Tone Curve Research Articles

Single Image Enhancement Using Gradient-Norm-Based Tone Curve for Images Captured in Wide-Dynamic-Range Scenes

Single Image Enhancement Using Gradient-Norm-Based Tone Curve for Images Captured in Wide-Dynamic-Range Scenes

The software for improvement of image quality after enlargement

In the paper digital images of various formats were investigated. The different vector image formats have different color rendering capabilities. The main task was to achieve a result of refinement of the random low resolution color raster image without quality and resolution loss. The biggest advantage of using specific vector or compressed raster formats is the ability of scaling without quality loss and comparatively small file size. This eases vector images transfer through networks. In the article a specific algorithm of raster images refinement was investigated, particularly the method of raster images refinement based on combination of interpolation algorithms with and without square root of the color values. The key point of the method is comparison and combination of vertical, horizontal and diagonal interpolation that allows to achieve better precision on color depth calculation. This exact method was never used in commercial of scientific software though there are different variation of combined interpolation methods similar to current one. In this paper two different approaches to image matrix re-calculation during image refinement were tested, in order to research how root squaring the value of color depth would affect the target color value. The result shows that this approach allows to keep more details in shadows and save contours during interpolation though the images lose somewhat of color depth. The experiment shows that this interpolation method with square rooting color values allows to enlarge and refine color images with complex tone curve structure and keep details of the objects in place, though color depth is worsened especially in deepest shades and blacks. On the opposite the method of combined interpolation without root squaring gives significantly better result with color interpolation but loses details in the dark areas of the initial image. The suggested method can be used in a number of different areas

ColorfulCurves: Palette-Aware Lightness Control and Color Editing via Sparse Optimization

Color editing in images often consists of two main tasks: changing hue and saturation, and editing lightness or tone curves. State-of-the-art palette-based recoloring approaches entangle these two tasks. A user's only lightness control is changing the lightness of individual palette colors. This is inferior to state-of-the-art commercial software, where lightness editing is based on flexible tone curves that remap lightness. However, tone curves are only provided globally or per color channel (e.g., RGB). They are unrelated to the image content. Neither tone curves nor palette-based approaches support direct image-space edits---changing a specific pixel to a desired hue, saturation, and lightness. ColorfulCurves solves both of these problems by uniting palette-based and tone curve editing. In ColorfulCurves , users directly edit palette colors' hue and saturation, per-palette tone curves, or image pixels (hue, saturation, and lightness). ColorfulCurves solves an L 2,1 optimization problem in real-time to find a sparse edit that satisfies all user constraints. Our expert study found overwhelming support for ColorfulCurves over experts' preferred tools.

Real-time self-supervised tone curve estimation for HDR image

High dynamic range (HDR) image acquisition technology can record real-scene information. However, most display devices only support standard dynamic range images; therefore, dynamic range compression via tone mapping operators is a key technology for HDR image visualization. Recently, deep learning has achieved significantly better results than traditional methods in tone mapping; however, some problems remain. On the one hand, the labels of datasets are usually selected from the results of existing traditional methods, which limit the quality of newly generated results. On the other hand, these algorithms require huge computational resources and cannot be practically applied. As the dynamic range can be compressed using an intuitive and simple sigmoid curve mapping, a lightweight network is designed in this study to estimate the patch-wise tone curve parameters for HDR images. Simultaneously, the differentiable approximation of tone mapped image quality assessment is introduced as a self-supervised loss term so that the method only needs HDR data as training data. Experimental results demonstrate that the proposed method achieves better results than existing methods in both objective and subjective metrics at a low computational cost.

Comparative Analysis of Color Simulation between Offset Printing and Inkjet Printing

This paper presents an analysis of the color output capability and accuracy of an inkjet printer, specifically the Epson L1800, used for simulating offset printing. The colorimetric values of the printer's cyan, magenta, yellow, and black primaries were found to be different from those used in offset printing, and attempts to adjust the maximal output ink level and tone curve were not able to fully eliminate the differences. As a result, the Epson printer's color gamut did not completely meet the requirements of offset printing, particularly in terms of high-chroma colors. However, the printer calibration process improved the printer's capacity and overall color output accuracy within the offset color gamut, with significant color differences only occurring for colors outside the printer's gamut. This study provides insights into the challenges and limitations of using an inkjet printer for simulating offset printing and highlights the importance of printer calibration for achieving accurate color reproduction in this context. Further research may focus on developing more advanced calibration methods or exploring alternative printer technologies to improve the accuracy of offset printing simulation using inkjet printers.

High dynamic range image compression based on the multi-peak S-shaped tone curve.

Tone mapping methods aim to compress the high dynamic range (HDR) images so that they can be displayed on common devices. The tone curve plays a key role in many tone mapping methods, which can directly adjust the range of the HDR image. The S-shaped tone curves can produce impressive performances due to their flexibility. However, the conventional S-shaped tone curve in tone mapping methods is single and had the problem of excessive compressing of the dense grayscale areas, resulting in the loss of details in this area, and insufficient compressing of the sparse grayscale areas, resulting in low contrast of tone mapped image. This paper proposes a multi-peak S-shaped (MPS) tone curve to address these problems. Specifically, the grayscale interval of the HDR image is divided according to the significant peak and valley distribution of the grayscale histogram, and each interval is tone mapped by an S-shaped tone curve. We further propose an adaptive S-shaped tone curve based on the luminance adaptation mechanism of the human visual system, which can effectively reduce the compression in the dense grayscale areas and increase the compression in the sparse grayscale areas, preserving details while improving the contrast of tone mapped images. Experiments show that our MPS tone curve replaces the single S-shaped tone curve in relevant methods for better performance and outperforms the state-of-the-art tone mapping methods.

GAN‐based tone curve learning for colour transfer

A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior learning, which results in unnatural output images when inappropriate images are learned; moreover, in such situations, analysing what kind of colour transformation has actually been performed is difficult. This state of the art motivates the proposal of a new colour transfer method that estimates tone curves based on generative adversarial nets. This method does not require any data set other than input and reference images, thus enabling a more appropriate colour transfer. The superior output of the proposed method compared with some baseline approaches is demonstrated through experiments.

Towards a Generic Neural Network Architecture for Approximating Tone Mapping Algorithms

Tone curves are a key feature in any image processing pipeline, and are used to change the pixel values of an input image to find an output image that looks better. Perhaps the most widely deployed tone curve algorithm is Contrast Limited Histogram Equalisation (CLHE). CLHE is an iterative algorithm that tone maps an input image so that the histogram of the output is (approximately) maximally uniform subject to the constraint that the tone curve has bounded slope (neither too large or too small).In this paper, we build upon a neural network framework [1] that was recently developed to deliver CLHE in fewer iterations (each layer in the neural network is analogous to a single iteration of CLHE, but the network has fewer layers than the number of iterations needed by CLHE). The key contribution of this paper is to show that the same network architecture can be used to implement a more complex (and more powerful) tone mapping algorithm. Experiments validate our method.

Weibull Tone Mapping for Underwater Imagery

Imagery is a preferred tool for environmental surveys within marine environments, particularly in deeper waters, as it is nondestructive compared to traditional sampling methods. However, underwater illumination effects limit its use by causing extremely varied and inconsistent image quality. Therefore, it is often necessary to pre-process images to improve visibility of image features and textures, and standardize their appearance. Tone mapping is a simple and effective technique to improve contrast and manipulate the brightness distributions of images. Ideally, such tone mapping would be automated, however we found that existing techniques are inferior when compared to custom manipulations by image annotators (biologists). Our own work begins with the observation that these userdefined tonal manipulations are quite variable, though on average, are fairly smooth, gentle waving operations. To predict user-defined tone maps we found it sufficed to approximate the brightness distributions of input and user adjusted images by Weibull distributions and then solve for the tone curve which matched these distributions from input to output. Experiments demonstrate that our Weibull Tone Mapping (WTM) method is strongly preferred over traditional automated tone mappers and weakly preferred over the users' own tonal adjustments.

Tone Curve Compensation of Multiple Color Halftoning Screen Printing for Heterogeneous Fabrics

For mass production, multiple color halftoning screen printing (MCHSP) can be considered as the alternative textile printing technology when vivid color gradation is needed and cost for digital printing is concerned. Essentially, MCHSP utilizes the same equipment as traditional screen printing to print overlapped multiple color gradation under halftoning patterns by applying the dedicated treatments on color separation and calibration. In order to ensure the color quality, the equipment calibration and tone curve compensation are required to compensate the variables from equipment setup and heterogeneous fabrics. In this research, we provided the procedure of tone curve compensation to alleviate the discrepancy from heterogeneous fabrics. The experimental result based on 55 samples of 44 different fabrics shows the compensation effectiveness and reveal the distribution of average compensation percentage across fabrics.

Linear Histogram Adjustment for Image Enhancement

Tone curves are one of the simplest techniques for image enhancement. Specified as a function, a tone curve is a transformation that maps pixel levels of an input image to new output levels. Tone curves are the basis of many contrast enhancement algorithms, including Contrast Limited Histogram Equalisation (CLHE), which derives a tone curve from a modification of the image histogram. While these methods can provide good enhancement, they are generally non-linear. In this paper we show the surprising result that a tone curve generated by the non-linear CLHE method (and HE) can be calculated by applying a linear transform to the histogram of the input image. Experiments validate our method.

Tone Curve Compensation of Multiple Color Halftoning Screen Printing for Heterogeneous Fabrics

Abstract For mass production, multiple color halftoning screen printing (MCHSP) can be considered as the alternative textile printing technology when vivid color gradation is needed and the cost of digital printing is a concern. Essentially, MCHSP utilizes the same equipment as traditional screen printing to print overlapping multiple color gradation under halftoning patterns by applying dedicated treatments on color separation and calibration. To ensure color quality, equipment calibration and tone curve compensation are required to compensate for the variables arising from equipment setup and heterogeneous fabrics. In this research, the authors present a procedure of tone curve compensation to eliminate the discrepancy from heterogeneous fabrics. The experimental results based on 55 samples of 44 different fabrics show the effectiveness of compensation and reveal the distribution of average compensation percentage across fabrics.

Edge Enhancement from Low-Light Image by Convolutional Neural Network and Sigmoid Function

Due to camera resolution or any lighting condition, captured image are generally over-exposed or under-exposed conditions. So, there is need of some enhancement techniques that improvise these artifacts from recorded pictures or images. So, the objective of image enhancement and adjustment techniques is to improve the quality and characteristics of an image. In general terms, the enhancement of image distorts the original numerical values of an image. Therefore, it is required to design such enhancement technique that do not compromise with the quality of the image. The optimization of the image extracts the characteristics of the image instead of restoring the degraded image. The improvement of the image involves the degraded image processing and the improvement of its visual aspect. A lot of research has been done to improve the image. Many research works have been done in this field. One among them is deep learning. Most of the existing contrast enhancement methods, adjust the tone curve to correct the contrast of an input image but doesn’t work efficiently due to limited amount of information contained in a single image. In this research, the CNN with edge adjustment is proposed. By applying CNN with Edge adjustment technique, the input low contrast images are capable to adapt according to high quality enhancement. The result analysis shows that the developed technique significantly advantages over existing methods.

Least-Squares Optimal Contrast Limited Histogram Equalisation

Contrast Limited Histogram Equalisation moves the input image histogram gently towards one which has a more uniform distribution. Viewed as a tone mapping operation, CLHE generates a tone curve with bounded max and min slopes. It is this boundedness which ensures that the processed images have more detail but few artefacts. Outside of limiting contrast, recent improvements to histogram equalisation include constraining the tone curve to make good whites and blacks and constraining the tone curve to be smooth. This paper makes three contributions. First, we show that the CLHE formalism is not least-squares optimal but optimality can be achieved by reformulating the problem in a quadratic programming framework. Second, we incorporate the additional constraints of tone curve smoothness and good whites and blacks in our quadratic programming CLHE framework. Third, experiments demonstrate the utility of our method.

음성학적 연구에 기반 한 중국어 3성교육에 대한 재고

The purpose of this study is to analyze the contents of tone3 in textbooks for native speakers and foreign learners and to compare the characteristics of the three characters defined in the textbooks and the actual features of the three characters recorded in the textbooks through phonetic analysis. In case of pronouncing singly, the tone curve is low and smooth. Most of the tone is not more than 1-2 degree. In other words, the stable characteristic of the three is in "low" rather than "rising". When the tone3 is located in the front syllable, most syllables are pronounced as "21" or "32", as described in the textbook. When the tone3 is located at the end of the back syllable or sentence, similar to the result of (1), but a little more various numerical values due to the intonation of the sentence, the characteristics of the low elliptical tone are unchanged, which was also different from the description of the textbook. If you give up the characteristic of "rising", students can distinguish it from "tone2. According to the results of the above analysis and the discrimination characteristics of the tone3 revealed in the previous study, the characteristics of the tone3 defined by many textbooks do not accurately reflect the pronunciation of the actual Chinese speaker, and the tone curve depicting the tone3 , The textbook contents have to review, and the teacher should exclude the "rising" characteristic to be emphasized.

Changes in indicators of intonation structure of speech in occupational activity of air traffic control operators

Introduction.The study is aimed to determine possible use of vocal signal analysis for diagnosis of functional states in air traffic control operators, with justifying selection of informative parameters of intonation structure of speech.Materials and methods.Experiments on semi-natural simulator complex with participation of 16 air traffic male dispatchers modelled occupational activity of air traffic dispatcher with moderate (6 aircrafts controlled) and intense (7–12 aircrafts controlled) work load. Duration of simulated working shiftwas 6 hours. Registration covered characteristics of main vocal tone of the examinees, with calculation of 8 jitter-factors that portrayed mirco-changes of main vocal tone curve and 2 tremor indices disclosing periodic waves of 4–16 Hz in main vocal tone curve. Functional state of the dispatchers was assessed via cardiac rhythm parameters. Reliability and work capacity of the dispatchers corresponded to correct radio traffi c, changes in threshold of reception and transfer of aircrafts in number of allowable dangerous approach of aircrafts, time to detection of input aircraft’s deviation from preset flight line.Results and discussion.According to analysis of the experiments results, some parameters of the main vocal tone carried significant changes both in first (simulated moderate work load) and second (simulated intense work load) experimental series.The data obtained prove lower level of psychic regulation of the dispatchers’ occupational activity during 3rd to 5thhours of “working shift” in the first experimental series and from 2nd to 4thhours of the second experimental series, due to decreased psychophysiologic resources and developing fatigue.Conclusion.Studies of changes in indicators of intonation structure of speech in occupational activity of air traffic dispatchers demonstrated that using such indicators provides adequate diagnosis of the functional state. The most informative indicators are average value, histogram asymmetry and excessive frequency of main vocal tone, duration of pauses between words of the dispatchers’ commands and fi ft h jitter-factor.

Enhancing Multi Exposure Images Using Convolution Neural Network

Due to the poor lighting condition and restricted dynamic vary of digital imaging devices, the recorded photos are usually under-/over-exposed and with low distinction. Most of the previous single image distinction improvement (SICE) strategies modify the tone curve to correct the distinction of an associated input image. Those strategies, however, typically fail in revealing image details due to the restricted data in a very single image. On the opposite hand, the SICE task is often higher accomplished if we will learn additional info from suitably collected coaching information. In this paper, we have a tendency to propose to use the convolutional neural network (CNN) to coach SICE attention. One key issue is the way to construct a coaching information set of low-contrast and high-contrast image pairs for end-to-end CNN learning. To this finish, we have a tendency to build a large-scale multi-exposure image knowledge set, that contains 589 in an elaborate way chosen high-resolution multi-exposure sequences with four, 413 images. Thirteen representatives multi-exposure image fusion and stack-based high dynamic vary imaging algorithms are accustomed urge the excellence enhanced footage for each sequence, and subjective experiments are conducted to screen the best quality one because of the reference image of every scene. With the constructed data set, a CNN can be easily trained as the SICE enhancer to improve the contrast of an under-/over-exposure image. Experimental results demonstrate the benefits of our methodology over existing SICE strategies with a major margin.

Core Color Rendering Algorithms for High Dynamic Range Display

As is well known, colors as they exist in the real world must be adjusted so as to look correct and pleasing when displayed on a TV or a cinema screen. In color science, the process of converting these “scene-referred” colors to “display-referred” colors is termed “rendering.” The Academy Color Encoding System (ACES) is a good example of a set of open-source picture rendering algorithms. In this paper, the authors, who both participated in the development of ACES, discuss the pros and cons of various rendering techniques and share the results of their latest work. Specifically, we present a method of applying a tone curve that preserves color ratios and has better noise properties than earlier techniques. This algorithm has been successfully used as part of a larger parametric rendering system for high dynamic range display. One of the nice properties of this algorithm is that it has a simple and robust inverse.

Automatic saturation correction for dynamic range management algorithms

High dynamic range (HDR) images require tone reproduction to match the range of values to the capabilities of a display. For computational reasons and given the absence of fully calibrated imagery, rudimentary color reproduction is often added as a post-processing step rather than integrated into tone reproduction algorithms. In the general case, this currently requires manual parameter tuning, and can be automated only for some global tone reproduction operators by inferring parameters from the tone curve. We present a novel and fully automatic saturation correction technique, suitable for any tone reproduction operator (including inverse tone reproduction), which exhibits fewer distortions in hue and luminance reproduction than the current state-of-the-art. We validated its comparative effectiveness through subjective experiments and objective metrics. Our experiments confirm that saturation correction significantly contributes toward the perceptually plausible color reproduction of tonemapped content and would, therefore, be useful in any color-critical application.

Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images.

Due to the poor lighting condition and limited dynamic range of digital imaging devices, the recorded images are often under-/over-exposed and with low contrast. Most of previous single image contrast enhancement (SICE) methods adjust the tone curve to correct the contrast of an input image. Those methods, however, often fail in revealing image details because of the limited information in a single image. On the other hand, the SICE task can be better accomplished if we can learn extra information from appropriately collected training data. In this work, we propose to use the convolutional neural network (CNN) to train a SICE enhancer. One key issue is how to construct a training dataset of low-contrast and high-contrast image pairs for end-to-end CNN learning. To this end, we build a large-scale multi-exposure image dataset, which contains 589 elaborately selected high-resolution multi-exposure sequences with 4,413 images. Thirteen representative multi-exposure image fusion and stack-based high dynamic range imaging algorithms are employed to generate the contrast enhanced images for each sequence, and subjective experiments are conducted to screen the best quality one as the reference image of each scene. With the constructed dataset, a CNN can be easily trained as the SICE enhancer to improve the contrast of an under-/over-exposure image. Experimental results demonstrate the advantages of our method over existing SICE methods with a significant margin.