Histogram Matching Research Articles

Multi-Institutional Development and Validation of a Radiomic Model to Predict Prostate Cancer Recurrence Following Radical Prostatectomy

The use of multiparametric magnetic resonance imaging (mpMRI)-derived radiomics has the potential to offer noninvasive, imaging-based biomarkers for the identification of subvisual characteristics indicative of a poor oncologic outcome. The present study, therefore, seeks to develop, validate, and assess the performance of an MRI-derived radiomic model for the prediction of prostate cancer (PC) recurrence following radical prostatectomy (RP) with curative intent. mpMRI imaging was obtained from 251 patients who had undergone an RP for the treatment of localized prostate cancer across two institutions and three surgeons. All patients had a minimum of 2 years follow-up via prostate-specific antigen serum testing. Each prostate mpMRI was individually reviewed, and the prostate was delineated as a single slice (ROI) on axial T2 high-resolution image sets. A total of 924 radiomic features were extracted and tested for stability via intraclass correlation coefficient (ICC) following image normalization via histogram matching. Fourteen important and nonredundant features were found to be predictors of PC recurrence at a mean ± SD of 3.2 ± 2.2 years post-RP. Five-fold, ten-run cross-validation of the model containing these fourteen features yielded an area under the curve (AUC) of 0.89 ± 0.04 in the training set (n = 225). In comparison, the University of California San Fransisco Cancer of the Prostate Risk Assessment score (UCSF-CAPRA) and Memorial Sloan Kettering Cancer Center (MSKCC) Pre-Radical prostatectomy nomograms yielded AUC of 0.66 ± 0.05 and 0.67 ± 0.05, respectively (p < 0.01). When the radiomic model was applied to the test set (n = 26), AUC was 0.78; sensitivity, specificity, positive predictive value, and negative predictive value were 60%, 86%, 52%, and 89%, respectively. Accuracy in predicting PC recurrence was 81%.

Non-parametric style transfer: Correlation-aware exact distribution matching

Early feed-forward neural methods of arbitrary image style transfer utilized the encoded feature map up to its second-order statistics, i.e., mean and variance (or covariance) of the encoded feature map. Recent methods have begun to utilize feature statistics beyond the 2nd-order statistics, e.g., a higher-order moment, slicing-based method, and histogram matching for better style representation. However, even in the distribution matching of the latest method, considering the channel-correlation and the order of duplicated values in the feature map is missing. This resulted in insufficient style transfer or artifacts on style-transferred images e.g., unexpected color or pattern co-occurrence, skewed color or style pattern into one side, noise between background and foreground, etc. In this work, we show how to make a feature transform layer to consider both channel-correlation and duplicated values in the feature map for exact feature distribution matching in style transfer. Our experimental results prove that the stylized images obtained with our method are more similar to the target style images qualitatively without losing content clearness and superior to the existing methods quantitatively in all possible style measures, e.g., 0.0311 lower sliced Wasserstein distance than the previous method and the most favored choice with 25.54% preference.

Histogram matching-based semantic segmentation model for crop classification with Sentinel-2 satellite imagery

ABSTRACT Accurate and near-real-time crop mapping from satellite imagery is crucial for agricultural monitoring. However, the seasonal nature of crops makes it challenging to rely on traditional machine learning methods and previous samples generated within specific domains. In this study, we improved the histogram matching method for color correction of multi-temporal images and tested the performance and prediction classification accuracy of three semantic segmentation models based on weak samples. Classification experiments were conducted for nine categories in two cities in Henan province from 2019 to 2022 using 10 m resolution Sentinel-2 images with different feature selection schemes. We trained the models using classified and recorrected results in four selected sites in 2019 and 2020, and designed experiments to assess the performance of the improved histogram matching method and verify the transferability of semantic segmentation models across regions and years. The experimental results showed that the UNet++ model with feature selection and improved histogram matching methods outperformed other models, such as DeepLab V3+ and UNet, in crop classification transfer cases, with better model performance and higher classification accuracy. The UNet++ model without training samples achieved optimal overall accuracy, Kappa coefficient, and mean F1-score values from 2019 to 2022, exceeding 87%, 82%, and 65%, respectively. Moreover, the representative error of weak samples and prediction classification results were analyzed to improve the model robustness. As an application of transfer-learning in crop mapping, the proposed model effectively addressed the classification problem of multispectral satellite imagery with missing labels.

Low-Light Image Enhancement Method Using a Modified Gamma Transform and Gamma Filtering-Based Histogram Specification for Convex Combination Coefficients

Recently, a lot of low-light image enhancement methods have been proposed. However, these methods have some problems such as causing fine details lost in bright regions and/or unnatural color tones. In this paper, we propose a new low-light image enhancement method to cope with these problems. In the proposed method, a pixel is represented by a convex combination of white, black, and pure color. Then, an equi-hue plane in RGB color space is represented as a triangle whose vertices correspond to white, black, and pure color. The visibility of low-light image is improved by applying a modified gamma transform to the combination coefficients on an equi-hue plane in RGB color space. The contrast of the image is enhanced by the histogram specification method using the histogram smoothed by a filter with a kernel determined based on a gamma distribution. In the experiments, the effectiveness of the proposed method is verified by the comparison with the state-of-the-art low-light image enhancement methods.

A General Relative Radiometric Correction Method for Vignetting Noise Drift

Due to the limitation of the number of sensor pixels, optical splicing is commonly used to improve the imaging width of remote sensing satellites, and this optical stitching can cause vignetting in the image data of adjacent sensors. The weak energy, low signal-to-noise ratio, and poor response stability of vignetting are key factors that restrict the relative radiometric correction of optical splicing remote satellites. This paper proposes a stability analysis method and a relative radiometric correction method for vignetting. First, we analyzed the stability of the response and the noise impact of vignetting. Massive data from the Jilin-1 GF03D satellites was used to analyze the stability of the response using the vignetting stability analysis method. Secondly, the data on the deep sea during nighttime (DDSN) of Jilin-1 GF03D satellites was used to obtain the characteristics of the sensors’ noise. Thirdly, by building a noise drift model, we calculated the coefficient of the noise drift according to its characteristics. Using the coefficient to eliminate the noise drift of each pixel in vignetting can improve the response stability of vignetting. The average response stability increased by 37.64% by this method. Finally, the automatic relative radiometric correction method was completed through histogram matching. Furthermore, we proposed color aberration metrics (CAMs) to evaluate the multi-spectral images after relative radiometric correction, and massive data from the 16 satellites of Jilin-1 GF03D was used to verify the effectiveness and generality. The experimental results show that the average CAM of the images increased by 15.97% using the proposed method compared to the traditional method.

Color image enhancement technique based on interval-valued intuitionistic fuzzy set

In this paper, a new interval-valued intuitionistic fuzzy-based algorithm is proposed to enhance low-light images. In this proposed algorithm, the low-light image is first changed to the fuzzy image by normal fuzzification. Then the above is converted to an intuitionistic fuzzy image and further to the interval-valued intuitionistic fuzzy image. After applying contrast limited adaptive histogram equalization, we derive the required image. In the experimental part, the proposed algorithm is compared with other existing algorithms including histogram equalization, contrast limited adaptive histogram equalization, histogram specification, dehazing, fractional order image enhancement, intuitionistic fuzzy, and interval-valued intuitionistic fuzzy. In terms of overall visual quality and performance metrics, the results showed that the proposed technique surpasses other current methods including entropy, absolute mean brightness error, and contrast improvement index.

Preserving Artistic Legacy: A Frame-Guided Approach for Color Recovery in Aged Tangka Paintings

Over time, the colors in old Tangka paintings can fade due to various factors, including exposure to light, air pollution, humidity, and dust deposition. Interestingly, the frame acts as a physical barrier between the artwork and its surroundings, offering some protection against the harmful factors that contribute to color fading. In this paper, we propose a novel approach to recover the faded colors of Tangka paintings by leveraging the visual cues provided by the frame-covered area. Our method involves the development of an interactive annotation pipeline and the utilization of histogram matching for color restoration. We applied this approach to faded, aged Tangka paintings in Palace Museum’s collection and achieved visually plausible color recovery, even for intricate patterns that are challenging to restore manually.

SHINE_color: Controlling low-level properties of colorful images

Visual perception combines top-down processes arising from participants individual histories, such as expectations and goals, and bottom-up processes that arise from visual stimuli properties, such as luminance and contrast. The precise control of low-level visual stimuli properties is essential when investigating visual perception. Without it, for instance, investigations of bottom-up processes are virtually impossible and investigations of top-down processes risk major confounds when testing and formulating hypotheses. The SHINE (spectrum, histogram, and intensity normalization and equalization) toolbox for MATLAB [1] allows precise control of images’ Fourier amplitude spectra, the normalizing and scaling of luminance and contrast, and exact histogram specification optimized for perceptual visual quality. Following Willenbockel and Cols (2010) advices, here we present an adaptation of the SHINE toolbox, named SHINE_color, which extends SHINE functionalities by allowing the parametrical manipulation of low-level properties of both static and animated colorful images.•Parametric manipulation of low-level properties of colorful images•Spectrum, histogram, and intensity normalization and equalization

Accuracy Assessment of Atmospheric Correction of KMSS-2 Meteor-M #2.2 Data over Northern Eurasia

Atmospheric correction of satellite remote sensing data is a prerequisite for a large variety of applications, including time series analysis and quantitative assessment of the Earth’s vegetation cover. It was earlier reported that an atmospherically corrected KMSS-M (Meteor-M #2) dataset was produced for Russia and neighboring countries. The methodology adopted for atmospheric correction was based on localized histogram matching of target KMSS-M and MODIS reference gap-free and date-matching imagery. In this paper, we further advanced the methodology and quantitatively assessed Level-2 surface reflectance analysis-ready datasets, operatively produced for KMSS-2 instruments over continental scales. Quantitative assessment was based on accuracy, precision, and uncertainty (APU) metrics produced for red and near-infrared bands of the KMSS-2 instrument based on a reference derived from a MODIS MOD09 reconstructed surface reflectance. We compared error distributions at 5%, 20%, and 50% levels of cloudiness and indicated that the cloudiness factor has little impact on the robustness of the atmospheric correction regardless of the band. Finally, the spatial and temporal gradients of accuracy metrics were investigated over northern Eurasia and across different seasons. It was found that for the vast majority of observations, accuracy falls within the −0.010–0.035 range, while precision and uncertainty were below 0.06 for any band. With the successful launch of the most recent Meteor-M #2.3 with a new KMSS-2 instrument onboard, the efficiency and interoperability of the constellation are expected to increase.

Monitoring spring leaf phenology of individual trees in a temperate forest fragment with multi-scale satellite time series

Forest fragmentation has been increasingly exacerbated by deforestation, urbanization, and agricultural expansion. Monitoring the forest fragments via the lens of tree-crown scale leaf phenology is critical to understand tree species phenological responses to climate change and identify the fragment species vulnerable to environmental disturbance. Despite advances in remote sensing for phenology monitoring, detecting tree-crown scale leaf phenology in fragmented forests remains challenging. Simultaneous tracking of key spring phenological events that are crucial to ecosystem functions and climate change responses is also neglected. To address these challenges, we develop a novel tree-crown scale remote sensing phenological monitoring framework to characterize all the critical spring phenological events of individual trees of deciduous forest fragments, with Trelease Woods in Champaign, Illinois as a case study. The novel framework comprises four components: 1) generate high spatiotemporal resolution fusion imagery from multi-scale satellite time series with a hybrid deep learning fusion model; 2) calibrate PlanetScope imagery time series with fusion data using histogram matching; 3) model tree-crown scale phenology trajectory with a Beck logistic-based method; 4) detect a diversity of tree-crown scale phenological events using several phenological metric extraction methods (i.e., threshold- and curve feature-based methods). Combined with weekly in-situ phenological observations of 123 individual trees across 12 broadleaf species from 2017 to 2020, the framework effectively bridges the satellite- and field-based phenological measures for the key spring phenological events (i.e., budswell, budburst, leaf expansion, and leaf maturity events) at the tree-crown scale, particularly for large individuals (RMSE <1 week for most events). Calibration of PlanetScope imagery using multi-scale satellite fusion data in consideration of landscape fragmentation is critical for monitoring tree phenology of forest fragments. Compared to curve feature-based methods, threshold-based phenometric extraction methods demonstrate enhanced capability in detecting spring leaf phenological dynamics of individual trees. Among the phenological events, full leaf out and early leaf expansion events are retrieved with high accuracy using calibrated PlanetScope time series (RMSE from 3 to 5 days and R-squared higher than 0.8). With both intensive satellite and field phenological efforts, this novel framework is at the forefront of interpreting tree-crown scale remotely sensed phenological metrics in the context of biologically meaningful field phenological events in fragmented forest setting.

Unsupervised Pixel-Level Detection of Rail Surface Defects Using Multistep Domain Adaptation

Detection of rail surface defects using deep learning largely relies on supervision with pixel-level ground truths, where the detection accuracy suffers due to unseen image domains. In order to streamline the laborious labeling process and accurately identify defects on rail surfaces a U-Net-based network that integrates spatial and channel attention (SA) modules, multistep domain adaptation (MSDA), and progressive histogram matching (PHM) is developed in the context of pixel-level defects detection in this research. MSDA with an unlabeled intermediate dataset is used to reduce the domain gap underlying different domains. To further improve the adaptation of the transferred model, the PHM method and the self-training method are employed to enhance detection accuracy. Trained in the source domain with ground truths, the deep learning model is then tested in the target domain with no annotations. Experimental results on the RSDD dataset and the Rail-Joint dataset demonstrate the applicability and effectiveness of the proposed approach. By alleviating the domain discrepancy, the developed model drastically enhances the average precision (AP) score of unsupervised detection from 0.103 to 0.861, which shows competitive performance compared with the AP score of 0.895 by the state-of-the-art supervised models. The novelty of this research lies in the development of a hybrid deep learning approach that is able to achieve competitive detection accuracy with a low overlap ratio between domains and few data labeling.

Quantifying morphological changes in middle trapezius with ultrasound scanning and a novel histogram matching algorithm

Quantifying morphological changes in middle trapezius with ultrasound scanning and a novel histogram matching algorithm

Fast textile pattern generation combining MRF-based and Gram-based methods

Textile pattern design is a tedious and challenging task for designers. This paper proposes a fast textile pattern generation algorithm that combines MRF-based and Gram-based methods. First, the reconstruction method based on image optimisation is determined after analysing the specific requirements of textile pattern design. The pre-trained VGG19 is selected as the style feature extraction neural network. Then, we compare the generation results of various combinations of style loss functions and propose a multi-resolution image optimisation method. Finally, the smoothing loss and colour histogram matching are added to improve the generation quality further, thus constructing an image generation algorithm for textile pattern design. Experimental results demonstrate that our algorithm can effectively generate complex textile patterns with global style and local detail features. The average image generation time is 575s, over 84.3% faster than traditional algorithms. At the same time, this algorithm is convenient for switching styles and requires lower computational capability. It can improve pattern design efficiency and promote the application of image generation technology in textile design.

Comparison of Image Normalization Methods for Multi-Site Deep Learning

In this study, we evaluate the influence of normalization on the performance of deep learning networks for tumor segmentation and the prediction of the pathological response of locally advanced rectal cancer to neoadjuvant chemoradiotherapy. The techniques were applied to a multicenter and multimodal magnet resonance imaging data set consisting of 201 patients recorded at six centers. We implemented and investigated six different normalization methods (setting the mean and standard deviation, histogram matching, percentiles, combining percentiles and histogram matching, fixed window and an auto-encoder with adversarial loss using the imaging parameters) and evaluated their impact on four deep learning tasks: tumor segmentation, prediction of treatment outcome, and prediction of sex and age. The latter two tasks were implemented as a reference test. We trained a modified U-Net with different normalization methods in multiple configurations: on all images, images from all centers except one, and images from a single center. Our results show that normalization only plays a minor role in segmentation, with a difference in Dice of less than 0.02 between the best and worst performing networks. For the prediction of sex and treatment outcomes, the percentile method combined with histogram matching works best for all scenarios. The biggest difference in performance, depending on the normalization method, occurs for classification. In conclusion, normalization is especially important for small data sets or for generalizing to different data distributions. The deep learning method was superior to the classical methods only in a minority of cases, probably due to the limited amount of training data.

SUShe: simple unsupervised shadow removal

Shadow removal is an important problem in computer vision, since the presence of shadows complicates core computer vision tasks, including image segmentation and object recognition. Most state-of-the-art shadow removal methods are based on complex deep learning architectures, which require training on a large amount of data. In this paper a novel and efficient methodology is proposed aiming to provide a simple solution to shadow removal, both in terms of implementation and computational cost. The proposed methodology is fully unsupervised, based solely on color image features. Initially, the shadow region is automatically extracted by a segmentation algorithm based on Electromagnetic-Like Optimization. Superpixel-based segmentation is performed and pairs of shadowed and non-shadowed regions, which are nearest neighbors in terms of their color content, are identified as parts of the same object. The shadowed part of each pair is relighted by means of histogram matching, using the content of its non-shadowed counterpart. Quantitative and qualitative experiments on well-recognized publicly available benchmark datasets are conducted to evaluate the performance of proposed methodology in comparison to state-of-the-art methods. The results validate both its efficiency and effectiveness, making evident that solving the shadow removal problem does not necessarily require complex deep learning-based solutions.

Reducing Domain Gap in Frequency and Spatial Domain for Cross-Modality Domain Adaptation on Medical Image Segmentation

Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the domain gap between different image modalities, which is ineffective due to its complicated training process. In this paper, we propose a simple yet effective UDA method based on frequency and spatial domain transfer under multi-teacher distillation framework. In the frequency domain, we first introduce non-subsampled contourlet transform for identifying domain-invariant and domain-variant frequency components (DIFs and DVFs), and then keep the DIFs unchanged while replacing the DVFs of the source domain images with that of the target domain images to narrow the domain gap. In the spatial domain, we propose a batch momentum update-based histogram matching strategy to reduce the domain-variant image style bias. Experiments on two commonly used cross-modality medical image segmentation datasets show that our proposed method achieves superior performance compared to state-of-the-art methods.

Echocardiogram Image Quality Enhancement using Upsampling and Histogram Matching Methods

The prevalence of heart disease has been increasing in the last ten years. One of the cardiac diagnostic tools is echocardiography. Echocardiogram medical images provide essential information, including shape, size, pumping capacity, heart function abnormalities, and location of heart damage, but echocardiogram images have high noise content and poor contrast, as well as limitations due to differences in anatomy or body mass. This will affect the reading results of patient diagnosis. Therefore, image quality improvement is needed by removing noise and increasing image contrast. This research has improved image quality using a method with low mathematical complexity and a fast computational process. The method used is the Upsampling method to generate a reference image. The quality of the image produced was the Nearest Neighbor upsampling method: 2.8 dB, Bi-linear Interpolation: 2.78 dB, and Bi-cubic Interpolation: 2.73 dB. Furthermore, the image with the highest SNR value is processed with Histogram Matching to accelerate improving image quality. The Histogram Matching image increases quality by more than 50% with a SSIM value of 0.54. The required computational process to apply this method to each medical image has an average duration of 0.4 s. This result provides a higher value than several methods using linear scaling and speckle reducing.

Direct phasing algorithm for protein crystals with high solvent content using low-resolution diffraction data.

Over the past decade, iterative projection algorithms, an effective approach to recovering phases from a single intensity measurement, have found application in protein crystallography to directly surmount the `phase problem'. However, previous studies have always assumed that some prior knowledge constraints (i.e. a low-resolution envelope about the protein structure in the crystal cell or histogram matching requiring a similar density distribution to the target crystal) must be known for successful phase retrieval, thus hindering its widespread application. In this study, a novel phase-retrieval workflow is proposed that eliminates the need for a reference density distribution by utilizing low-resolution diffraction data in phasing algorithms. The approach involves randomly assigning one out of 12 possible phases at 30° intervals (or two for centric reflections) to produce an initial envelope, which is then refined through density modification after each run of phase retrieval. To evaluate the success of the phase-retrieval procedure, information entropy is introduced as a new metric. This approach was validated using ten protein structures with high solvent content, demonstrating its effectiveness and robustness.

Relaxation-Based Radiometric Normalization for Multitemporal Cross-Sensor Satellite Images

Multitemporal cross-sensor imagery is fundamental for the monitoring of the Earth’s surface over time. However, these data often lack visual consistency because of variations in the atmospheric and surface conditions, making it challenging to compare and analyze images. Various image-normalization methods have been proposed to address this issue, such as histogram matching and linear regression using iteratively reweighted multivariate alteration detection (IR-MAD). However, these methods have limitations in their ability to maintain important features and their requirement of reference images, which may not be available or may not adequately represent the target images. To overcome these limitations, a relaxation-based algorithm for satellite-image normalization is proposed. The algorithm iteratively adjusts the radiometric values of images by updating the normalization parameters (slope (α) and intercept (β)) until a desired level of consistency is reached. This method was tested on multitemporal cross-sensor-image datasets and showed significant improvements in radiometric consistency compared to other methods. The proposed relaxation algorithm outperformed IR-MAD and the original images in reducing radiometric inconsistencies, maintaining important features, and improving the accuracy (MAE = 2.3; RMSE = 2.8) and consistency of the surface-reflectance values (R2 = 87.56%; Euclidean distance = 2.11; spectral angle mapper = 12.60).

Gaussianization of LA-ICP-MS features to improve calibration in forensic glass comparison

The forensic comparison of glass aims to compare a glass sample of an unknown source with a control glass sample of a known source. In this work, we use multi-elemental features from Laser Ablation Inductively Coupled Plasma with Mass Spectrometry (LA-ICP-MS) to compute a likelihood ratio. This calculation is a complex procedure that generally requires a probabilistic model including the within-source and between-source variabilities of the features. Assuming the within-source variability to be normally distributed is a practical premise with the available data. However, the between-source variability is generally assumed to follow a much more complex distribution, typically described with a kernel density function. In this work, instead of modeling distributions with complex densities, we propose the use of simpler models and the introduction of a data pre-processing step consisting on the Gaussianization of the glass features. In this context, to obtain a better fit of the features with the Gaussian model assumptions, we explore the use of different normalization techniques of the LA-ICP-MS glass features, namely marginal Gaussianization based on histogram matching, marginal Gaussianization based on Yeo-Johnson transformation and a more complex joint Gaussianization using normalizing flows. We report an improvement in the performance of the Likelihood Ratios computed with the previously Gaussianized feature vectors, particularly relevant in their calibration, which implies a more reliable forensic glass comparison.