RGB Color Space Research Articles

A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles

Owing to factors such as climate change and human activities, ecological and environmental problems of land desertification have emerged in many regions around the world, among which the problem of land desertification in northwestern China is particularly serious. To grasp the trend of land desertification and the degree of natural vegetation degradation in northwest China is a basic prerequisite for managing the fragile ecological environment there. Visible light remote sensing images taken by a UAV can monitor the vegetation cover in desert areas on a large scale and with high time efficiency. However, as there are many low shrubs in desert areas, the shadows cast by them are darker, and the traditional RGB color-space-based vegetation index is affected by the shadow texture when extracting vegetation, so it is difficult to achieve high accuracy. For this reason, this paper proposes the Lab color-space-based vegetation index L2AVI (L-a-a vegetation index) to solve this problem. The EXG (excess green index), NGRDI (normalized green-red difference index), VDVI (visible band difference vegetation index), MGRVI (modified green-red vegetation index), and RGBVI (red-green-blue vegetation index) constructed based on RGB color space were used as control experiments in the three selected study areas. The results show that, although the extraction accuracies of the vegetation indices constructed based on RGB color space all reach more than 70%, these vegetation indices are all affected by the shadow texture to different degrees, and there are many problems of misdetection and omission. However, the accuracy of the L2AVI index can reach 99.20%, 99.73%, and 99.69%, respectively, avoiding the problem of omission due to vegetation shading and having a high extraction accuracy. Therefore, the L2AVI index can provide technical support and a decision basis for the protection and control of land desertification in northwest China.

Digital Video Compression Using DCT-Based Iterated Function System (IFS)

Large video files processing involves a huge volume of data. The codec, storage systems and network needs resource utilization, so it becomes important to minimize the used memory space and time to distribute these videos over the Internet using compression techniques. Fractal image and video compression falls under the category of lossy compression. It gives best results when used for natural images.
 This paper presents an efficient method to compress an AVI (Audio Video Interleaved) file with fractal video compression(FVC). The video first is separated into a sequence of frames that are a color bitmap images, then images are transformed from RGB color space to Luminance/Chrominance components (YIQ) color space; each of these components is compressed alone with Enhanced Partition Iterated Function System (EPIFS), then fractal codes are saved.
 The classical IFS suffers from a very long encoding time that needed to find the best matching for each range block when compared with the domain image blocks. In this work, the (FVC) is enhanced by enhancing the IFS of the fractal image compression using a classification scheme based on the Discrete Cosine Transform (DCT). Experimentation is performed by considering different block sizes and jump steps to reduce number of the tested domain blocks. Results shows a significant reduction in the encoding time with good quality and high compression ratio for different video files.

Virtual cleaning of works of art using a deep generative network: spectral reflectance estimation

Generally applied to a painting for protection purposes, a varnish layer becomes yellow over time, making the painting undergo an appearance change. Upon this change, the conservators start a process that entails removing the old layer of varnish and applying a new one. As widely discussed in the literature, helping the conservators through supplying them with the probable outcome of the varnish removal can be of great value to them, aiding in the decision making process regarding varnish removal. This help can be realized through virtual cleaning, which in simple terms, refers to simulation of the cleaning process outcome. There have been different approaches devised to tackle the problem of virtual cleaning, each of which tries to develop a method that virtually cleans the artwork in a more accurate manner. Although successful in some senses, the majority of them do not possess a high level of accuracy. Prior approaches suffer from a range of shortcomings such as a reliance on identifying locations of specific colors on the painting, the need to access a large set of training data, or their lack of applicability to a wide range of paintings. In this work, we develop a Deep Generative Network to virtually clean the artwork. Using this method, only a small area of the painting needs to be physically cleaned prior to virtual cleaning. Using the cleaned and uncleaned versions of this small area, the entire unvarnished painting can be estimated. It should be noted that this estimation is performed in the spectral reflectance domain and herein it is applied to hyperspectral imagery of the work. The model is first applied to a Macbeth ColorChecker target (as a proof of concept) and then to real data of a small impressionist panel by Georges Seurat (known as ‘Haymakers at Montfermeil’ or just ‘Haymakers’). The Macbeth ColorChecker is simulated in both varnished and unvarnished forms, but in the case of the ‘Haymakers’, we have real hyperspectral imagery belonging to both states. The results of applying the Deep Generative Network show that the proposed method has done a better job virtually cleaning the artwork compared to a physics-based method in the literature. The results are presented through visualization in the sRGB color space and also by computing Euclidean distance and spectral angle (calculated in the spectral reflectance domain) between the virtually cleaned artwork and the physically cleaned one. The ultimate goal of our virtual cleaning algorithm is to enable pigment mapping and identification after virtual cleaning of the artwork in a more accurate manner, even before the process of physical cleaning.

Traditional Machine Learning-Based Classification of Cashew Kernels Using Colour Features

Cashew is one of the major commercial commodities contributing to the national economy of Tanzania as foreign revenue. And yet still the processing of cashew is run locally using manual labour for a big part. If processed well under ideal conditions, cashews kernels are expected to be white in colour. But due to various factors like prolonged roasting in the steam chambers or over-drying, some cashew kernels tend to have a slight brown colour, and these are referred to as scorched cashews. Despite sharing the same characteristics with white cashew kernels, including nutritional quality, these cashew kernels are supposed to be graded differently. In many places around the world, particularly in Tanzania, the sorting and grading process of cashew kernels is performed by hand. In international trade, cashew grading is very important and this means more effective and consistent methods need to be applied in this stage of production in order to increase the quality of the products. The objective of this study was to evaluate the use of traditional Machine Learning techniques in the classification of cashew kernels as white or scorched by using colour features. In this experiment, various colour features were extracted from the images. The extracted features include the means (μ), standard deviations (σ), and skewness (γ) of the channels in RGB and HSV colour spaces. The relevant features for this classification problem were selected by applying the wrapper approach using the Boruta Library in Python, and the irrelevant ones were removed. 5 models are studied and their efficiencies analysed. The studied models are Logistic Regression, Decision Tree, Random Forest, Support Vector Machine and K-Nearest Neighbour. The Decision Tree model recorded the least accuracy of 98.4%. The maximum accuracy of 99.8% was obtained in the Random Forest model with 100 trees. Due to simplicity in application and high accuracy, the Random Forest is recommended as the best model from this study.

Drawing deviation assessment of ship plate marking lines using progressive target extraction

In the construction of large marine structures such as ships, the precise assembly of parts is imperative for ensuring the overall structure's strength and functionality. Currently, construction workers still use marking lines to assist with ship part assembly tasks, and conventional measuring tools are used to draw marking lines throughout the whole assembly process. Unfortunately, there is not yet a method for accurately assessing marking line errors. Hence, this article proposes a method for evaluating the marking line accuracy of a hull part. A progressive sampling method is applied to extract the edge point set and marking lines. An optimised marking evaluation can be obtained while preserving the details of the as-built model. In the proposed method, geometric features are used to extract edge elements from the as-built model and then register it with its as-designed counterpart instead of using the overall data for registration. In addition, the marking lines are extracted in HSV colour space instead of RGB colour space. Using the most common panels in a ship hull structure, we evaluated the accuracy of the marking lines for each hull plate and demonstrated the effectiveness of the proposed method. The proposed method has the potential to reduce the need for rework and increase the speed of ship fabrication.

The Fast Detection of Crop Disease Leaves Based on Single-Channel Gravitational Kernel Density Clustering

Plant diseases and pests may seriously affect the yield of crops and even threaten the survival of human beings. The characteristics of plant diseases and insect pests are mainly reflected in the occurrence of lesions on crop leaves. Machine vision disease detection is of great significance for the early detection and prevention of plant diseases and insect pests. A fast detection method for lesions based on a single-channel gravitational kernel density clustering algorithm was designed to examine the complexity and ambiguity of diseased leaf images. Firstly, a polynomial was used to fit the R-channel feature histogram curve of a diseased leaf image in the RGB color space, and then the peak point and peak area of the fitted feature histogram curve were determined according to the derivative attribute. Secondly, the cluster numbers and the initial cluster center of the diseased leaf images were determined according to the peak area and peak point. Thirdly, according to the clustering center of the preliminarily determined diseased leaf images, the single-channel gravity kernel density clustering algorithm in this paper was used to achieve the rapid segmentation of the diseased leaf lesions. Finally, the experimental results showed that our method could segment the lesions quickly and accurately.

ТИНКТОРИАЛЬНЫЕ И МОРФОЛОГИЧЕСКИЕ ХАРАКТЕРИСТИКИ МИКРОБНЫХ ОБЪЕКТОВ ДЛЯ ФОРМИРОВАНИЯ ЭЛЕКТРОННОГО АТЛАСА В СИСТЕМЕ АВТОМАТИЗИРОВАННОГО АНАЛИЗА

The authors present the results of automated analysis of gram positive and gram negative cocci and bacilli (Staphylococcus aureus, Neisseria spp., Corynebacterium spp., Escherichia coli) for a database that facilitates detection of changes in normal microflora and diagnosis of disbiotic conditions of various human biotopes. Following the standard sample preparations and Gram staining, microbial smears were investigated using an automated and computerized analyzer developed by the Mintz Radio Engineering Institute in Moscow. Morphological and tinctorial analysis established significant differences in cell area, perimeter and limit. Significant differences in tinctorial properties of microbial cells make possible image research using the RGB and HSV color spaces. Automated analysis enables identification of microbial cells simultaneously by digital images of morphological and color/brightness parameters. The proposed techniques can be helpful in constructing an electronic microflora atlas of various human biotopes.

U-shape Transformer for Underwater Image Enhancement.

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we built a large scale underwater image (LSUI) dataset, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets. The dataset contains 4279 real-world underwater image groups, in which each raw image's clear reference images, semantic segmentation map and medium transmission map are paired correspondingly. We also reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task. The U-shape Transformer is integrated with a channel-wise multi-scale feature fusion transformer (CMSFFT) module and a spatial-wise global feature modeling transformer (SGFMT) module specially designed for UIE task, which reinforce the network's attention to the color channels and space areas with more serious attenuation. Meanwhile, in order to further improve the contrast and saturation, a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle. The extensive experiments on available datasets validate the state-of-the-art performance of the reported technique with more than 2dB superiority. The dataset and demo code are available on https://bianlab.github.io/.

Convolutional Neural Network Based Hand Gesture Recognition in Sophisticated Background for Humanoid Robot Control

Hand gesture recognition is a preferred way for human-robot interactions. Conventional approaches are generally based on image processing and recognition of hand poses with simple backgrounds. In this paper, we propose deep learning models, and humanoid robot integration for offline and online (real-time) recognition and control using hand gestures. One thousand and two hundred of hand images belonging to four participants are collected to construct the hand gesture database. Five class (forward, backward, right, left and stop) images in six sophisticated backgrounds with different illumination levels are obtained for four participants, and then one participant's images are kept as testing data. A lightweight Convolutional Neural Network (CNN), and transfer learning techniques using VGG16, and Mobilenetv2 are performed on this database to evaluate user independent performance of the hand gesture system. After offline training, real-time implementation is designed using a mobile phone (Wi-Fi and camera), Wi-Fi router, computer with embedded deep learning algorithms, and NAO humanoid robot. Streamed video by the mobile phone is processed and recognized using the proposed deep algorithm in the computer, and then command is transferred to robot via TCP/IP protocol. Thus, the NAO humanoid robot control using hand gesture in RGB and HSV color spaces is evaluated in sophisticated background, and the implementation of the system is presented. In our simulations, 95% and 100% accuracy rates are yielded for the lightweight CNN, and transfer learning, respectively.

Multiscale Underwater Image Enhancement in RGB and HSV Color Spaces

Multiscale Underwater Image Enhancement in RGB and HSV Color Spaces

Python programming code for stellar photometry in astrophysics teaching on a cloud computing service

Nowadays, there is various software used for both education and astronomy research. For photometry, licensed software and high-performance computer operating systems are required, which is a fund limitation for some schools in Thailand. Thus, in this article, we develop and present the Demonstration Photometry Scripts for Astrophysics Teaching (DPSAT version 1.0). The program is designed to work on cloud computing services via internet browsers to avoid hardware and operation requirement pain points. The DPSAT is programming on flexible, low-cost, on-trend language, Python, and Jupyter Notebook online editor. In advance, our new code supports the home-use image or video file format, i.e., jpg, png, or mp4. Thus, it will be more accessible for teachers and students who do not have standard astronomical instruments. The DPSAT measures the stellar light intensity from the time-series still-images or video files from a smartphone or other digital devices. The code can extract video files into sequenced still images, then transform the RGB color space images into greyscale. The light intensity signal of selected pixels is counted with a simple aperture method in time series. It shows the results, for example, the mean signal, standard variation, measured signal as light intensity versus time, and image of light sources. This will be fruitful for low-cost and easily accessible teaching of astrophysics subjects.

A Novel Method for Calibration of Digital Soil Images Captured under Irregular Lighting Conditions.

Soil color is commonly used as an indicator to classify soil and identify its properties. However, color-based soil assessments are susceptible to variations in light conditions and the subjectivity of visual evaluations. This study proposes a novel method of calibrating digital images of soil, regardless of lighting conditions, to ensure accurate identification. Two different color space models, RGB and CIELAB, were assessed in terms of their potential utility in calibrating changes to soil color in digital images. The latter system was determined to be suitable, as a result of its ability to accurately reflect illuminance and color temperature. Linear regression equations relating soil color and light conditions were developed based on digital images of four different types of soil samples, each photographed under 15 different light conditions. The proposed method can be applied to calibrate variations in the soil color obtained by digital images, thus allowing for more standardized, objective, and accurate classification and evaluation of soil based on its color.

Hue-Recognition Strategy-Based Immunoassay Using Functionalized Dendritic Silica Colloids and Gold Nanoclusters for Point-of-Care Testing of C-Reactive Proteins

Considering that hue-recognition has drawn increasing research interests for visual detection because of its high accuracy and flexible analysis modalities, the exploration of a rational hue-recognition sensing system is highly demanded. Here, we report a hue-recognition-based lateral flow immunoassay (HLFIA) by ratiometric modulation of emission from two nanoprobes, in which red-emitting ruthenium(II)-doped dendritic silica colloids and green-emitting gold nanoclusters function as reporter and reference, respectively. The HLFIA strip can generate a visually discernible green-to-orange-red color gradient alternation, enabling the naked-eye semiquantitative inspection of successive C-reactive protein (CRP) concentration and concentration intervals (0–50, 50–150, and 150–500 ng mL–1) with a visual detection limit of 10 ng mL–1. By integrating with a customized smartphone-based portable imaging device and RGB color space recognition, the precise quantification of CRP can be achieved with a linear range of 0–100 ng mL–1 and a limit of detection of 0.64 ng mL–1. The HLFIA strip is robust and validated for CRP detection in real serum, holding great promise for noninstrumental and deprofessionalized point-of-care immunoassay of biomarkers.

Innovative Models Built Based on Image Textures Using Traditional Machine Learning Algorithms for Distinguishing Different Varieties of Moroccan Date Palm Fruit (Phoenix dactylifera L.)

The aim of this study was to develop the procedure for the varietal discrimination of date palm fruit using image analysis and traditional machine learning techniques. The fruit images of ‘Mejhoul’, ‘Boufeggous’, ‘Aziza’, ‘Assiane’, and ‘Bousthammi’ date varieties, converted to individual color channels, were processed to extract the texture parameters. After performing the attribute selection, the textures were used to build models intended for the discrimination of different varieties of date palm fruit using machine learning algorithms from Functions, Bayes, Lazy, Meta, and Trees groups. Models were developed for combining image textures selected from a set of all color channels and for sets of textures selected for individual color spaces and color channels. The models, including combined textures selected from all color channels, distinguished all five varieties with an average accuracy reaching 98%, and ‘Bousthammi’ and ‘Mejhoul’ were completely correctly discriminated for the SMO (Functions) and IBk (Lazy) machine learning algorithms. By reducing the number of varieties, the correctness of the date palm fruit classification increased. The models developed for the three most different date palm fruit varieties ‘Boufeggous’, ‘Bousthammi’, and ‘Mejhoul’ revealed an average discrimination accuracy of 100% for each algorithm used (SMO, Naive Bayes (Bayes), IBk, LogitBoost (Meta), and LMT (Trees)). In the case of individual color spaces and channels, the accuracies were lower, reaching 97.3% for color space RGB and SMO and LMT algorithms for all five varieties and 99.63% for Naive Bayes and IBk for the ‘Boufeggous’, ‘Bousthammi’, and ‘Mejhoul’ date palm fruits. The results can be used in practice to develop vision systems for sorting and distinguishing the varieties of date palm fruit to authenticate the variety of the fruit intended for further processing.

Enhancement method with naturalness preservation and artifact suppression based on an improved Retinex variational model for color retinal images.

Retinal images are widely used for the diagnosis of various diseases. However, low-quality retinal images with uneven illumination, low contrast, or blurring may seriously interfere with diagnosis by ophthalmologists. This study proposes an enhancement method for low-quality retinal color images. In this paper, an improved variational Retinex model for color retinal images is first proposed and applied to each channel of the RGB color space to obtain the illuminance and reflectance layers. Subsequently, the Naka-Rushton equation is introduced to correct the illumination layer, and an enhancement operator is constructed to improve the clarity of the reflectance layer. Finally, the corrected illuminance and enhanced reflectance are recombined. Contrast-limited adaptive histogram equalization is introduced to further improve the clarity and contrast. To demonstrate the effectiveness of the proposed method, this method is tested on 527 images from four publicly available datasets and 40 local clinical images from Tianjin Eye Hospital (China). Experimental results show that the proposed method outperforms the other four enhancement methods and has obvious advantages in naturalness preservation and artifact suppression.

Optimization method for segmentation of concrete components in digital images of test sample sections

The application of optimization method of image segmentation to estimate the percentage content of concrete components is considered. Non-destructive testing methods (ultrasonic, magnetic, radiographic, image processing) are actively used to assess the condition of concrete structures and structures of long-term use. Recently, the share of studies of the mechanical properties of concrete based on the processing of images of sections of its samples has increased significantly. The relationship between the parameters obtained by digital image processing methods and the compressive strength of concrete is established on the basis of regression analysis. A method of segmentation of color images of test sample sections of concrete based on the Gaussian mixture method and level-sets model is developed. Based on the analysis of the differences in the color characteristics of the background and the object, it is concluded that they can be divided into two classes in the RGB color space. For this purpose appropriate training samples are created, which contain image pixel samples with typical features of the respective classes. The training sample consists of a set of feature vectors of image pixels. The parameters of the segmentation model have been adjusted. The experimental results of the segmentation of color images of sections of test concrete samples by the proposed method are presented. An analysis of the obtained results is carried out.

Visual retrieval of digital media image features based on active noise control

In order to improve the recall and precision of image retrieval, a visual retrieval method of digital media image features based on active noise is proposed. In this paper, Canny algorithm is used to detect the edge of the image to get the feature information of the edge of the image. The RGB color space model is used to decompose the color information of the image, and the color characteristic information of the image is obtained. Extracting image features to retain the useful information contained in the image as much as possible; In order to facilitate the visual retrieval of image features, reduce the retrieval complexity and further fuse image features, FPCA and ReliefF algorithms are used to reduce the dimensionality of image features, and the active noise control method is used to sharpen the image. After processing the results, a digital media image feature visual retrieval platform is established to realize the visual retrieval of digital media image features. Experimental results show that the proposed method has a high accuracy of over 80% and a high recall rate of 95.2%.

Evaluation of Color Anomaly Detection in Multispectral Images for Synthetic Aperture Sensing

In this article, we evaluate unsupervised anomaly detection methods in multispectral images obtained with a wavelength-independent synthetic aperture sensing technique called Airborne Optical Sectioning (AOS). With a focus on search and rescue missions that apply drones to locate missing or injured persons in dense forest and require real-time operation, we evaluate the runtime vs. quality of these methods. Furthermore, we show that color anomaly detection methods that normally operate in the visual range always benefit from an additional far infrared (thermal) channel. We also show that, even without additional thermal bands, the choice of color space in the visual range already has an impact on the detection results. Color spaces such as HSV and HLS have the potential to outperform the widely used RGB color space, especially when color anomaly detection is used for forest-like environments.

Application of Imaging and Artificial Intelligence for Quality Monitoring of Stored Black Currant (Ribes nigrum L.).

The objective of this study was to assess the influence of storage under different storage conditions on black currant quality in a non-destructive and inexpensive manner using image processing and artificial intelligence. Black currants were stored at a room temperature of 20 ± 1 °C and a temperature of 3 °C (refrigerator). The images of black currants directly after harvest and fruit stored for one and two weeks were obtained using a digital camera. Then, texture parameters were computed from the images converted to color channels R (red), G (green), B (blue), L (lightness component from black to white), a (green for negative and red for positive values), b (blue for negative and yellow for positive values), X (component with color information), Y (lightness), and Z (component with color information). Models for the classification of black currants were built using various machine learning algorithms based on selected textures for RGB, Lab, and XYZ color spaces. Models built using the IBk, multilayer perceptron, and multiclass classifier for textures from RGB color space, and the IBk algorithm for textures from Lab color space distinguished unstored black currants and samples stored in the room for one and two weeks with an average accuracy of 100%, and the kappa statistic and weighted averages of precision, recall, Matthews correlation coefficient (MCC), receiver operating characteristic (ROC) area, and precision-recall (PRC) area equal to 1.000. This indicated a very distinct change in the external structure of the fruit after the first week and more and more visible changes in quality with increasing storage time. A classification accuracy reaching 98.67% (multilayer perceptron, Lab color space) for the samples stored in the refrigerator may indicate smaller quality changes caused by storage at a low temperature. The approach combining image textures and artificial intelligence turned out to be promising to monitor the quality changes in black currants during storage.

Performance of machine learning algorithms for detecting pine wilt disease infection using visible color imagery by UAV remote sensing

Automatic detection of pine wilt disease will be useful in forest management, as it can prevent the spread of epidemics and resulting huge economic losses. Previous studies have reported the precise pine wilt disease detection by combining machine learning algorithms and hyperspectral sensors with platform of unmanned aerial vehicles (UAVs). However, these approaches require expensive hardware and advanced processing techniques, rendering them unsuitable for practical use in on-site forest management. This study deals with the simplification of the automatic detection method, which enables practical countermeasures to be taken by forest management entities. An optimal method for detecting PWD using images obtained by a simple unmanned aerial vehicle (UAV)-mounted visible color sensor is presented in this study. The method combines six major machine learning algorithms: logistic regression, linear support vector machine, support vector machine, k-nearest neighbors, random forest, and artificial neural network, with both RGB and HSV color space datasets. The performance of the six algorithms was validated using the metrics of accuracy, precision, recall, F1-scores, and area under the receiver operating characteristic curve with their 95% confidence intervals. The experimental results show that the combination of the HSV color space dataset with the artificial neural network algorithm is the best performer algorithm (accuracy: 0.995). Moreover, logistic regression, linear support vector machine, support vector machine, and artificial neural network have equally high detection accuracy in the RGB color space (accuracy: 0.990, 0.990, 0.990, 0.985, respectively), with a low possibility of overfitting. These results indicate that the generally used visible color sensors mounted on UAV, which are available at a low cost, can be used for highly accurate detection.