RGB Color Space Research Articles

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Different kinds of techniques are evaluated and analyzed for various classification models for the detection of diseases of citrus fruits. This paper aims to systematically review the papers that focus on the prediction, detection, and classification of citrus fruit diseases that have employed machine learning, deep learning, and statistical techniques. Additionally, this paper explores the present state of the art of the concept of image acquisition, digital image processing, feature extraction, and classification approaches, and each one is discussed separately. A total of 78 papers are selected after applying primary selection criteria, inclusion/exclusion criteria, and quality assessment criteria. We observe that the following are widely used in the selected studies: hyperspectral imaging systems for the image acquisition process, thresholding for image processing, support vector machine (SVM) models as machine learning (ML) models, convolutional neural network (CNN) architectures as deep learning models, principal component analysis (PCA) as a statistical model, and classification accuracy as evaluation parameters. Moreover, the color feature is the most popularly used feature for the RGB color space. From the review studies that performed comparative analyses, we find that the best techniques that outperformed other techniques in their respective categories are as follows: SVM among the ML methods, ANN among the neural network networks, CNN among the deep learning methods, and linear discriminant analysis (LDA) among the statistical techniques.This study concludes with meta-analysis, limitations, and future research directions.

TCRN: A Two-Step Underwater Image Enhancement Network Based on Triple-Color Space Feature Reconstruction

The underwater images acquired by marine detectors inevitably suffer from quality degradation due to color distortion and the haze effect. Traditional methods are ineffective in removing haze, resulting in the residual haze being intensified during color correction and contrast enhancement operations. Recently, deep-learning-based approaches have achieved greatly improved performance. However, most existing networks focus on the characteristics of the RGB color space, while ignoring factors such as saturation and hue, which are more important to the human visual system. Considering the above research, we propose a two-step triple-color space feature fusion and reconstruction network (TCRN) for underwater image enhancement. Briefly, in the first step, we extract LAB, HSV, and RGB feature maps of the image via a parallel U-net-like network and introduce a dense pixel attention module (DPM) to filter the haze noise of the feature maps. In the second step, we first propose the utilization of fully connected layers to enhance the long-term dependence between high-dimensional features of different color spaces; then, a group structure is used to reconstruct specific spacial features. When applied to the UFO dataset, our method improved PSNR by 0.21% and SSIM by 0.1%, compared with the second-best method. Numerous experiments have shown that our TCRN brings competitive results compared with state-of-the-art methods in both qualitative and quantitative analyses.

Exploring multivariate generalized gamma manifold for color texture retrieval

This work proposes a novel method for color-textured image retrieval on a Multivariate Generalized Gamma Distribution manifold (MGΓD). Thanks to the Gaussian copula theory, we define the expression of MGΓD, which efficiently models the statistical dependence structure between dual-tree complex wavelet transform (DTCWT) of the color components. The major contribution of this paper is to provide a geometric perspective to the MGΓD by treating it as a Riemannian manifold while proposing the geodesic distance (GD) as a measure of Riemannian similarity on it. Based on information geometry tools, we conduct a geometrical study of the MGΓD manifold, allowing us to derive two suitable approximations of the GD. The experiments are performed on five well-known color texture databases, considering the content-based image retrieval (CBIR) framework and using the RGB color space. The obtained results demonstrate the efficiency of the geometric interpretation through the proposed GD as a natural and intuitive similarity measure on the studied statistical manifold.

An enhanced 2-D color space diversity using RGB-LED overlapping for optical camera communication

In this paper, an enhanced two-dimension (2-D) color space diversity technique using red, green, and blue light emitting diode (RGB LED) overlapping is proposed and investigated experimentally to improve the system reliability for optical camera communication (OCC). The transmitter adopts an 8-color shift keying (8-CSK) modulation scheme with two RGB LED overlapping. The receiver uses a camera to form a multi-input single-output system to improve capacity. Different mapping methods are proposed and compared in 2-D YCbCr and CIElab color space to avoid the influence of brightness in conventional 3-D RGB space. Besides, clustering-based demapping is applied in the OCC system to transfer the color information into a data stream. The experimental results show that the mapping scheme with the maximum Euclidean distance in 2-D YCbCr color space has the best bit error rate (BER) performance. Compared with the conventional 3-D RGB color space, the proposed enhanced 2-D YCbCr color space diversity has a higher resolution to signal, which can realize 1.46 dB Q-factor improvement at an illumination of 660 lux. In addition, it can achieve a net data rate of 11.52 kb/s and maintain a 7% forward error correction (FEC) requirement even under low illumination. It is verified that the proposed scheme is a potential application for capacity and performance improvement.

Semiquantitative color catcher and smartphone-based analysis of synthetic food dyes in alcohol containing beverages

Solid phase extraction, based on the use of color catcher sheets, was successfully employed for the preconcentration of food dyes from alcohol containing beverages. The photos of color catcher sheets with the adsorbed dyes were taken with a mobile phone. The smartphone-based image analysis of the photos was performed using Color Picker application. The values of several color spaces were collected. Specific values from RGB, CMY, RYB and LAB color spaces were proportional to the dye concentration in the analyzed samples. The described inexpensive, simple and elution free assay enables analysis of dyes concentration in various solutions.

Plasmonic Metamaterial Ag Nanostructures on a Mirror for Colorimetric Sensing.

In this study, we demonstrate the localized surface plasmon resonance (LSPR) in the visible range by using nanostructures on mirrors. The nanohemisphere-on-mirror (NHoM) structure is based on random nanoparticles that were obtained by heat-treating silver thin films and does not require any top-down nanofabrication processes. We were able to successfully tune over a wide wavelength range and obtain full colors using the NHoM structures, which realized full coverage of the Commission Internationale de l'Eclairage (CIE) standard RGB (sRGB) color space. Additionally, we fabricated the periodic nanodisk-on-glass (NDoG) structure using electron beam lithography and compared it with the NHoM structure. Our analysis of dark-field microscopic images observed by a hyperspectral camera showed that the NHoM structure had less variation in the resonant wavelength by observation points compared with the periodic NDoG structure. In other words, the NHoM structure achieved a high color quality that is comparable to the periodic structure. Finally, we proposed colorimetric sensing as an application of the NHoM structure. We confirmed the significant improvement in performance of colorimetric sensing using the NHoM structure and succeeded in colorimetric sensing using protein drops. The ability to fabricate large areas in full color easily and inexpensively with our proposed structures makes them suitable for industrial applications, such as displays, holograms, biosensing, and security applications.

Automatic Monitoring Alarm Method of Dammed Lake Based on Hybrid Segmentation Algorithm

Mountainous regions are prone to dammed lake disasters due to their rough topography, scant vegetation, and high summer rainfall. By measuring water level variation, monitoring systems can detect dammed lake events when mudslides block rivers or boost water level. Therefore, an automatic monitoring alarm method based on a hybrid segmentation algorithm is proposed. The algorithm uses the k-means clustering algorithm to segment the picture scene in the RGB color space and the region growing algorithm on the image green channel to select the river target from the segmented scene. The pixel water level variation is used to trigger an alarm for the dammed lake event after the water level has been retrieved. In the Yarlung Tsangpo River basin of the Tibet Autonomous Region of China, the proposed automatic lake monitoring system was installed. We pick up data from April to November 2021, during which the river experienced low, high, and low water levels. Unlike conventional region growing algorithms, the algorithm does not rely on engineering knowledge to pick seed point parameters. Using our method, the accuracy rate is 89.29% and the miss rate is 11.76%, which is 29.12% higher and 17.65% lower than the traditional region growing algorithm, respectively. The monitoring results indicate that the proposed method is a highly adaptable and accurate unmanned dammed lake monitoring system.

Underwater image enhancement combining dual color space and contrast learning

With the continuous increase of human society’s demand for marine resources, underwater vision plays an increasingly important role in marine information acquisition. However, due to the absorption and scattering of light, underwater images have characteristics such as blurring, low contrast, and color distortion, which are not conducive to the acquisition of underwater image information. The rapid development of deep learning and powerful feature learning capabilities have been widely used in underwater image enhancement tasks, but current research still has problems such as loss of local details and oversaturation. Aiming at the above problems, this paper proposes an underwater image enhancement method combining dual color space and contrast learning, including RGB color space and Lab color space. The RGB color space is used for color correction and artifact removal, and the Lab color space is used to enhance saturation and detail texture. The contrastive learning of positive and negative samples makes the generated image closer to the clear underwater image and deviates from the real underwater image. Experimental results on real underwater datasets show that the proposed method achieves the best results on PSNR, SSIM and UIQM compared to other underwater image enhancement methods.

Tracing and visualisation of contributing water sources in the LISFLOOD-FP model of flood inundation (within CAESAR-Lisflood version 1.9j-WS)

Abstract. We describe the formulation of a simple method of water source tracing for computational models of flood inundation and demonstrate its implementation within CAESAR-Lisflood. Water source tracing can provide additional insight into flood dynamics by accounting for flow pathways of each model boundary condition. The method developed is independent of the hydraulic formulation used, allowing it to be implemented in other model codes without affecting flow routing. In addition, we developed a method which allows up to three water sources to be visualised in the RGB colour space, while continuing to allow depth to be resolved. The number of water sources that may be traced is limited only by the computational resources. We show the application of the methods developed for example applications of a major flood event, a shallow estuary, and Amazonian wetland inundation. A key advantage is that the method is independent of the hydraulic formulation, meaning that it is relatively straightforward to add to existing finite-volume codes, including those based on or developed around the LISFLOOD-FP method. This method enables water tracing with a minimal computational overhead, allowing users of the LISFLOOD-FP method to address environmental issues relating to water sources and mixing, such as water quality and contamination problems.

PA-ColorNet: progressive attention network based on RGB and HSV color spaces to improve the visual quality of underwater images

PA-ColorNet: progressive attention network based on RGB and HSV color spaces to improve the visual quality of underwater images

Support Vector Machine Based Classification of Leaf Diseases

Myanmar is well known for agricultural country; wherein about 65% of the labor force depends on agriculture. Since the leaf diseases are microscopic organism, cannot be detected normal human eyes. Leaves are special indicator to distinguish the diseases because the image information of the leaf are changed when the leaf surf the diseases. So, the image processing techniques can be used in agricultural sector. The research work presents a support vector machine classifier algorithm by using MATLAB R2017a for the classification of leaf diseases such as Alternaria Alternata, Cercospora leaf spot, Bacterial Blight and so on. In this research work, RGB color space is converted into HSI (Hue Saturation Intensity) color space. In segmentation step, k-means clustering is used to select the defected area, and it is extracted the features by using GLCM (Gray Level Co-occurrence Matrix). Prior to the features extraction, the median filter is used for getting noise free feature results. Finally, the leaf disease is classified by using support vector machine (SVM) and computes the accuracy. From the obtained results, the maximum accuracy of the system is 83%.

Fire Warning Algorithm based on Combining R-S Fusion Layer Images with Convolutional Neural Networks

In order to overcome the problems of low detection rate and high false alarm rate of fire detection system, a video fire detection algorithm based on R-S weighted model and convolutional neural network is proposed. First, the R-S fusion layer image is obtained by RGB color space and HSI color space; Then, the convolutional neural network is used to construct the fire detection algorithm. During the training process, the extracted R-S fusion layer image is sent to the convolutional neural network for training. During the detection process, the test image is sent to the model for detection. The experimental results show that the method has more effective flame detection effect.

A device-independent method for the colorimetric quantification on microfluidic sensors using a color adaptation algorithm.

Ageneral and adaptable method is proposedto reliably extract quantitative information from smartphone images of microfluidic sensors. By analyzing and processing the color information of selected standard substances, the influence of light conditions, device differences, and human factors could be significantly reduced. Machine learning and multivariate fitting methods were proved to be effective for chroma correction, and a key element was the training ofsample size and the fitting form, respectively. A custom APP was developed and validated using a high-sensitivity chromium ion quantification paper chip. The average chroma deviations under different conditions were reduced by more than 75% in RGB color space, and the concentration test error was reduced by more than half compared with the commonly used method. The proposed approach could be a beneficial supplement to existing and potential colorimetry-based detection methods.

Novel apparatus for monitoring simultaneously color and °Brix of selected fruit juices through RGB image analysis

AbstractThis work introduces a novel apparatus for monitoring both color and °Brix of selected fruit juices. These parameters are essential for quality and processing control at concentration and dilution operations. The proposed apparatus performs the red, green, and blue (RGB) image analysis of the fruit juice as it flows through a transparent cell equipped with a webcam and a light source. The viewing cell is inside a box for controlling temperature and for ensuring homogeneous lighting. This apparatus not only measures the RGB color space of the fruit juice online but also allows relating it to the °Brix. The relationship between RGB and °Brix was obtained by measuring the RGB color space of various fruit juice samples, of which the °Brix were previously determined using a digital refractometer. RGB image analysis showed an excellent relationship with °Brix (R2 > 0.99, using an exponential fit), allowing for monitoring reliably this parameter during continuous fruit juice concentration and dilution experiments. These results show the potential of this novel apparatus to substitute conventional instruments such as colorimeters and refractometers for online process monitoring. Furthermore, it has the advantage of not requiring sampling, which reduces measurement errors and saves time.Practical applicationsThis work introduces a novel apparatus based on RGB image analysis for monitoring simultaneously the color and the °Brix of fruit juices. These parameters are important to control the production and quality of fruit juices, especially at concentration and dilution operations. The apparatus proposed here is a viewing cell where the RGB color space is quantified using the software RGBview® as the fruit juice flows through it. The °Brix are determined from the RGB color space using a suitable fit obtained from a previous calibration with juice samples with known °Brix. This is an alternative to conventional analytical instruments such as colorimeters and refractometers but with the advantage of performing an online measurement. This configuration allows for the reduction of analytical errors associated with sampling and saves time. Moreover, this apparatus has the potential to monitor other physicochemical properties related to the color of fruit juices.

Maximum Gradient Autofocus Technology of Microsporidia Images Based on Color Feature

There are many impurities in the microscopic images of extracted microsporidia samples of Bombyx mori pebrine, and Bombyx mori pebrine with elliptical symmetric shape has certain fluidity and obvious stratification. Traditional focusing methods cannot accurately locate the main regions of microsporidia images, and the focusing effect is poor. On this basis, an automatic focusing method combining the microsporidia image features and the evaluation and determination of maximum gradient direction is proposed. First, the HSV color space with stable color information is used to extract the suspected positions of microsporidia targets, so that the interference of some impurities under complex backgrounds is removed and the redundancy of image content calculation is reduced. Then, combined with the light green features of Bombyx mori pebrine, the G-component gray image of microsporidia in the RGB color space is used to extract the significant gradient region. A dynamic focus window is constructed to accurately locate the target region and reduce the influence of microsporidia flow on the focus evaluation function and the bimodal interference caused by impurities. Finally, the maximum second-order difference is obtained through the four-dimensional gradient distribution, and the focus sharpness evaluation function is formulated to adapt to the microsporidia shape and improve the sensitivity of the focus function. The experiments show that under the dynamic window of microsporidia color gradient of different samples, the sharpness ratio and the highest sensitivity factor of the focus evaluation function proposed in this paper can reach 0.06341 and 0.95, respectively. It can meet the accurate and sensitive autofocus of microscopic images of color microsporidia samples under complex backgrounds.

A Novel Approach to Quantifying the Failure Modes of Concrete-Epoxy Interface

The failure or debonding of CEIs (Concrete-Epoxy Interfaces) in Fiber-Reinforced Polymer concrete (FRP) systems occurs in one or a combination of three modes: CC (Cohesive failure in Concrete), CE (Cohesive failure in Epoxy), and IF (Interfacial Failure). These failure modes are usually identified, and their relationships are established by human intuition, which is prone to subjectivity. This study proposes a novel method based on image processing techniques to analyze CEI fracture surfaces and evaluate their failure modes. The failure modes of CEI fracture surfaces of specimens from a 3PB (Three-Point Bending) experiment were assessed using an HVS, CIE L*a*b*, YCbCr, or RGB color space image segmentation-based image processing technique on the preprocessed images of the CEI failure sides. A manual approach was adopted to validate the accuracy of the proposed method. Comparing the failure mode (CE) obtained using the manual and the proposed methodology, an RMSE (Root Means Square Error) of 0.19, 0.10, 0.23, and 0.26 was obtained for HVS, CIE L*a*b*, YCbCr, or RGB color space, respectively. The epoxy area selected with CIE L*a*b* color space produced the most accurate evaluation of the failure modes. This study provides an accurate method of quantifying the failure modes of CEI fracture surfaces. The methodology proposed in this study is recommended for forensic investigations to understand better the possible causes of failure in externally bounded fiber-reinforced polymers.

MACGRAN-IJ: AN EFFICIENT METHOD TO ANALYZE DIMENSIONS AND COLOR OF WHEAT GRAINS

The dimensions, shape, and color of wheat grain are important in plant breeding, although their manual measurement is difficult and time-consuming. While it is true that digital image analysis (DIA) with specific software has made it easier, some are semiautomatic, exclude color, and require the digitization of individual grains. The goal of this study was to compare the precision, accuracy, and efficiency of MacGran-IJ versus SmartGrain, GrainScan, and manual caliper measurement. The morphological characteristics of durum wheat (Triticum durum Desf.) and bread wheat (Triticum aestivum L.) grains were measured using DIA with MacGran-IJ, including color (in RGB and CIELab color spaces), size (mm2), lateral length (LLG, mm), ventral length (VLG, mm), lateral (LWG, mm) and ventral (VWG, mm) width, perimeter (mm), and circularity. Length, LWG, and VWG were measured with a digital caliper. The time (s) taken in each method was recorded. Size, LLG, VLG, and VWG were the same between methods for both species, but the LWG measurement obtained with vernier showed differences between the three programs (p ≤ 0.01), as well as low accuracy and precision. VWG obtained manually had R2 values of 0.92, 0.91, and 0.89 (p ≤ 0.01) for MacGran-IJ, SmartGrain, and GrainScan, respectively. The ventral and lateral color red of wheat grain differed between MacGran-IJ and GrainScan; the lateral part of the bread wheat grain showed differences for red, green, and blue (p ≤ 0.05). DIA in CIELab color required 11.57 s, and in RGB it needed 7.25 s (p ≤ 0.01). Manual measurement of 50 wheat grains required 1528.07 s, whereas SmartGrain took 101.84 s, MacGran-IJ 45.4 s, and GrainScan 54.11 s (H = 36.59, p ≤ 0.01). MacGran-IJ is an automated, simple, and efficient method for accurately measuring the size, length, and width of wheat grains using digitized images

Underwater Image Enhancement Based on the Improved Algorithm of Dark Channel

Enhancing underwater images presents a challenging problem owing to the influence of ocean currents, the refraction, absorption and scattering of light by suspended particles, and the weak illumination intensity. Recently, different methods have relied on the underwater image formation model and deep learning techniques to restore underwater images. However, they tend to degrade the underwater images, interfere with background clutter and miss the boundary details of blue regions. An improved image fusion and enhancement algorithm based on a prior dark channel is proposed in this paper based on graph theory. Image edge feature sharpening, and dark detail enhancement by homomorphism filtering in CIELab colour space are realized. In the RGB colour space, the multi-scale retinal with colour restoration (MSRCR) algorithm is used to improve colour deviation and enhance colour saturation. The contrast-limited adaptive histogram equalization (CLAHE) algorithm defogs and enhances image contrast. Finally, according to the dark channel images of the three processing results, the final enhanced image is obtained by the linear fusion of multiple images and channels. Experimental results demonstrate the effectiveness and practicality of the proposed method on various data sets.

Fabricating a photochromic benzonitrile Schiff base into a low-cost reusable paper-based wearable sensor for naked-eye dosimetry of UV radiations

We report in this study a photochromic benzonitrile Schiff base, (E)-4-((2-hydroxy-4-methoxybenzylidene)amino)benzonitrile (HMBAB). The molecular design, synthesis, aggregation-induced emission (AIE) as well as the quantum chemical calculations were outlined. In particular, HMBAB would undergo a reversible tautomerism in response to UV exposure, exhibiting remarkable changes in both absorption and emission: the compound shows yellow color and green-yellow luminescence; after UV exposure, the changes into orange-red while the luminescence is dramatically quenched, accompanied by a large bathochromic-shift. In addition, the photochromic state can be fully recovered via thermal treatment. Such reversible dual-channel photochromism was investigated using UV–vis reflectance spectroscopy and colorimeter, wherein a gradient change with time and a high fatigue resistance in cycle use was recorded. The photochromism is quantified by well-established RGB and Lab color space, in which the color change can be accurately analyzed by the chromatic aberration (ΔE*Lab). Sensitivity test gives a two-stage linear relation between ΔE*Lab and UV intensity, by which a limit of detection (LOD) as low as 67 μW/cm2 is obtained. HMBAB was further fabricated into a paper-based wearable sensor, capable of being integrated into a chest card or a bracelet. It exhibits various degrees of color change in different sunlight environments, which can be readily observed by naked eyes, providing an early warning for high-dose UV radiations.

Unburnt carbon estimation through flame image and gauss process regression

ABSTRACT The presence of unburned carbon in coal-burning systems undoubtedly causes a loss in the amount of energy that can be obtained from the system, and also reveals an inadequacy in terms of the usability of the ashes. The expensiveness of existing unburned carbon prediction methods is one of the reasons why these technologies cannot be used. This situation requires working on alternative non-combustible carbon technologies. In this paper, a new approach is presented for estimating unburned carbon in a small-scale coal burner system using the Gaussian regression model and CCD camera-acquired flame image. The proposed approach evaluates brightness, fluctuation amplitude, area, and radiation signal properties of the flame image. The proposed non-combustible carbon estimation technique does not require prior knowledge of CCD camera features. In the feature acquisition phase, results were obtained for each natural component of the flame image in RGB colour space separately, in pairs, all together and for three artificial colour channels (grey image). With the proposed method, the unburned carbon estimation was obtained with an accuracy of R = 0.9664 when all colour channels of the RGB image were used together. This result shows that unburned carbon can be estimated from the instantaneous flame images obtained with the CCD camera.