Image Correction Research Articles

Correcting Optical Aberration via Depth-Aware Point Spread Functions.

Optical aberration is a ubiquitous degeneration in realistic lens-based imaging systems. Optical aberrations are caused by the differences in the optical path length when light travels through different regions of the camera lens with different incident angles. The blur and chromatic aberrations manifest significant discrepancies when the optical system changes. This work designs a transferable and effective image simulation system of simple lenses via multi-wavelength, depth-aware, spatially-variant four-dimensional point spread functions (4D-PSFs) estimation by changing a small amount of lens-dependent parameters. The image simulation system can alleviate the overhead of dataset collecting and exploiting the principle of computational imaging for effective optical aberration correction. With the guidance of domain knowledge about the image formation model provided by the 4D-PSFs, we establish a multi-scale optical aberration correction network for degraded image reconstruction, which consists of a scene depth estimation branch and an image restoration branch. Specifically, we propose to predict adaptive filters with the depth-aware PSFs and carry out dynamic convolutions, which facilitate the model's generalization in various scenes. We also employ convolution and self-attention mechanisms for global and local feature extraction and realize a spatially-variant restoration. The multi-scale feature extraction complements the features across different scales and provides fine details and contextual features. Extensive experiments demonstrate that our proposed algorithm performs favorably against state-of-the-art restoration methods.

Anti-noise performance analysis in amplitude-modulated collinear holographic data storage using deep learning

In an amplitude-modulated collinear holographic data storage system, optical system aberration and experimental noise due to the recording medium often result in a high bit error rate (BER) and low signal-to-noise ratio (SNR) in directly read detector data. This study proposes an anti-noise performance analysis using deep learning. End-to-end convolutional neural networks were employed to analyze noise resistance in encoded data pages captured by the detector. Experimental results demonstrate that these networks effectively correct system imaging aberrations, detector light intensity response, holographic storage medium response non-uniformity, and defocusing noise from the recording objective lens. Consequently, the BER of reconstructed encoded data pages can be reduced to 1/10 of that from direct detection, while the SNR can be increased more than fivefold, enhancing the accuracy and reliability of data reading in amplitude holographic data storage systems.

Unfolder: fast localization and image rectification of a document with a crease from folding in half

Presentation of folded documents is not an uncommon case in modern society. Digitizing such documents by capturing them with a smartphone camera can be tricky since a crease can divide the document contents into separate planes. To unfold the document, one could hold the edges potentially obscuring it in a captured image. While there are many geometrical rectification methods, they were usually developed for arbitrary bends and folds. We consider such algorithms and propose a novel approach Unfolder developed specifically for images of documents with a crease from folding in half. Unfolder is robust to projective distortions of the document image and does not fragment the image in the vicinity of a crease after rectification. A new Folded Document Images dataset was created to investigate the rectification accuracy of folded (2, 3, 4, and 8 folds) documents. The dataset includes 1600 images captured when document placed on a table and when held in hand. The Unfolder algorithm allowed for a recognition error rate of 0.33, which is better than the advanced neural network methods DocTr (0.44) and DewarpNet (0.57). The average runtime for Unfolder was only 0.25 s/image on an iPhone XR.

AutoCorNN: An Unsupervised Physics-Aware Deep Learning Model for Geometric Distortion Correction of Brain MRI Images Towards MR-Only Stereotactic Radiosurgery.

Geometric distortions in brain MRI images arising from susceptibility artifacts at air-tissue interfaces pose a significant challenge for high-precision radiation therapy modalities like stereotactic radiosurgery, necessitating sub-millimeter accuracy. To achieve this goal, we developed AutoCorNN, an unsupervised physics-aware deep-learning model for correcting geometric distortions. Two publicly available datasets, the MPI-Leipzig Mind-Brain-Body with 318 subjects, and the Vestibular Schwannoma-SEG dataset, encompassing 242 patients were utilized. AutoCorNN integrates two 2D convolutional encoder-decoder neural networks with the forward physical model of MRI signal generation to predict undistorted MR and field map images from distorted MR input. The network is trained in an unsupervised manner by minimizing the mean absolute error between the measured and estimated k-space data, without requiring ground truth images during training or deployment. The model was evaluated on vestibular schwannoma cases. AutoCorNN achieved a peak signal-to-noise ratio (PSNR) of 41.35 ± 0.02dB, a root mean square error (RMSE) of 0.02 ± 0.003, and a structural similarity index (SSIM) of 0.99 ± 0.02 outperforming uncorrected and B0-mapping correction methods. Geometric distortions of about 1.6mm were observed at the air-tissue interfaces at the air canal and nasal cavity borders. Geometrically, distortion correction increased the target volume from 3.12 ± 0.52cc to 3.84 ± 0.54cc. Dosimetrically, AutoCorNN improved target coverage (0.96 ± 0.01 to 0.97 ± 0.02), conformity index (0.92 ± 0.03 to 0.94 ± 0.03), and reduced dose gradients outside the target. AutoCorNN achieves accurate geometric distortion correction comparable to conventional iterative methods while offering substantial computational acceleration, enabling precise target delineation and conformal dose delivery for improved radiation therapy outcomes.

Computer Vision Algorithm Design in Image Processing Based on Projective Geometry

Image processing with computer vision, particularly in the realm of projective geometry, offers remarkable potential for various applications. Through the lens of projective geometry, images can be transformed, augmented, and reconstructed with precision, facilitating tasks such as image rectification, 3D reconstruction, and object tracking. Landmark estimation in computer vision is a vital task with broad applications across various domains. This process involves identifying key points or landmarks within images, enabling tasks such as facial recognition, object tracking, and gesture recognition. This paper, proposed a novel approach for landmark estimation in computer vision using Projective Geometry Landmark Estimation (PGLM). The proposed model aims to estimate the landmark features by a projective geometry model. With the estimation of the geometry features landmarks related to the facial, object, and medical images are computed. The PGLM model uses the point features for the location of the landmark features. In order to compare PGLM's performance to that of more conventional classification methods like Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), simulation analysis is carried out. From what we can see, PGLM routinely beats these alternatives when we compare their accuracy, precision, recall, and F1 score. The findings stated the effectiveness of PGLM as a promising approach for landmark estimation in image processing tasks, paving the way for further advancements in this domain.

Optimization of handheld spectrally encoded coherence tomography and reflectometry for point-of-care ophthalmic diagnostic imaging.

Handheld optical coherence tomography (HH-OCT) systems enable point-of-care ophthalmic imaging in bedridden, uncooperative, and pediatric patients. Handheld spectrally encoded coherence tomography and reflectometry (HH-SECTR) combines OCT and spectrally encoded reflectometry (SER) to address critical clinical challenges in HH-OCT imaging with real-time en face retinal aiming for OCT volume alignment and volumetric correction of motion artifacts that occur during HH-OCT imaging. We aim to enable robust clinical translation of HH-SECTR and improve clinical ergonomics during point-of-care OCT imaging for ophthalmic diagnostics. HH-SECTR is redesigned with (1)optimized SER optical imaging for en face retinal aiming and retinal tracking for motion correction, (2)a modular aluminum form factor for sustained alignment and probe stability for longitudinal clinical studies, and (3)one-handed photographer-ergonomic motorized focus adjustment. We demonstrate an HH-SECTR imaging probe with micron-scale optical-optomechanical stability and use it for in vivo human retinal imaging and volumetric motion correction. This research will benefit the clinical translation of HH-SECTR for point-of-care ophthalmic diagnostics.

Benthic habitat mapping for estimating seagrass carbon stock across Takabonerate Islands, Indonesia

Data on benthic habitat cover are essential for monitoring and managing coastal areas, providing valuable ecosystem services for local communities. Moreover, seagrass extent is crucial for estimating carbon stock using Tier-1 calculations. On the other side, remote sensing technology has proven effective in mapping benthic habitat cover, including seagrass, over large local areas. Therefore, this research aims to map specific benthic habitats in a local area to obtain high-accuracy estimates of seagrass extent for carbon stock estimation. The study was conducted in the Takabonerate Islands, Indonesia, using Sentinel-2A imagery. The study involved field data processing, which enabled the mapping of eight benthic habitat classes using Sentinel-2A images, along with the steps for Sentinel-2A image processing for benthic habitat mapping. The benthic habitat map was produced following image correction steps, including atmospheric, sunglint, and water column corrections, followed by image classification using a Neural Net Classifier (NNC). Seagrass carbon stock estimation was performed using the Tier-1 equation from IPCC 2013. The study revealed a total benthic habitat area of 57,538.04 ha, with a seagrass area of 3127.42 ha for carbon stock estimation. The potential seagrass carbon stock in the study area was estimated to range from 337.76 GgC/ha to 31.27 GgC/ha using the Tier-1 equation. The overall accuracy of the benthic habitat map was 80.5 %, calculated using a confusion matrix table. The spatial information from this study can be used by local coastal managers and governments for baseline and monitoring purposes. The key interpretations from this study provide valuable findings that can be adapted and improved for future local mapping purposes.

Deep-learning-based Attenuation Correction for 68Ga-DOTATATE Whole-body PET Imaging: A Dual-center Clinical Study.

Attenuation correction is a critical phenomenon in quantitative positron emission tomography (PET) imaging with its own special challenges. However, computed tomography (CT) modality which is used for attenuation correction and anatomical localization increases patient radiation dose. This study was aimed to develop a deep learning model for attenuation correction of whole-body 68Ga-DOTATATE PET images. Non-attenuation-corrected and computed tomography-based attenuation-corrected (CTAC) whole-body 68Ga-DOTATATE PET images of 118 patients from two different imaging centers were used. We implemented a residual deep learning model using the NiftyNet framework. The model was trained four times and evaluated six times using the test data from the centers. The quality of the synthesized PET images was compared with the PET-CTAC images using different evaluation metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean square error (MSE), and root mean square error (RMSE). Quantitative analysis of four network training sessions and six evaluations revealed the highest and lowest PSNR values as (52.86±6.6) and (47.96±5.09), respectively. Similarly, the highest and lowest SSIM values were obtained (0.99±0.003) and (0.97±0.01), respectively. Additionally, the highest and lowest RMSE and MSE values fell within the ranges of (0.0117±0.003), (0.0015±0.000103), and (0.01072±0.002), (0.000121±5.07xe-5), respectively. The study found that using datasets from the same center resulted in the highest PSNR, while using datasets from different centers led to lower PSNR and SSIM values. In addition, scenarios involving datasets from both centers achieved the best SSIM and the lowest MSE and RMSE. Acceptable accuracy of attenuation correction on 68Ga-DOTATATE PET images using a deep learning model could potentially eliminate the need for additional X-ray imaging modalities, thereby imposing a high radiation dose on the patient.

Correction Compensation and Adaptive Cost Aggregation for Deep Laparoscopic Stereo Matching

Perception of digitized depth is a prerequisite for enabling the intelligence of three-dimensional (3D) laparoscopic systems. In this context, stereo matching of laparoscopic stereoscopic images presents a promising solution. However, the current research in this field still faces challenges. First, the acquisition of accurate depth labels in a laparoscopic environment proves to be a difficult task. Second, errors in the correction of laparoscopic images are prevalent. Finally, laparoscopic image registration suffers from ill-posed regions such as specular highlights and textureless areas. In this paper, we make significant contributions by developing (1) a correction compensation module to overcome correction errors; (2) an adaptive cost aggregation module to improve prediction performance in ill-posed regions; (3) a novel self-supervised stereo matching framework based on these two modules. Specifically, our framework rectifies features and images based on learned pixel offsets, and performs differentiated aggregation on cost volumes based on their value. The experimental results demonstrate the effectiveness of the proposed modules. On the SCARED dataset, our model reduces the mean depth error by 12.6% compared to the baseline model and outperforms the state-of-the-art unsupervised methods and well-generalized models.

Deep underwater image compression for enhanced machine vision applications

Underwater image compression is fundamental in underwater visual applications. The storage resources of autonomous underwater vehicles (AUVs) and underwater cameras are limited. By employing effective image compression methods, it is possible to optimize the resource utilization of these devices, thereby extending the operational time underwater. Current image compression methods neglect the unique characteristics of the underwater environment, thus failing to support downstream underwater visual tasks efficiently. We propose a novel underwater image compression framework that integrates frequency priors and feature decomposition fusion in response to these challenges. Our framework incorporates a task-driven feature decomposition fusion module (FDFM). This module enables the network to understand and preserve machine-friendly information during the compression process, prioritizing task relevance over human visual perception. Additionally, we propose a frequency-guided underwater image correction module (UICM) to address noise issues and accurately identify redundant information, enhancing the overall compression process. Our framework effectively preserves machine-friendly features at a low bit rate. Extensive experiments across various downstream visual tasks, including object detection, semantic segmentation, and saliency detection, consistently demonstrated significant improvements achieved by our approach.

Illumination correction for dyed products with spotted hyena optimizer and regularized extreme learning machine

Dyed products exhibit varying colors when illuminated by different light sources. Human eyes possess color constancy, enabling them to automatically adjust and overlook color discrepancies, effectively self-correcting visually. However, these variations are perceived as distinct colors by computers. To eliminate the effects of lighting on the dyed products, illumination correction is needed to make the dyed products show their original color. To achieve this goal, this article presents a novel algorithm, WOA-SHO-RELW (Whale Optimization Algorithm-Spotted Hyena Optimizer-Regularized Extreme Learning Machine), designed to emulate color constancy and applies it to the illumination correction of dyed products. We employ the WOA to optimize the initial population of SHO, carefully selecting a group of suitable initial parameters. Subsequently, SHO is utilized to optimize the hidden biases and input weights of RELM, with the overarching aim of enhancing the model’s effectiveness and performance, thereby ensuring more precise illumination correction for images of dyed products. The comparison results with other algorithms show that our WOA-SHO-RELM has better comprehensive performances.

Enhancements in image quality and block detection performance for Reinforced Soil-Retaining Walls under various illuminance conditions

To ensure continuous monitoring of reinforced soil-retaining walls (RSWs) even under low-illuminance conditions, such as during the night, it is imperative to evaluate the performance of deep learning-based detection. In this study, we constructed a laboratory RSW model and generated a dataset with varying illuminance levels to assess the impact of image enhancement and block detection. Various image enhancement methods were applied to improve image quality and evaluate their effect on deep learning. RGB optimization (RO) was proposed to optimize RGB intensity and compared with gamma correction, histogram equalization, and low-light image enhancement with illumination map estimation. RO demonstrated outstanding image enhancement performance, as evidenced by lightness order error, peak signal-to-noise ratio, and structural similarity index measure, ensuring high image quality. The trained RO model using Mask R-CNN exhibited excellent accuracy, recall, and F1 score, delivering remarkable detection performance under low illuminance conditions, resulting in a 7.44 % improvement in the F1 score. Image enhancement techniques that maintain similarity, such as lightness order error and structural similarity, across varying illuminance conditions contribute to enhancing the block detection performance of Mask R-CNNs.

Subpixel motion artifacts correction and motion estimation for 3D-OCT.

A number of hardware-based and software-based strategies have been suggested to eliminate motion artifacts for improvement of 3D-optical coherence tomography (OCT) image quality. However, the hardware-based strategies have to employ additional hardware to record motion compensation information. Many software-based strategies have to need additional scanning for motion correction at the expense of longer acquisition time. To address this issue, we propose a motion artifacts correction and motion estimation method for OCT volumetric imaging of anterior segment, without requirements of additional hardware and redundant scanning. The motion correction effect with subpixel accuracy for in vivo 3D-OCT has been demonstrated in experiments. Moreover, the physiological information of imaging object, including respiratory curve and respiratory rate, has been experimentally extracted using the proposed method. The proposed method offers a powerful tool for scientific research and clinical diagnosis in ophthalmology and may be further extended for other biomedical volumetric imaging applications.

Error analysis and correction of atmospheric disturbance for interferometric imaging radar altimeter

The interferometric imaging radar altimeter (InIRA) is a newly developed microwave remote sensing system in recent years. It is of great significance to analyze the main sources of its height measurement error through simulation, and to develop the corresponding image phase error correction methods. This can provide basis and reference for the subsequent correction of the real images phase error. In this study, according to the interaction principle between atmospheric interference and InIRA radar electromagnetic waves, the influence of background ionosphere and background troposphere on height measurement error is analyzed by introducing ionosphere and troposphere delays into echo signals respectively. The impact of ionospheric scintillation and atmospheric turbulence on the height measurement error is analyzed by building multi-layer phase screen models. Then according to the analysis results, a phase error correction method for InIRA images combined by the improved fruit fly optimization algorithm (IFOA) and the joint minimum entropy criterion (JMEC) is proposed. The image is divided into several sub-images with negligible spatial variation of phase error according to the principle of first range and then azimuth. IFOA is used to search the optimal phase compensation values iteratively to compensate the phase of all sub-images. When the joint entropy of the sub-images reaches the minimum value, the phase error correction of the whole InIRA image is completed. Experimental results show that the proposed method can correct the phase of InIRA images with inconspicuous features and polluted by weak ionospheric scintillation and atmospheric turbulence relatively quickly. After correction, the height measurement error can be reduced from decimeter level to centimeter level. The correction accuracy and efficiency of the proposed method are superior to those of the method combined by particle swarm optimization algorithm and joint minimum entropy criterion (PSO-JMEC), the method combined by genetic algorithm and joint minimum entropy criterion (GA-JMEC), the method combined by phase gradient autofocus and Map Drift (PGA-MD), and improved PGA-MD algorithm.

A Secure Self-Embedding Technique for Manipulation Detection and Correction of Medical Images

A Secure Self-Embedding Technique for Manipulation Detection and Correction of Medical Images

Coherence-based phase aberration correction and beamforming for ring-array ultrasound imaging

Degradation of image quality caused by aberrations and off-axis interferences is common in medical ultrasound imaging. The ring-array echo imaging also suffers from these constraints, where phase aberrations caused by tissue heterogeneity create overlapping of interest target and worsen the interpretability of anatomical structures; while off-axis interferences reduce the spatial resolution and contrast of the reconstructed images. To address them, the signal coherence is available since they can be considered as incoherent interference and noise. The coherence factor (CF) is sensitive to phase aberrations and is thus adopted in this study. Moreover, the convolutional beamforming algorithm (COBA) specifically exploits the autocorrelation operation to improve the signal coherence and effectively reduce noise. Therefore, we first utilize the CF to detect the local coherence and its maximization criterion as a way to estimate the sound speed to correct for phase aberration. Then, CF is used as an adaptive weighting factor to suppress the noise, and based on this, we develop a short-lag COBA to further enhance the image quality, referred to as the CF_SLCOBA method. Simulations and experiments were performed to evaluate the performance of the proposed methods. Results show that, the improvements of the CF_SLCOBA method in resolution is about 26.8% compared with CF; while about 92.0% in contrast ratio (CR) compared with COBA, in the experiments. Meanwhile, the proposed method yields a good performance in phase aberration correction. This demonstrates that the proposed method may provide benefits for rebuilding high-quality images, which also reveals that it offers a certain potential for practical applications.

Anisotropic regularization for sparsely sampled and noise-robust Fourier ptychography.

Fourier ptychography (FP) is a powerful computational imaging technique that provides super-resolution and quantitative phase imaging capabilities by scanning samples in Fourier space with angle-varying illuminations. However, the image reconstruction in FP is inherently ill-posed, particularly when the measurements are noisy and have insufficient data redundancy in the Fourier space. To improve FP reconstruction in high-throughput imaging scenarios, we propose a regularized FP reconstruction algorithm utilizing anisotropic total variation (TV) and Tikhonov regularizations for the object and pupil functions, respectively. To solve this regularized FP problem, we formulate a reconstruction algorithm using the alternating direction method of multipliers and show that our approach successfully recovers high-quality images with sparsely sampled and/or noisy measurements. The results are quantitatively and qualitatively compared against various FP reconstruction algorithms to analyze the effect of regularization under harsh imaging conditions. In particular, we demonstrate the effectiveness of our method on the real experimental FP microscopy images, where the TV regularizer effectively suppresses the measurement noise while maintaining the edge information in the biological specimen and helps retrieve the correct amplitude and phase images even under insufficient sampling.

Exposure image correction of electrical equipment nameplate based on the LMPEC algorithm

Exposure image correction of electrical equipment nameplate based on the LMPEC algorithm

A detailed study on human height estimation model that combines video surveillance systems with 3D laser scanning.

The increase of video surveillance systems has highlighted the interest in forensic anthropometric analysis of subjects who commit crimes and are captured by cameras during their criminal activities. There are different methodologies for human height estimation. Forensic researchers developed a methodological approach that allows the height of a subject to be estimated through a combined model of 3D laser scanning acquisition and video images acquired by video surveillance systems. The proposed study had highlighted three limits: not assessments had been made for image correction to limit the distortion effect, the method had been tested by only one laboratory and probably height assessment was dependent on the ergonomics. To overcome these limitations, in this paper the analysis was repeated by correcting the images to compare the new results obtained with the previous ones. Furthermore, the same methodological approach was applied by estimating the height of a mannequin, to limit the ergonomic effects, and proposing the same study to three different forensic laboratories to compare the results. The presented study demonstrates the reliability and repeatability of the system, as the results obtained by the three laboratories are very similar. They have obtained the same trend and the maximum estimate distance is approximately 6 cm. Furthermore, it has showed that the accuracy of results is dependent on image correction, which has little impact (approximately 1 cm more accurate on the corrected frame than the normal frame) on the height evaluation and they are not dependent to the ergonomics of the subject captured.

Hystero-Salphingography in current clinical practice-old flames, die hard!

Hysterosalpingography (HSG) remains a valuable diagnostic tool in current clinical practice, offering crucial insights into endometrial cavity, fallopian tubes and the adjoining part of the pelvic peritoneal cavity. Despite the emergence of alternative imaging and non-imaging options, HSG continues to be widely utilized due to its diagnostic accuracy, cost-effectiveness, and easy accessibility. Due attention to the correct technique and optimal image interpretation will further enhance its diagnostic accuracy and precision in the work-up of patients with fertility problems.