Image Enhancement Research Articles

Symmetric deformable registration of multimodal brain magnetic resonance images via appearance residuals.

Deformable registration of multimodal brain magnetic resonance images presents significant challenges, primarily due to substantial structural variations between subjects and pronounced differences in appearance across imaging modalities. Here, we propose to symmetrically register images from two modalities based on appearance residuals from one modality to another. Computed with simple subtraction between modalities, the appearance residuals enhance structural details and form a common representation for simplifying multimodal deformable registration. The proposed framework consists of three serially connected modules: (i) an appearance residual module, which learns intensity residual maps between modalities with a cycle-consistent loss; (ii) a deformable registration module, which predicts deformations across subjects based on appearance residuals; and (iii) a deblurring module, which enhances the warped images to match the sharpness of the original images. The proposed method, evaluated on two public datasets (HCP and LEMON), achieves the highest registration accuracy with topology preservation when compared with state-of-the-art methods. Our residual space-guided registration framework, combined with GAN-based image enhancement, provides an effective solution to the challenges of multimodal deformable registration. By mitigating intensity distribution discrepancies and improving image quality, this approach improves registration accuracy and strengthens its potential for clinical application.

FIPNet: Self-supervised low-light image enhancement combining feature and illumination priors

FIPNet: Self-supervised low-light image enhancement combining feature and illumination priors

A Practical Usage of Point Spread Function for Industrial Barcode Image Enhancement

Barcodes are extensively utilized across industries for a variety of critical and routine applications, ranging from logistics to inventory management. Their widespread use has driven a high demand for barcode-reading devices. Optical barcode readers rely heavily on camera performance and image quality to achieve successful decoding. However, the cost of these cameras can vary significantly based on factors such as lighting conditions, working distance, and exposure time. To reduce costs without the need to upgrade cameras or other hardware, a computational enhancement approach leveraging the Point Spread Function (PSF) has been developed. This method enhances image quality, ensuring effective barcode decoding even under suboptimal conditions, thereby offering a cost-efficient solution for industrial applications.

Multi-Region Detection of eye Conjunctiva Images Using DNCNN and YOLOv8 Algorithms

Artificial intelligence is encountered in many areas today. It makes our lives easier with its use in our daily lives. With the advancement of medical big data and artificial intelligence, eye images have begun to be used in the detection of endocrine, cardiovascular, neurological, renal, hematological and many other diseases. It is possible to find more connections between systemic disorders and eye disorders and apply them to increase the effectiveness of artificial intelligence. The eye is an anatomically complex organ. Detection of the conjunctiva regions of the eye generally plays an important role in the diagnosis of eye diseases and applications related to eye health. The conjunctiva is a thin membrane tissue that covers the inner surface of the eyelids and the white part of the eye. Detection and analysis of this region is used in the examination of inflammation, redness, dryness and other disorders in the eye. The relevant regions were found using conjunctiva images in the study. Conjunctiva region detection Images were taken from a public database and enhanced with the image enhancement method DNCNN. The YOLO algorithm is applied to raw images and DNCNN enhanced images separately using the same parameters. As a result, the effect of the deep learning based method on finding the truth in images is presented with F1-confidence curve, precision-confidence curve, recall-confidence curve, precision-recall curve and confusion matrix metrics. In the proposed method, the mAP value is given as 0.984 in all classes.

Underwater image enhancement via adaptive white-balancing and multi-restoration image fusion

Underwater image enhancement via adaptive white-balancing and multi-restoration image fusion

CPDM: Content-preserving diffusion model for underwater image enhancement

Underwater image enhancement (UIE) is challenging since image degradation in aquatic environments is complicated and changing over time. Existing mainstream methods rely on either physical-model or data-driven, suffering from performance bottlenecks due to changes in imaging conditions or training instability. In this article, we attempt to adapt the diffusion model to the UIE task and propose a Content-Preserving Diffusion Model (CPDM) to address the above challenges. CPDM first leverages a diffusion model as its fundamental model for stable training and then designs a content-preserving framework to deal with changes in imaging conditions. Specifically, we construct a conditional input module by adopting both the raw image and the difference between the raw and noisy images as the input at each time step of the diffusion process, which can enhance the model’s adaptability by considering the changes involving the raw images in underwater environments. To preserve the essential content of the raw images, we construct a content compensation module for content-aware training by extracting low-level image features of the raw images as compensation for each down block. We conducted tests on the LSUI, UIEB, and EUVP datasets, and the results show that CPDM outperforms state-of-the-art methods in both subjective and objective metrics, achieving the best overall performance. The GitHub link for the code is https://github.com/GZHU-DVL/CPDM.

Enhancing Image Quality With Deep Learning: Techniques And Applications

The emergence of deep learning has transformed numerous fields, particularly image processing, where it has substantially enhanced image quality. This paper provides a structured overview of the objectives, methods, results, and conclusions of deep learning techniques for image enhancement. It examines deep learning methodologies and their applications in improving image quality across diverse domains. The discussion includes state-of-the-art algorithms such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and Autoencoders, highlighting their applications in medical imaging, photography, and remote sensing. These methods have demonstrated notable impacts, including noise reduction, resolution enhancement, and contrast improvement. Despite its significant promise, deep learning faces challenges such as computational complexity and the need for large annotated datasets. outlines future research directions to overcome these limitations and further advance deep learning's potential in image enhancement.

Intelligent Agent-Based Architecture for Low-Light Image Enhancement Using an A3C Framework

Low-light image enhancement (LLIE) is an important area of research as many applications such as photography, video surveillance, and security are confronted with image degradation in low-light environments. This paper presents an intelligent agent-based method for LLIE using the Asynchronous Advantage Actor-Critic (A3C) framework. The enhancement task is effectively cast in this work into the framework of a Markov Decision Process. This method enables an agent to learn a policy that successively improves image quality. In the agent, features are extracted by a Fully Convolutional Network (FCN), a policy network for choosing an action, and a value network for estimating the reward. In training, non-reference loss functions are also used to measure image quality without the availability of the reference image or ground truth images. Such functions include spatial consistency loss, exposure control loss, and illumination smoothness loss, and the approach achieves end-to-end enhancement without reference image. The experimental results on LOL and MIT-Adobe dataset also show that the proposed technique enhances image brightness, Contrast, and structure much better as compared to other state-of-the-art methods. Especially, the methodology proposed scored 25.93 PSNR, 0.932 SSIM, and 0.053 LPIPS on the LOL dataset, achieving better results than related strategies. The designed agent-based approach works under a wide range of low-light situations. This approach allows obtaining enhancement results that will be satisfactory in terms of the users’ preferences and needs of the specific applications. The findings highlight the method's robustness and flexibility, making it suitable for various practical applications. This work demonstrates that reinforcement learning agents have promising applications in improved image processing capabilities, and establishes a new record for low-light image improvement.

AUTOMATIC SEGMENTATION OF COLON CANCER USING SAM AI

The third most prevalent form of cancer globally in both men and women is colon cancer which affects the digestive tract and occurs in the human body's greater intestine develops from certain polyps are tiisues that grow inside the colon of various sizes which at later stage can develop into a cancer cell. The tissues are taken from colon using biopsy method and cured. Under a microscope, histopathology images are categorised as a manual screening of colon the study tissue. Size of the nucleus and form of the glands are accepted standards for identifying colon cancer cells. The images obtaimed using colonscopy are converted into gray scale images where feature extraction done by conventional techniques and classified. To improve diagnosis methods for processing images and AI characteristics are also used. The automatic thresholding approach known as Otsu's Method, image thresholding, image enhancement, and edge detection techniques are used in the many processing procedures for an image. The SAM AI model is utilised to extract the malignancy characteristic of colon cancer. For the diagnostic images, metrics like resolution and peak signal to noise ratio are acquired.

Enhancement of Sentinel-2A Images for Ship Detection via Real-ESRGAN Model

Ship detection holds great value regarding port management, logistics operations, ship security, and other crucial issues concerning surveillance and safety. Recently, ship detection from optical satellite imagery has gained popularity among the research community because optical images are easily accessible with little or no cost. However, these images’ quality and quantity of feature details are bound to their spatial resolution, which often comes in medium-low spatial resolution. Accurately detecting ships requires images with richer texture and resolution. Super-resolution is used to recover features in medium-low resolution images, which can help leverage accuracy in ship detection. In this regard, this paper quantitatively and visually investigates the effectiveness of super-resolution in enabling more accurate ship detection in medium spatial resolution images by comparing Sentinel-2A images and enhanced Sentinel-2A images. A collection of Sentinel-2A images was enhanced four times with a Real-ESRGAN model that trained PlanetScope images with high spatial resolution. Separate ship detections with YOLOv10 were implemented for Sentinel-2A images and enhanced Sentinel-2A images. The visual and metric results of both detections were compared to demonstrate the contributory effect of enhancement on the ships’ detection accuracy. Ship detection on enhanced Sentinel-2A images has a mAP50 and mAP50-95 value of 87.5% and 68.5%. These results outperformed the training process on Sentinel-2A images with a mAP value increase of 2.6% for both mAP50 and mAP50-95, demonstrating the positive contribution of super-resolution.

Enhancement of satellite images based on CLAHE and augmented elk herd optimizer

Satellite images often have very narrow brightness value ranges, so it is necessary to enhance the contrast and brightness, maintain the quality of visual information, and preserve pertinent details in the images before conducting additional analysis. This is because improving the brightness and contrast of images is crucial to image processing and analysis as it makes it easier for people to identify and comprehend the images. The Incomplete Beta Function (IBF) is a popular transformation function for Image Contrast Enhancement (ICE). Nevertheless, IBF has modest efficiency in parameter selection, a small set of adjustable parameters for stretching regions with high or low gray levels, and image enhancement is almost ineffective with stretching at either end. Meta-heuristic algorithms have been utilized efficiently and effectively over the past few decades to solve complicated image processing problems. This paper presents an Augmented version of the Elk Herd Optimizer (AEHO) combined with other traditional ICE techniques to improve edge details, entropy, local contrast, and local brightness of low-contrast natural and satellite images. The AEHO method employs a multi-stage strategic procedure, where its mathematical model undergoes several enhancements before being applied to ICE to allow for further exploration and exploitation of its features. This method uses a pre-established fitness criterion for the purpose of optimizing a set of parameters to rework a well-known transformation function and an effective assessment technique as an objective standard for this purpose. In the proposed image enhancement model, contrast limited adaptive histogram equalization was first applied as a prior step to ameliorate the color intensity. Then, the optimal IBF’s parameters for ICE were adaptively determined using AEHO. After that, bilateral gamma correction was used to improve the visual quality of images without sacrificing edge details or natural color quality. The proposed AEHO-based image enhancement model is tested on natural scenes, certain standard images, and publicly available satellite images. In addition to other five techniques built on based on pre-existing meta-heuristics, the performance of the proposed method was compared against other well-known state-of-the-art image enhancement algorithms. The objective evaluation of the enhancement algorithms was achieved utilizing a variety of full-reference, no-reference, and pertinent performance evaluation norms. The experimental findings illustrated that the proposed image enhancement method can successfully outperform several other algorithms that employed the same image enhancement model as AEHO in addition to other conventional image enhancement methods included for comparison. The results on ten natural and satellite color images showed that the presented method performs better than all other comparative methods in the corresponding evaluation criteria in terms of average peak signal-to-noise ratio, average universal quality index, average structural contrast-quality index, and average values of discrete entropy results, which are more than 32.30, 94.0%, 0.98.9%, and 7.4, respectively. In a nutshell, AEHO can be an efficient method that can be used to tackle several image processing problems.

Adaptive Compression and Reconstruction for Multidimensional Medical Image Data: A Hybrid Algorithm for Enhanced Image Quality.

Spatial regions within images typically hold greater priority over adjacent areas, especially in the context of medical images (MI) where minute details can have significant clinical implications. This research addresses the challenge of compressing medical image dimensions without compromising critical information by proposing an adaptive compression algorithm. The algorithm integrates a modified image enhancement module, clustering-based segmentation, and a variety of lossless and lossy compression techniques. Edge enhancement contrast limited adaptive histogram equalization (EE-CLAHE) and 2D adaptive anisotropic diffusion filter are employed to enhance and denoise the images, followed by adaptive expectation maximization clustering (AEMC) for segmentation into regions of interest (ROI) and non-ROI. The clustering process is optimized utilizing fuzzy c-means (FCM) and Otsu thresholding. Subsequently, distinct compression schemes are applied to ROI and non-ROI regions, such as Coiflet + Haar, Coiflet + Daubecheis, modified SPIHT Huffman, EZW, and SPIHT algorithms, to ensure effective storage and transmission while preserving diagnostic details. Experimental results demonstrate that the combination of the modified SPIHT Huffman algorithm for ROI and EZW for non-ROI yields superior reconstruction quality across various measures, enabling comprehensive analysis of multi-dimensional images from MRI, CT, and X-ray modalities.

Low-light image enhancement via an attention-guided deep Retinex decomposition model

Low-light image enhancement via an attention-guided deep Retinex decomposition model

LDWLE: self-supervised driven low-light object detection framework

Low-light object detection involves identifying and locating objects in images captured under poor lighting conditions. It plays a significant role in surveillance and security, night pedestrian recognition, and autonomous driving, showcasing broad application prospects. Most existing object detection algorithms and datasets are designed for normal lighting conditions, leading to a significant drop in detection performance when applied to low-light environments. To address this issue, we propose a Low-Light Detection with Low-Light Enhancement (LDWLE) framework. LDWLE is an encoder-decoder architecture where the encoder transforms the raw input data into a compact, abstract representation (encoding), and the decoder gradually generates the target output format from the representation produced by the encoder. Specifically, during training, low-light images are input into the encoder, which produces feature representations that are decoded by two separate decoders: an object detection decoder and a low-light image enhancement decoder. Both decoders share the same encoder and are trained jointly. Throughout the training process, the two decoders optimize each other, guiding the low-light image enhancement towards improvements that benefit object detection. If the input image is normally lit, it first passes through a low-light image conversion module to be transformed into a low-light image before being fed into the encoder. If the input image is already a low-light image, it is directly input into the encoder. During the testing phase, the model can be evaluated in the same way as a standard object detection algorithm. Compared to existing object detection algorithms, LDWLE can train a low-light robust object detection model using standard, normally lit object detection datasets. Additionally, LDWLE is a versatile training framework that can be implemented on most one-stage object detection algorithms. These algorithms typically consist of three components: the backbone, neck, and head. In this framework, the backbone functions as the encoder, while the neck and head form the object detection decoder. Extensive experiments on the COCO, VOC, and ExDark datasets have demonstrated the effectiveness of LDWLE in low-light object detection. In quantitative measurements, it achieves an AP of 25.5 and 38.4 on the synthetic datasets COCO-d and VOC-d, respectively, and achieves the best AP of 30.5 on the real-world dataset ExDark. In qualitative measurements, LDWLE can accurately detect most objects on both public real-world low-light datasets and self-collected ones, demonstrating strong adaptability to varying lighting conditions and multi-scale objects.

Underwater Image Enhancement Based on Difference Convolution and Gaussian Degradation URanker Loss Fine-Tuning

Underwater images often suffer from degradation such as color distortion and blurring due to light absorption and scattering. It is essential to utilize underwater image enhancement (UIE) methods to acquire high-quality images. Convolutional networks are commonly used for UIE tasks, but their learning capacity is still underexplored. In this paper, a UIE network based on difference convolution is proposed. Difference convolution enables the model to better capture image gradients and edge information, thereby enhancing the network’s generalization capability. To further improve performance, attention-based fusion and normalization modules are incorporated into the model. Additionally, to mitigate the impact of the absence of authentic reference images in datasets, a URanker loss module based on Gaussian degradation is proposed during the fine-tuning. The input images are subjected to Gaussian degradation, and the image quality assessment model URanker is utilized to predict the scores of the enhanced images before and after degradation. The model is further fine-tuned using the score difference between the two. Extensive experimental results validate the outstanding performance of the proposed method in UIE tasks.

The IPEDs assemblage: Tracing the entanglements of biomedicine, technology, enhancement and anti-doping policies in sport and society.

The US Anti-Doping Agency (USADA) and Ultimate Fighting Championship (UFC) recently ended their anti-doping partnership amidst controversy. We treat this decision, and the motivations underpinning it, as a means of exploring the complexities of anti-doping norms and the blurred lines between image and performance enhancing drug (IPED) use in sport and wider society. Drawing ideas from assemblage thinking, we analyse the evolving power dynamics surrounding IPED use, anti-doping policy, and the role of popular athletes in shaping societal perceptions of the use of, and potential harms associated with IPEDs. The study offers a case analysis of recent controversies in the UFC to investigate the entanglements of biomedicine, technology and celebrity culture in what we call the IPED assemblage. The 2023 termination of the USADA-UFC partnership has sparked debates about shifts in anti-doping standards, raising concerns about weaker testing protocols and perceptions of IPED normalisation. The case of Conor McGregor's injury recovery and alleged IPED use underscores the blurred lines between therapeutic and enhancement drug use within the IPED assemblage, challenging conventional distinctions between 'good' and 'bad' drugs in the context of sports management and anti-doping policy making. We highlight the inadequacy of current doping policies in responding to the IPED assemblage and highlight the need to shift public discourse to foster a more critical understanding of therapeutic and enhancement strategies to drive innovation in anti-doping frameworks.

Intelligent Recognition of Road Internal Void Using Ground-Penetrating Radar

Internal road voids can lead to decreased load-bearing capacity, which may result in sudden road collapse, posing threats to traffic safety. Three-dimensional ground-penetrating radar (3D GPR) detects internal road structures by transmitting high-frequency electromagnetic waves into the ground and receiving reflected waves. However, due to noise interference during detection, accurately identifying void areas based on GPR-collected images remains a significant challenge. Therefore, in order to more accurately detect and identify the void areas inside the road, this study proposes an intelligent recognition method for internal road voids based on 3D GPR. First, extensive data on internal road voids was collected using 3D GPR, and the GPR echo characteristics of void areas were analyzed. To address the issue of poor image quality in GPR images, a GPR image enhancement model integrating multi-frequency information was proposed by combining the Unet model, Multi-Head Cross Attention mechanism, and diffusion model. Finally, the intelligent recognition model and enhanced GPR images were used to achieve intelligent and accurate recognition of internal road voids, followed by engineering validation. The research results demonstrate that the proposed road internal void image enhancement model achieves significant improvements in both visual effects and quantitative evaluation metrics, while providing more effective void features for intelligent recognition models. This study offers technical support for precise decision making in road maintenance and ensuring safe road operations.

Dual-statistic white balance guided 3DLUT for image enhancement

Dual-statistic white balance guided 3DLUT for image enhancement

A submesoscale eddy identification dataset in the northwest Pacific Ocean derived from GOCI I chlorophyll a data based on deep learning

Abstract. This paper presents a dataset on the identification of submesoscale eddies, derived from high-resolution chlorophyll a data captured by GOCI I in the northwest Pacific Ocean. Our methodology involves a combination of digital image processing, filtering, and object detection techniques, along with a specific chlorophyll a image enhancement procedure to extract essential information about submesoscale eddies. This information includes their time, polarity, geographical coordinates of the eddy center, eddy radius, coordinates of the upper left and lower right corners of the prediction box, area of the eddy's inner ellipse, and confidence score. The dataset spans eight time intervals, ranging from 00:00 to 08:00 (UTC) daily, covering the period from 1 April 2011 to 31 March 2021. A total of 19 136 anticyclonic eddies and 93 897 cyclonic eddies were identified, with a minimum confidence threshold of 0.2. The mean radius of anticyclonic eddies is 24.44 km (range 2.5 to 44.25 km), while that of cyclonic eddies is 12.34 km (range 1.75 to 44 km). This unprecedented hourly resolution dataset on submesoscale eddies offers valuable insights into their distribution, morphology, and energy dissipation. It significantly contributes to our understanding of marine environments, ecosystems, and the improvement of climate model predictions. The dataset is available at https://doi.org/10.5281/zenodo.13989785 (Wang and Yang, 2023).

Adltformer Team-Training with Detr: Enhancing Cattle Detection in Non-Ideal Lighting Conditions Through Adaptive Image Enhancement.

This study proposes an image enhancement detection technique based on Adltformer (Adaptive dynamic learning transformer) team-training with Detr (Detection transformer) to improve model accuracy in suboptimal conditions, addressing the challenge of detecting cattle in real pastures under complex lighting conditions-including backlighting, non-uniform lighting, and low light. This often results in the loss of image details and structural information, color distortion, and noise artifacts, thereby compromising the visual quality of captured images and reducing model accuracy. To train the Adltformer enhancement model, the day-to-night image synthesis (DTN-Synthesis) algorithm generates low-light image pairs that are precisely aligned with normal light images and include controlled noise levels. The Adltformer and Detr team-training (AT-Detr) method is employed to preprocess the low-light cattle dataset for image enhancement, ensuring that the enhanced images are more compatible with the requirements of machine vision systems. The experimental results demonstrate that the AT-Detr algorithm achieves superior detection accuracy, with comparable runtime and model complexity, reaching 97.5% accuracy under challenging illumination conditions, outperforming both Detr alone and sequential image enhancement followed by Detr. This approach provides both theoretical justification and practical applicability for detecting cattle under challenging conditions in real-world farming environments.