Deep Learning Underwater Image Color Correction and Contrast Enhancement Based on Hue Preservation

Yeh, Chia‐Hung; Huang, Chih-Hsiang; Lin, Chu-Han

doi:10.1109/ut.2019.8734469

Cited by 11 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main feature of the limited contrast adaptive histogram equalization algorithm (CLAHE) is that it limits the contrast [12], overcomes the problem of excessive amplification noise and blocky effect, and mainly enhances the local contrast, thus enhancing the image details [13]. Common CLAHE algorithm enhances R, G and B components respectively in RGB color space, and then combines them into RGB images [14].…”

Section: Improved Limited Contrast Adaptive Histogram Equalization Im...mentioning

confidence: 99%

An Underwater Target Ranging System based on Binocular Vision

Wang¹

2023

FCIS

View full text Add to dashboard Cite

In order to accurately measure the distance and size information of underwater targets, an underwater target ranging and size measurement system based on binocular vision is proposed. Underwater binocular calibration method is used to obtain the underwater parameters of binocular camera, and the underwater images are calibrated to make them coplanar and aligned. The improved CLAHE algorithm is used to process underwater images and improve the image contrast. The parallax map is obtained by SGBM stereo matching algorithm, and the distance and size of the target are measured and calculated according to the parallax map. The results of underwater experiment show that the measurement accuracy of the system is high for the distance and size of the close-range underwater target, and the measurement error conforms to the requirements of underwater experiment.

show abstract

Section: Improved Limited Contrast Adaptive Histogram Equalization Im...mentioning

confidence: 99%

An Underwater Target Ranging System based on Binocular Vision

Wang¹

2023

FCIS

View full text Add to dashboard Cite

show abstract

“…A method to drive the vision autonomous guided vehicle (AVM), the RG color space is combined with CIE L*a*b, along with fuzzy intrusion using fast R-CNN, increases the ability of color sign recognition [4]. To solve the problem of color contrast and distortion which is usually observed in underwater images, a method of using CNN for converting the image to gray scale and to restore hue is been proposed [5]. To increase the generalization ability of texture-based image classification, data augmentation of deep learning is applied, the method significantly increases the accuracy [6].…”

Section: Related Workmentioning

confidence: 99%

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

Rao¹,

Kapanaiah²

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Advancements in sensors and image acquisition devices lead to tremendous increase in creation of unlabeled database of images, and traditional image retrieval approaches are inefficient in retrieving semantic images. Neural network is emerging as popular method to solve most of the state-of-the-art problems in filling the gap between low level features and high level semantics. Convolution neural network (CNN) is a category of neural network which automatically extracts the important features without any human intervention, with considerably reduced set of parameters. In this paper, a model is generated using CNN (VGG-16) architecture which combines convolution and max pooling layers at different levels using effective regularization and transfer learning with data augmentation. The effectiveness of proposed model is demonstrated on benchmarking Caltech 101 and 256 datasets. The results obtained have proven the capacity of model in understanding high level semantics and outperformed several contemporary techniques.

show abstract

“…In recent years, the research on underwater image restoration has mostly focused on the application of mathematical methods such as depth neural network to image processing [14]- [21]. Studies on degenerate models mainly includes: Professor Hou and his colleagues proposed and studied the degradation model [22]- [24] and image restoration [25], [26]of undersea turbulence in various ocean imaging environments; Mohua [27] proposed a new image formation model for image restoration; In my previous papers, the underwater imaging degradation model based on beam propagation is also established for obtaining the point spread function (PSF) [28].…”

Section: Introductionmentioning

confidence: 99%

A New Degradation Model for Imaging in Natural Water and Validation Through Image Recovery

2019

View full text Add to dashboard Cite

Scattering and turbulence are the main factors affecting imaging in natural water environment. A new model for underwater turbulent degradation is obtained by calculating the scattering transfer factors including the intensity distribution of beam propagation, turbulent fluid medium and suspended particle. In order to verify the proposed model, a controlled laboratory simulation system of turbulent water is established, from which the degradation transfer factor is measured and compared by image restoration and reconstruction. The new model is also applied for field tests in natural ocean water. Experimental results show that based on the proposed model, effect of image restoration and reconstruction can be substantially improved, which proves the correctness and validity of the model.

show abstract

Deep Learning Underwater Image Color Correction and Contrast Enhancement Based on Hue Preservation

Cited by 11 publications

References 8 publications

An Underwater Target Ranging System based on Binocular Vision

An Underwater Target Ranging System based on Binocular Vision

Learning Semantic Features for Classifying Very Large Image Datasets Using Convolution Neural Network

A New Degradation Model for Imaging in Natural Water and Validation Through Image Recovery

Contact Info

Product

Resources

About