Image Enhancement Method Research Articles

Colour image enhancement using weighted histogram equalization with improved monarch butterfly optimization

ABSTRACT Image enhancement is a technique for improving the quality of an image so that it can be viewed by both humans and machines. The primary purpose of picture contrast enhancement is to improve the image’s visual quality. Histogram equalisation (HE) is one way to increase contrast. One disadvantage of He is that it does not sustain brightness while increasing contrast since a sdden mean shift occurs during the equalisation process. A new image enhancement method is established with weighted histogram equalisation with Oppositional-based Customised Monarch Butterfly Optimisation (OCMBO), for better visual perception and improving image quality. The collected input image is in RGB format. This image is then converted into YCbCr format for contrast stretching. In digital image processing, the YCbCr colour space is often used to take advantage of the lower resolution capability of the human visual system for colour concerning luminosity. The weighted histogram equalisation with Oppositional-based Customised Monarch Butterfly Optimisation (OCMBO) is applied to the converted image’s Y component, and then the Cr, Cb and modified Y components are combined back into RGB format.

Cooling-excited infrared thermography for enhancing the detection of concrete filled steel tube interfacial debonding at concrete hydration

Interfacial Debonding occurring in concrete-filled steel Tube (CFST) arch bridges during construction is a critical issue, which can reduce the CFST carrying capacity and thus degrade the operational lifespan of the bridge. Timely detection of this type of defect during bridge construction can be highly cost-effective but rare sensing technology was reported for detection at this stage. Infrared thermography has been recognized as a potential detection method but still faces the challenge of low thermal contrast developed from concrete hydration. This research investigates the feasibility of using hydration heat as an internal heat source and proposes water-spray cooling as an external excitation to improve infrared debonding detection. The experimental study is carried out to investigate the detectability enhancement before and after the cooling excitation in terms of different debonding sizes and thicknesses. An image enhancement method is then proposed for debonding visualization based on the temperature difference matrix. In addition, the numerical simulation is conducted to analyze the cooling effect regarding the excitation intensity variation. The findings reveal that the thermal contrast of debonding ranges from 0.1 to 0.35℃ before cooling excitation and is enhanced by 2–3 times thereafter. In addition, the developed maximum thermal contrast of debonding can be characterized through a linear relationship to the cooling excitation intensity based on numerical analysis. The proposed method shows significant feasibility for early detection of debonding in CFST during arch bridge construction, which enables a new potential for structural inspection.

Dark Light Image-Enhancement Method Based on Multiple Self-Encoding Prior Collaborative Constraints

The purpose of dark image enhancement is to restore dark images to visual images under normal lighting conditions. Due to the ill-posedness of the enhancement process, previous enhancement algorithms often have overexposure, underexposure, noise increases and artifacts when dealing with complex and changeable images, and the robustness is poor. This article proposes a new enhancement approach consisting in constructing a dim light enhancement network with more robustness and rich detail features through the collaborative constraint of multiple self-coding priors (CCMP). Specifically, our model consists of two prior modules and an enhancement module. The former learns the feature distribution of the dark light image under normal exposure as an a priori term of the enhancement process through multiple specific autoencoders, implicitly measures the enhancement quality and drives the network to approach the truth value. The latter fits the curve mapping of the enhancement process as a fidelity term to restore global illumination and local details. Through experiments, we concluded that the new method proposed in this article can achieve more excellent quantitative and qualitative results, improve detail contrast, reduce artifacts and noise, and is suitable for dark light enhancement in multiple scenes.

WaterPairs: a paired dataset for underwater image enhancement and underwater object detection

Due to its importance in marine engineering and aquatic robotics, underwater image enhancement works as a preprocessing step to improve the performance of high-level vision tasks such as underwater object detection and recognition. Although several studies exhibit that underwater image enhancement algorithms can boost the detection accuracy of detectors, no work has focused on studying the relationship between these two tasks. This is mainly because current underwater datasets lack either bounding box annotations or high-quality reference images, based on which detection accuracy or image quality assessment metrics are calculated. To examine how underwater image enhancement methods affect underwater object detection tasks, we provide a large-scale underwater object detection dataset with both bounding box annotations and high-quality reference images, namely, the WaterPairs dataset. The WaterPairs dataset offers a platform for researchers to comprehensively study the influence of underwater image enhancement algorithms on underwater object detection tasks. We will release our dataset at https://github.com/IanDragon/WaterPairs once this paper is accepted.

A lightness-aware loss for low-light image enhancement

Current low-light image enhancement methods have made great progress on improving the visibility of low-light images. Nevertheless, they pay less attention to preserving visual naturalness and therefore often introduce over-enhancement and local artifacts into their results. To address this issue, it is useful to introduce additional multi-view information of an image into enhancement models, such as illumination distribution. In this context, we propose a simple but effective loss term that expects the originally bright regions in input images and their corresponding enhanced images to be as similar as possible. Via fully exploring the illumination distribution of an image, the loss term makes enhancement models to know which regions should be preserved during training. Therefore, the unnatural effects in output images can be effectively relieved. In our experiments, we incorporate our loss term into several recently proposed low-light image enhancement models. The experimental results on multiple datasets show that over-enhancement and local artifacts can be effectively suppressed by using our loss term.

An in-situ image enhancement method for the detection of marine organisms by remotely operated vehicles

Abstract With the assistance of the visual system, remote operated vehicles (ROVs) can replace frogmen to achieve safer and more efficient capturing of marine organisms. However, the selective absorption and scattering of light lead to a decrease in the visual quality of underwater images, which hinders ROV operators from observing the operating environment. Unfortunately, most image enhancement methods only focus on image color correction rather than perceptual enhancement, which in turn prevents the object detector from quickly locating the target. Therefore, a visual-enhanced and detection-friendly underwater image enhancement method is needed. In this paper, an underwater image enhancement method called in-situ enhancement is proposed to improve the semantic information of the visual hierarchy based on current scene information in multiple stages. Mapping the underwater image to its dual space allows the enhancement equation to be applied to severely degraded underwater scenes. Moreover, it is also a detection-friendly method and has good generalization in both visual quality improvement and object detection. The experimental results show that in different underwater datasets, the in-situ enhancement effectively improves the visual quality of underwater images, and its enhanced results train different object detectors with high detection accuracy.

Weighted Fusion of Pre-processing Techniques for Neural Network-based Image Haze Removal

Haze is the natural phenomenon, which affects an image's air light and visibility. It creates a layer that hides the information in an acquired hazy image and decreases its visibility. Hazy scenarios are mostly seen in the transportation sector and remote sensing. It affects the quality of an image captured. Haze is one of the major hurdles in several computer vision applications. This paper observes and analyses different methods of haze removal via image enhancement techniques. Proposes the weighted average of the image enhancement methods to generate the enhanced hazy input image as the initial step. These enhanced images do train the neural network to estimate transmission map as well as atmospheric light, used for haze removal from images. The proposed method is experimented with 135 hazy images from three standard datasets, alias I-Haze, NH-Haze, and O-Haze (45 images from each total 135 hazy images). It gives clearer results than a few similar existing haze removal techniques. Also, the experimental results tested with performance metrics Entropy PSNR, and SSIM have demonstrated the effectiveness of the proposed haze removal method having weighted fusion of pre-processing techniques.

Improving the perception of low-light enhanced images.

Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric -such as PSNR or SSIM- on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods -that focus on distortion minimization- cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.

Step‐by‐step image enhancement method for PTZ‐camera based crack detection in expressways

AbstractCracks on highway pavement surfaces are among the most critical problems affecting expressway maintenance. A pan/tilt/zoom (PTZ) camera‐based crack detection method was proposed, owing to the intelligent traffic system (ITS) development of an expressway network in China. However, the quality of the crack image decreased at distant PTZ camera distances, resulting in a low mean average precision (MVP) for crack detection, which is difficult to implement in civil engineering. A weighted superposition‐based crack enhancement algorithm for crack detection was proposed to enhance crack images collected by PTZ cameras. Compared with the poor generalization ability of using a single image enhancement method, this method combines the advantages and characteristics of multiple image enhancement methods, thereby ensuring the quality of crack images. This enhances the visual characteristics of the cracks to adapt to various illuminations, thereby improving the crack detection rate and providing scientific and technological reserves for its application in highway maintenance engineering. Further comparison tests on crack detection for pavement crack images collected from the China G4/Jingshi Highway demonstrated that the proposed method was efficient in detecting is efficiently to detect cracks, achieving 96% MAP and 94% F1 values after enhancing the crack images, thereby providing an objective and promising means of crack detection using PTZ cameras.

A DoLP image enhancement method based on DGIF and multi-channel difference SNR estimation

A DoLP image enhancement method based on DGIF and multi-channel difference SNR estimation

Deep-CNN based knowledge learning with Beluga Whale optimization using chaogram transformation using intelligent sensors for speech emotion recognition

In recent times, there has been a lot of focus placed on speech emotion recognition, often known as SER. SER is a fundamental approach to emotional human-machine interaction. Utilising DCNNs has resulted in significant advancements being made, notably with regard to the learning of high-level characteristics for SER. However, one of the primary challenges that arises when applying deep neural networks to SER is the problem of overfitting, which occurs commonly when too many parameters are chosen using insufficiently large datasets. The majority of the research that has been done to attempt to solve this problem has focused on translating the audio input into a picture and employing transfer learning methods. According to research, the patterns generated in this region include significant emotional aspects of the speaker. A new speech signal format called Chaogram was designed to project these patterns, which would result in three channels like RGB images, in order to give an input that works with VGG-based Deep-CNNs. The original phase space is then used to reconstruct the voice samples in a three-dimensional space. In the subsequent stage, the Chaogram photos' finer details were accentuated by image enhancing techniques. To learn Chaogram's high-level features and emotion classifications, the Visual Geometry Group (VGG) deep convolutional neural network (DCNN) is employed after being pre-trained on the massive ImageNet dataset using intelligent sensors. We next apply transfer learning to our datasets to further improve the provided model, which we combine with the proposed model. To enhance the hyper-parameter layout of architecture-determined CNNs, a new Deep-CNN with BWO (Beluga Whale Optimization) is introduced. In order to apply Deep–CNN–KL and to the field of SER, thispropose a new method of representing speech signals, which we call Chaograms, by mapping the signal onto a 2D image. On two publicly available emotion datasets, these findings demonstrate the ability of the proposed approach, which has the potential to significantly improve SER applications: EMO-DB and eNTERFACE05. Image enhancement methods that place more emphasis on such features may lead to more precise classification in the performance analysis. Classification accuracy can be considerably improved by adapting these images to work with the pre-trained Deep-CNN inputs.

Underwater image enhancement method based on a cross attention mechanism

Underwater image enhancement method based on a cross attention mechanism

Bearing fault diagnosis based on the feature enhancement of improved mean differential SDP images★ ★This work is supported by National Natural Science Foundation of China [No. 61603149]; Shandong Province Natural Science Foundation [No. ZR2023MF102

In the fault diagnosis of mechanical equipment, vibrational signals often contain noise. In order to solve the problem of rolling bearing fault diagnosis under the influence of noise, an image enhancement method based on mean difference images is proposed. Convert one-dimensional time series into two-dimensional image data by using the symmetrized dot pattern method. The data are processed and grouped by variational mode decomposition to obtain a mean image with stable features. A feature enhancement method based on improved mean difference images is used to achieve data mining of fault features. The improved Canberra distance is used as the classification basis to realize the accurate classification of rolling bearing faults. Finally, the classification effect of the method is verified by experiments. The experimental results show that the image enhancement method proposed in this paper can improve fault features in the image and has a good anti-noise ability.

A novel slime mold algorithm for grayscale and color image contrast enhancement

Image enhancement is a key step in image pre-processing. To address the problem of low quality and visual effect of images under low illumination conditions, this paper proposes an image enhancement method with hyperbolic oscillation factor and quadratic interpolation of slime mold algorithm (SSMA) in non-complete beta function dynamically looking to adjust the grayscale curve. The new strategy mainly proposes three different improvement strategies for the problem that the classical slime mold algorithm has low convergence accuracy and can easily fall into local optimum. Experimenting the proposed SSMA with other conventional and latest algorithms on the CEC2017 benchmark function and low-illumination standard dataset. The experimental results show that the convergence accuracy and convergence speed of SSMA are better than other algorithms. The proposed SSMA-optimized image enhancement algorithm effectively enhances the image brightness while preserving more details of the image, which is significantly better than other algorithms for image enhancement.

Image enhancement method for low-light pipeline weld X-ray radiographs based on weakly supervised deep learning

X-ray inspection is the most intuitive approach for the non-destructive testing (NDT) of pipeline weld defects to avoid pipeline safety accidents. However, identifying pipeline weld defects in dark X-ray images is difficult due to low greyscale values. This paper proposed a weakly supervised network for denoising and enhancing low-light pipeline weld X-ray images. First, a semi-supervised network based on an improved Retinex-Net which implemented by self-paced learning was proposed to enhance illumination, yielding more natural X-ray images without artifacts, distortion, and overexposure. A new denoising network constrained by the X-ray images themselves was designed to achieve denoising while preserving the image detail. Qualitative comparison and quantitative analysis indicated that the proposed method outperformed other industrial image enhancement methods used for pipeline weld detection in terms of both subjective visual effects and objective metric values.

A real-world underwater image enhancement method based on multi-color space and two-stage adaptive fusion

A real-world underwater image enhancement method based on multi-color space and two-stage adaptive fusion

Multi-scale dense spatially-adaptive residual distillation network for lightweight underwater image super-resolution

Underwater images are typically of poor quality, lacking texture and edge information, and are blurry and full of artifacts, which restricts the performance of subsequent tasks such as underwater object detection, and path planning for underwater unmanned submersible vehicles (UUVs). Additionally, the limitation of underwater equipment, most existing image enhancement and super-resolution methods cannot be implemented directly. Hence, developing a weightless technique for improving the resolution of submerged images while balancing performance and parameters is vital. In this paper, a multi-scale dense spatially-adaptive residual distillation network (MDSRDN) is proposed aiming at obtaining high-quality (HR) underwater images with odd parameters and fast running time. In particular, a multi-scale dense spatially-adaptive residual distillation module (MDSRD) is developed to facilitate the multi-scale global-to-local feature extraction like a multi-head transformer and enriching spatial attention maps. By introducing a spatial feature transformer layer (SFT layer) and residual spatial-adaptive feature attention (RSFA), an enhancing attention map for spatially-adaptive feature modulation is generated. Furthermore, to maintain the network lightweight enough, blue separable convolution (BS-Conv) and distillation module are applied. Extensive experimental results illustrate the superiority of MDSDRN in underwater image super-resolution reconstruction, which can achieve a great balance between parameters (only 0.32M), multi-adds (only 13G), and performance (26.38 dB on PSNR in USR-248) with the scale of ×4.

Underwater Image Enhancement With Reinforcement Learning

In this article, we develop an underwater image enhancement framework based on reinforcement learning. To do this, we model the underwater image enhancement as a Markov decision process (MDP), in which states are represented by image feature maps, actions are represented by image enhancement methods, and rewards are represented by image quality improvements. The MDP trained with reinforcement learning can characterize a sequence of enhanced results for an underwater image. At each step of the MDP, a state transitions from one to another according to an action of image enhancement selected by a deep Q network. The final enhanced image in the sequence is obtained with respect to the biggest overall image quality improvement. In this manner, our reinforcement learning framework effectively organizes a sequence of image enhancement methods in a principled manner. In contrast to the black box processing schemes of deep learning methods, our reinforcement learning framework gives a sequence of specific actions, which are transparent from the implementation perspective. Benefiting from the exploration and exploitation training fashion, our reinforcement learning framework possibly generates enhanced images that are of better quality than reference images. Experimental results validate the effectiveness of our reinforcement learning framework in underwater image enhancement. The code and detailed results are available at https://gitee.com/sunshixin_upc/underwater-image-enhancement-with-reinforcement-learning.

Research on Medical Image Enhancement Method Based on Conditional Entropy Generative Adversarial Networks

Abstract This study proposes an image enhancement method combining conditional entropy and generative adversarial network, aiming to improve the image quality while avoiding overfitting through the negative training of dependent generative adversarial network and introducing dependent entropy distance loss. Through NIQMC, NIQE and BTMQI evaluation indexes, this paper evaluates the effects of different parameter combinations and image chunk sizes on the enhancement results. It utilizes information entropy as an evaluation index to measure the impact of conditional entropy distance loss. The effectiveness of adversarial learning and conditional entropy in image enhancement is verified by comparing the experimental results. The experiments show that the system can achieve the best image quality of SSIM=0.9852, PSNR=27.58, and SNROI=21.34 with the parameters S=50 and R=4.0%, indicating that the method can effectively retain the detailed information and realism of the Image while enhancing the clarity of the Image, demonstrating a significant performance advantage.

An image enhancement method for cable tunnel inspection robot

Influenced by multiple factors such as low light intensity, dispersed light, excessive dust, and excessive ambient noise inside cable tunnels, the images captured by cable tunnel inspection robots have shortcomings such as low contrast, low pixel values, and high noise. To improve the image quality, this paper proposes an image enhancement method suitable for cable tunnel inspection robot. First, in this paper, a bivariate hybrid optimization module using the alternating direction multiplier method and the adaptive learning rate acceleration SVRG algorithm is constructed to achieve image pre-processing. Second, a feature extraction module combining a U-Net network and a coordinate attention mechanism is constructed to extract features from the original image and the pre-processed image. Third, the progressive feature fusion module and the image recovery module are constructed to fuse the above features and are combined with the original image to obtain the enhanced image. Finally, the pixel compensation module is constructed to compensate for the features of the enhanced image and recover the lost texture details.