features of algal cells due to histogram stretching, clip limit and grey-level mapping. Finally, this paper proposes a dual-image wavelet fusion method adapted for HAB microscopic images, which integrates the images processed by contrast limited adaptive histogram equalization (CLAHE) with an empirical modal feature map and then achieves the image enhancement effect. The comparison experimental results show that the enhanced microscopic images of HABs by this method presents the best texture clarity and global contrast and improves the accuracy of algae image edge detection significantly.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-023-04502-x