Scoping review on automatic color equalization algorithm

Plutino, Alice; Casiraghi, Elena; Rizzi, Alessandro

doi:10.1117/1.jei.30.2.020901

Cited by 11 publications

(6 citation statements)

References 218 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of underwater images presents challenges such as color bias, unclear image quality, and image quality degradation 54 . Methods for enhancing underwater image have been developed, including the histogram-based method, which can improve the visual appearance by manipulating pixels directly without regard to the imaging principle 55 , 56 . In future studies, methods for enhancing underwater image quality should be applied.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-based image classification of turtles imported into Korea

Baek,

Kim,

Kim

2023

Sci Rep

View full text Add to dashboard Cite

Although turtles play a key role in maintaining healthy and balanced environments, these are endangered due to global trade to meet the high demand for food, medicine, and pets in Asia. In addition, imported non-native turtles have been controlled as alien invasive species in various countries, including Korea. Therefore, a rapid and accurate classification of imported turtles is needed to conserve and detect those in native ecosystems. In this study, eight Single Shot MultiBox Detector (SSD) models using different backbone networks were used to classify 36 imported turtles in Korea. The images of these species were collected from Google and were identified using morphological features. Then, these were divided into 70% for training, 15% for validation, and 15% for test sets. In addition, data augmentation was applied to the training set to prevent overfitting. Among the eight models, the Resnet18 model showed the highest mean Average Precision (mAP) at 88.1% and the fastest inference time at 0.024 s. The average correct classification rate of 36 turtles in this model was 82.8%. The results of this study could help in management of the turtle trade, specifically in improving detection of alien invasive species in the wild.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning-based image classification of turtles imported into Korea

Baek,

Kim,

Kim

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The ACE algorithm consists of two steps: (1) the adjustment of the color and space of the image to complete the correction of color difference; (2) the dynamic expansion of the corrected image [ 24 ]. Its calculation formula is as follows:

…”

Section: Multi-jet Image Processingmentioning

confidence: 99%

State Recognition of Multi-Nozzle Electrospinning Based on Image Processing

et al. 2023

View full text Add to dashboard Cite

The online monitoring of a multi-jet electrospinning process is critical to the achievement of stable mass electrospinning for industrial applications. In this study, the construction of an ejection state recognition system of a multi-jet electrospinning process based on image processing is reported. The ejection behaviors regarding multi-nozzle electrospinning were recorded by CMOS industrial cameras in real time. The characteristic information regarding the multi-jet cone tip was obtained by processing the images regarding Roberts operator edge detection, Hough transform line detection, and mask histogram analysis. The jet anomalies of the hanging droplets in the nozzle outlet area could be obtained and identified by the vision. The identification accuracy towards the target hanging droplets was more than 85%. This work reports the intelligent control of large-scale multi-nozzle electrospinning equipment.

show abstract

“…As described in Ref. [8], it has been successfully applied in several fields, such as for fine art and photographic prints [29], fresco recovery [30], assessment for digital interfaces [31], and digital film restoration [28,32].…”

Section: Automatic Color Equalizationmentioning

confidence: 99%

Three-Dimensional Adaptive Digital Halftoning

Sarti¹,

Plutino²,

Rizzi³

2022

jist

View full text Add to dashboard Cite

The automatic color equalization (ACE) algorithm, part of the Retinex-derived family of spatial color algorithms (SCAs), is an image enhancement algorithm that mimics the adjustment behavior of the human visual system (HVS). It is commonly used on a unique channel for black & white images or independently on the three channels for color images. In this work, we introduce a novel application of ACE on hyperspectral images, referred to as HyperspectrACE. Here the goal is not to introduce the most performing hyperspectral image enhancer in the field, but to discuss the performance of a qualitative model of human color sensation when applied on more than the standard RGB channels. For this reason, we present the test of the proposed approach compared with classic ACE and other classic methods, to assess the differences in image dynamic stretching and global and local filtering contrast adjustment.

show abstract

Scoping review on automatic color equalization algorithm

Cited by 11 publications

References 218 publications

Deep learning-based image classification of turtles imported into Korea

Deep learning-based image classification of turtles imported into Korea

State Recognition of Multi-Nozzle Electrospinning Based on Image Processing

Three-Dimensional Adaptive Digital Halftoning

Contact Info

Product

Resources

About