Optimal Color Space Research Articles

Forest Fire Smoke Detection Based on Multiple Color Spaces Deep Feature Fusion

The drastic increase of forest fire occurrence, which in recent years has posed severe threat and damage worldwide to the natural environment and human society, necessitates smoke detection of the early forest fire. First, a semantic segmentation method based on multiple color spaces feature fusion is put forward for forest fire smoke detection. Considering that smoke images in different color spaces may contain varied and distinctive smoke features which are beneficial for improving the detection ability of a model, the proposed model integrates the function of multi-scale and multi-type self-adaptive weighted feature fusion with attention augmentation to extract the enriched and complementary fused features of smoke, utilizing smoke images from multi-color spaces as inputs. Second, the model is trained and evaluated on part of the FIgLib dataset containing high-quality smoke images from watchtowers in the forests, incorporating various smoke types and complex background conditions, with a satisfactory smoke segmentation result for forest fire detection. Finally, the optimal color space combination and the fusion strategy for the model is determined through elaborate and extensive experiments with a superior segmentation result of 86.14 IoU of smoke obtained.

The monitoring of burning buildings with convolutional neural network

Artificial intelligence is constantly expanding. This is used in many domains, from agriculture to the medical field. Lately, the focus has been on image-based learning (deep learning) because it has greater applicability in reality. An example is the identification of buildings that burn in real-time, the purpose being the saving as many lives as possible by the firefighters. This paper aims to identify the optimal color space for the identification of fire in images. To achieve this the images were selected from two databases taken from the Kaggle platform, and the images were processed with six color spaces: RGB, YCbCr, HSV, HLS, L*a*b, and L*u*v. In this form the images fed convolutional neural networks (CNNs). After that, the models were trained on six datasets, a dataset for each color space, and after compiling of CNNs, a testing set for the prediction model was proposed. The results of the model were analyzed and interpreted according to accuracy and loss function and the space YCbCr identified the fire from the images with an accuracy of 100% and loss function of 4.02*10-05.

The Optimal Color Space for Realistic Color Reproduction in Virtual Reality Content Design

In the emerging era of the Metaverse in which virtual reality (VR) is used for various purposes such as product demonstration, marketing, and online commerce, it becomes essential to reproduce colors accurately not only for gaming but also for brand recognition and product representation. In this regard, this study investigated the optimal color space to minimize the difference between the intended colors for the VR device and the colors selected on the designers’ monitor during the development process. To this end, this study conducted measurements and provided technical demonstrations to highlight the color differences between three different color spaces of sRGB, AdobeRGB, and DCI-P3. Through this approach, we discovered that designing the VR content using the DCI-P3 color gamut yields the most ideal results currently available.

Application of Multiple-Optimization Filtering Algorithm in Remote Sensing Image Denoising.

Denoising remote sensing images is crucial in the application and research of remote sensing imagery. Noise in remote sensing images originates from sensor characteristics, signal transmission, and environmental conditions, among which Gaussian noise is the most common type. In this paper, we proposed a multiple-optimization bilateral filtering (MOBF) algorithm based on edge detection and differential evolution (DE) methods. The proposed algorithm optimizes the spatial domain filtering kernel and the spatial domain Gaussian kernel by using the standard deviation and width of the edge response. By employing the DE algorithm, the individuals in the population based on the standard deviation of the gray value domain are subjected to iterative mutation, crossover, and selection operations to refine the latent solution vectors and determine the optimal color space for optimizing the standard deviation of the pixel range domain kernel. As a result, the MOBF algorithm, which does not require any parameter input, is realized. To verify the feasibility and effectiveness of the proposed algorithm, denoising experiments were conducted on remote sensing images by using evaluation metrics such as the mean squared error, peak signal-to-noise ratio, and structural similarity index. The experimental results revealed that the MOBF algorithm outperforms traditional algorithms for all three evaluation metrics.

Color Classification Under Complex Background via Genetic Algorithm-Based Color Difference Histogram

Color classification of polycrystalline silicon solar cells is really challenging for performing the task of production quality control during the manufacturing due to the non-Gaussian color distribution and random texture background. The motivation of this work is to present a robust color classification technique by designing a novel tiny color difference feature descriptor. Thus, a genetic algorithm based color difference histograms (GACDH) is proposed. First, the optimal color space of color difference histogram (CDH) to represent tiny color changes is designed. It counts the perceptually uniform color difference in a small local neighborhood in the L*a*b* color space, which reduces the false classification due to small color variations and illumination variation. Second, the genetic algorithm based color quantization for CDH is proposed to select the optimal quantization bins in the L* component, then we make some comparative experiments in a* and b* color components to select optimal quantization bins. The optimization of feature dimension not only reduces the large dimensionality of histogram bins in the computation but also improves the following classification performance. Finally, the proposed algorithm is validated with color dataset of solar cells with distance measure method. Some experimental results and analysis show that the overall performance of the proposed method achieves 98.6% and outperforms other techniques available in the literature in terms of weak discriminative color difference classification.

Comparative study on the effect of color spaces and color formats on heart rate measurement using the imaging photoplethysmography (IPPG) method.

BACKGROUND: The imaging photoplethysmography (IPPG) technology has been demonstrated to be an effective method for heart rate (HR) monitoring. However, some interference caused by the ambient illumination variation and facial motion severely influences the accuracy of the HR measurement. Some color spaces and color formats are assumed to reduce the interference, and enhance the accuracy of HR estimation.OBJECTIVE: The aim is to identify the optimal color space and format for IPPG based HR measurement.METHODS: Six color spaces and 3 color formats are compared in this study, based on an IPPG based HR measurement system. 424 pieces of videos captured by the system are used for the selection of the optimal color channel and color space; while 10 pieces of videos are for the identification of the optimal color format. RESULTS: The results shows that the green channel of RGB space is the optimal color channel, and RGB is the optimal color space, in respect of the mean squared error of HR estimation. BayerBG 8bit is found to be the optimal color format for video recording, which can significantly reduce the HR estimation error.CONCLUSIONS: BayerBG 8bit color format for video recording, and RGB color space for video analysis is suggested for the IPPG based HR measurement system. The suitable configuration of color space and format could enhance the accuracy of HR measurement.

CU-Net: A New Improved Multi-Input Color U-Net Model for Skin Lesion Semantic Segmentation

Melanoma is considered one of the most dangerous skin cancer diseases that threaten human health and life. Early diagnosis of melanoma is a big challenge, especially with the presence of color variations across similar lesion types. Automatic skin lesion segmentation is an essential step to build a successful skin disease classification system. Recent deep learning architectures significantly improve the skin lesion segmentation results. Especially, U-Net deep convolutional neural network (CNN) is considered one of the state-of-the-art models with promising performance. Most deep CNNs and particularly U-Net model utilize a single input RGB color image for skin lesion semantic segmentation. However, RGB color space is not usually the best choice to represent the invariant characteristics of skin lesion chromatic information. The selection of the optimal color space significantly affects the performance of segmentation results. In this paper, three novel variants of U-Net model with single, dual, and triple inputs, namely, Single Input Color U-Net (SICU-Net), Dual Input Color U-Net (DICU-Net) and Triple Input Color U-Net (TICU-Net) are proposed. The structure of SICU-Net, DICU-Net, and TICU-Net contains single, dual, and triple encoder sub-networks connected with only a single decoder path. Each encoder sub-network is fed with different color space of the input image. A channel-wise attention module is utilized to fuse the contribution of the learned feature maps from each encoder sub-network which is fed to the decoder sub-network to generate segmented image map. Moreover, a composite loss function is designed to improve the performance of the proposed CU-Net models. Three public benchmark datasets, namely, International Skin Imaging Collaboration (ISIC 2017, ISIC 2018) and PH2 datasets, are utilized to evaluate the performance of the proposed models. Experimental results reveal that the proposed models significantly improve the performance of the original U-Net model and achieve comparable performance with other state-of-the-art methods.

Enhanced Unsupervised Change Detector for Industrial Surveillance Systems

Detecting an intruder that is trespassing a prohibited area is a critical task of intelligent surveillance systems. This task requires a change detector to segment an intruder (foreground object) from the background. The task suffers the inherent drawbacks of change detectors due to the dual-camera sensor (color/IR), illumination changes, night time, static, and camouflaged foreground objects. This article proposes an enhanced unsupervised change detector to compensate for the aforementioned challenges for industrial sterile zone monitoring. The camera switch detection based on skewness patterns detects a switch between the dual-camera sensors (color/IR). The optimal color space selection based on the mean squared error will select tolerant color space (RGB/YCbCr) to illumination changes for modeling the background. In addition, the IR camera frames are contrast-enhanced to tackle the camouflaged intruders during the night. The incoming frames are split into respective channels before modeling the background. The background is modeled by Gaussian mixture models. The adaptive background model update scheme is proposed to tackle the various challenges posed by environment and object such as a static foreground object. The comparison is performed on three databases with top-ranked unsupervised change detection algorithms.

A Convolutional Neural Network Based Disease Diagnosis in Wireless Capsule Endoscopy Images

In wireless capsule endoscopy (WCE), a swallow-able miniature optical endoscope is used to transmit color images of the gastrointestinal tract. However, the number of images transmitted is large, taking a significant amount of the medical expert’s time to review the scan. In this research, we propose a technique to automate the abnormality detection in WCE images. We split the image into several patches and extract features pertaining to each block using a Convolutional neural network (CNN) to increase their generality while overcoming the drawbacks of manually crafted features. We intend to exploit the importance of color information for the task. Experiments are performed to determine the optimal color space components for feature extraction and classifier design. We obtained an area under receiver-operating-characteristic (ROC) curve of approximately 0.8 on a dataset containing multiple abnormalities.

Unsupervised segmentation of greenhouse plant images based on modified Latent Dirichlet Allocation.

Agricultural greenhouse plant images with complicated scenes are difficult to precisely manually label. The appearance of leaf disease spots and mosses increases the difficulty in plant segmentation. Considering these problems, this paper proposed a statistical image segmentation algorithm MSBS-LDA (Mean-shift Bandwidths Searching Latent Dirichlet Allocation), which can perform unsupervised segmentation of greenhouse plants. The main idea of the algorithm is to take advantage of the language model LDA (Latent Dirichlet Allocation) to deal with image segmentation based on the design of spatial documents. The maximum points of probability density function in image space are mapped as documents and Mean-shift is utilized to fulfill the word-document assignment. The proportion of the first major word in word frequency statistics determines the coordinate space bandwidth, and the spatial LDA segmentation procedure iteratively searches for optimal color space bandwidth in the light of the LUV distances between classes. In view of the fruits in plant segmentation result and the ever-changing illumination condition in greenhouses, an improved leaf segmentation method based on watershed is proposed to further segment the leaves. Experiment results show that the proposed methods can segment greenhouse plants and leaves in an unsupervised way and obtain a high segmentation accuracy together with an effective extraction of the fruit part.

Colorimetric analysis of saliva–alcohol test strips by smartphone-based instruments using machine-learning algorithms

We report a smartphone-based colorimetric analysis of saliva–alcohol concentrations, utilizing optimal color space and machine-learning algorithms. Commercial saliva–alcohol kits are used as a model experiment, utilizing a custom-built optical attachment for the smartphone to obtain consistent imaging of the alcohol strips. The color of the strips varies with the alcohol concentration, and the smartphone camera captures the color produced on the test strip. To make a suitable library for each alcohol concentration, statistical methods were tested to maximize between-scatter and minimize within-scatter for each concentration. Results of three different classification methods (LDA, SVM, and ANN) and four-color spaces (RGB, HSV, YUV, and Lab) were evaluated with various machine-learning data sets and five different smartphone models. Cross-validation results were used to assess the statistical performance, such as positive (PPV) and negative (NPV) predictive values. An Android app developed and provided average classification rates of 100% and 80% for the standard and enhanced concentrations, respectively.

Optimal color space selection method for plant/soil segmentation in agriculture

Color analysis techniques in agriculture should be able to deal with non-trivial capture conditions such as shadows, noise, pixel saturation, low lighting, different varieties of crops and intrinsic parameters of the cameras. Previous studies have shown the importance of selecting the optimum color space for each application domain. This paper presents a new probabilistic approach to color processing capable not only to create optimum color models for the plant/soil segmentation, but also to select the most adequate color space for each problem. The system evaluates all the possible alternatives, producing color models in the optimum space and channels. Thereby, the dependences on the kind of crop, camera and capture conditions are avoided, since the method is adapted to the training conditions. The basis of the proposal is the use of non-parametric models for the probability density functions of plant/soil colors. The proposed method has been implemented and validated in a new software tool, called ACPS (Automatic Classification of Plants and Soil), thus proving its practical feasibility. The final purpose of this system is the analysis of the vegetal ground cover, in order to obtain the PGC (percentage of green cover) parameter. The ACPS software has been developed to be used by professionals, researchers, technicians and anyone working in the agricultural area. Furthermore, the models created can be exported to a defined file format which can be used in applications in the cloud, mobile devices and compact controllers that are currently being developed.

Dots Detection in HER2 FISH Images Based on Alternative Color Spaces

This article presents an algorithm for detection of HER2 gene and chromosome centromere - CEN17 signals in FISH images. FISH is a popular fluorescence staining method which allows the evaluation the degree of HER2 gene amplification on breast cancer tissues. The FISH test allows the choice of an appropriate treatment. To ensure the best discrimination of the spots from the non-spots elements (i.e. a stroma) the algorithm was based on the color spaces transformation. The main point of this algorithm is an automatic red and green spots detection using transformations into different color spaces. Quality-identification tests were performed by using one-class SVM. The selection of an optimal color space for identification of the spots was completed using automatic Fisher feature selection. The results of the experiments are promising and show good effect of color transformation application on genes recognition system. Detailed results are presented.

Moving Object Detection for Video Surveillance using Different Color Spaces

In many vision based application identifying moving objects is important and critical task. For different computer vision application Background subtraction is fast way to detect moving object. Background subtraction separates the foreground from background. However, during background subtraction pixels belonging to shadow are misclassified as foreground object. Moving cast shadow associated with moving object also gets detected making it challenge for video surveillance. Now days many methods are available for background subtraction. The core of background subtraction is background modeling. Gaussian Mixture model is good balance between accuracy and complexity. However, it is difficult to determine the optimal color space in which to remove shadow. In this paper, we study the features of moving object and shadow in different color spaces to solve the problem.

Investigation of Optimal Segmentation Color Space of Bayer True Color Images with Multi-Objective Optimization Methods

For the selection of the optimal segmentation space of Bayer true color unmanned aerial vehicle image, this paper introduces multi-objectives constraints optimization to solve the inconsistency of multiple indicators. First, the Bayer color images were converted to YIQ(Luninance, Inphase, Quadrature), YCbCr(Luninance, Blue-difference, Red-difference), I1I2I3 (Three linear transformed color-opponent dimensions), HSI(Hue, Saturation, Intensity), Nrgb(Normalized Red, Green, Blue) and CIE(L*a*b*) (Comission Internationale de l′Eclairage, L*a*b* for Lightness and two color-opponent dimensions)color space, then the transformed images were segmented with multi-resolution segmentation method. By introducing the multi-objective constraint function, three parameters such as the topology index, geometric index and spectral area matching index were synthetically considered to determine the optimal segmentation scale. Based on that, the multi-objective constraint function was built to comprehensively analyze the result of segmentation, so as to find out the optimal color space for a certain type of building. And then the global optimum color space appropriate for all kinds of buildings can be gained through the comprehensive analysis of the F value of different types of buildings. Finally a series of images of different acquisition conditions and ground features were selected to conduct the test. The result shows that the optimal segmentation color spaces of different types of buildings vary a little. For cottage the I1I2I3 space can get the excellent object areas that reflect the real edge of the ground features, while the YCbCr space has some advantages on the segmentation of tile-building. Overall, only I1I2I3 color space has better integrated segmentation result for all buildings, and it is considered to be the best color space suitable for segmentation.

Color model and method for video fire flame and smoke detection using Fisher linear discriminant

Video fire detection is playing an increasingly important role in our life. But recent research is often based on a traditional RGB color model used to analyze the flame, which may be not the optimal color space for fire recognition. It is worse when we research smoke simply using gray images instead of color ones. We clarify the importance of color information for fire detection. We present a fire discriminant color (FDC) model for flame or smoke recognition based on color images. The FDC models aim to unify fire color image representation and fire recognition task into one framework. With the definition of between-class scatter matrices and within-class scatter matrices of Fisher linear discriminant, the proposed models seek to obtain one color-space-transform matrix and a discriminate projection basis vector by maximizing the ratio of these two scatter matrices. First, an iterative basic algorithm is designed to get one-component color space transformed from RGB. Then, a general algorithm is extended to generate three-component color space for further improvement. Moreover, we propose a method for video fire detection based on the models using the kNN classifier. To evaluate the recognition performance, we create a database including flame, smoke, and nonfire images for training and testing. The test experiments show that the proposed model achieves a flame verification rate receiver operating characteristic (ROC I) of 97.5% at a false alarm rate (FAR) of 1.06% and a smoke verification rate (ROC II) of 91.5% at a FAR of 1.2%, and lots of fire video experiments demonstrate that our method reaches a high accuracy for fire recognition.

Determination of the Optimal Color Space from Eight Types of Color Spaces for Distinguishing Small Retinal Hemorrhages from Dust Artifacts

To determine the optimal color space from eight types of color spaces for distinguishing small retinal hemorrhages from dust artifacts in cases of early diabetic retinopathy. We constructed an experimental device, which comprised an illumination optical system and a photographic optical system separated by a mirror having a hole. This device included a canon EOS 50D camera, an EF 50 mm f/1.8–2 camera lens, a Speedlite 270EX flash, an object lens, four double-convex lenses, three aperture stops, and six artificial eyes. The hemispherical eye ground was made of polythene terephthalate, which was painted with six matt color sprays: red, coffee, ocher, yellow, ivory, and orange. Five fragments of house dust on the object lens and the two lenses were photographed under each artificial eye. The RGB color space, measured by Paint Shop Pro from pictures, was changed into seven types of color spaces: XYZ, CMY, HSL, HSV, HSI, L*a*b*, and L*u*v*. The L*u*v* color space was the optimal one as it demonstrated the highest sensitivity and the best reproducibility. This result demonstrated that this color space could distinguish small hemorrhages from dust artifacts. Next, we analyzed the L*u*v* color space and compared the following three types of house dust positions: “on an object lens,” “on a photographic optical system,” and “on an illumination optical system.” The house dust position “on an object lens” had the highest sensitivity and the best reproducibility. However, the positions “on a photographic optical system” and “on an illumination optical system” had high sensitivity and good reproducibility only under certain conditions. In addition, no differences were found among the six types of fundus colors.

A Systematic Method Development Strategy for Quantitative Color Measurement in Drug Substances, Starting Materials, and Synthetic Intermediates

The color of active pharmaceutical ingredients (APIs) can be a critical quality attribute for pharmaceutical products. Color variation can be indicative of contaminants, chemical impurities, solid-state form impurities, or degradation products. The color of the pharmaceutical materials is typically specified and determined using visual appearance testing. To avoid the inherent subjectivity of visual appearance testing, to understand the link between the color and the process parameters, and to facilitate quality agreements between customers and vendors of chemical starting materials, quantitative color measurements utilizing visible spectroscopic methods are increasingly needed. In this work, a systematic method development strategy (MDS) is described to assist with the development of robust and rugged quantitative color measurement methods based on a science- and risk-based approach aligned with quality-by-design principles. The MDS is illustrated using typical scenarios encountered in method development through several examples including a method developed for 2,3-dimethyl-2H-indazol-6-amine, a starting material in the commercial synthesis of pazopanib hydrochloride API. Flowcharts and examples are presented to illuminate key decision points in the MDS process including selection of (1) solution-state versus solid-state spectroscopic method, (2) optimal color space for reporting color measurement results, and (3) appropriate method risk assessment and control to ensure successful method implementation. General guidance is also provided to facilitate the discussion for setting quantitative color specifications.

U87MG Decoded: The Genomic Sequence of a Cytogenetically Aberrant Human Cancer Cell Line

U87MG is a commonly studied grade IV glioma cell line that has been analyzed in at least 1,700 publications over four decades. In order to comprehensively characterize the genome of this cell line and to serve as a model of broad cancer genome sequencing, we have generated greater than 30× genomic sequence coverage using a novel 50-base mate paired strategy with a 1.4kb mean insert library. A total of 1,014,984,286 mate-end and 120,691,623 single-end two-base encoded reads were generated from five slides. All data were aligned using a custom designed tool called BFAST, allowing optimal color space read alignment and accurate identification of DNA variants. The aligned sequence reads and mate-pair information identified 35 interchromosomal translocation events, 1,315 structural variations (>100 bp), 191,743 small (<21 bp) insertions and deletions (indels), and 2,384,470 single nucleotide variations (SNVs). Among these observations, the known homozygous mutation in PTEN was robustly identified, and genes involved in cell adhesion were overrepresented in the mutated gene list. Data were compared to 219,187 heterozygous single nucleotide polymorphisms assayed by Illumina 1M Duo genotyping array to assess accuracy: 93.83% of all SNPs were reliably detected at filtering thresholds that yield greater than 99.99% sequence accuracy. Protein coding sequences were disrupted predominantly in this cancer cell line due to small indels, large deletions, and translocations. In total, 512 genes were homozygously mutated, including 154 by SNVs, 178 by small indels, 145 by large microdeletions, and 35 by interchromosomal translocations to reveal a highly mutated cell line genome. Of the small homozygously mutated variants, 8 SNVs and 99 indels were novel events not present in dbSNP. These data demonstrate that routine generation of broad cancer genome sequence is possible outside of genome centers. The sequence analysis of U87MG provides an unparalleled level of mutational resolution compared to any cell line to date.

Comparative color gamut analysis of xvYCC standard

In the paper, a new wide color gamut encoding standard of IEC, namely xvYCC, has been extensively studied. To judge a correct volume size of the color gamut, the xvYCC color space has been analyzed in a part of physically possible legal and impossible illegal colors. Within the legal colors, the gamut volume of the xvYCC has been computed in CIE-LAB uniform color space, and compared with theoretical possible optimal colors as all human visible colors in various color spaces of CIE-xy, xvYCC, and CIE-LAB. Because of a color gamut limitation of the optimal surface colors, a new optimal illuminant color space has been introduced for the CIE-XYZ tristimulus sensor. With this, the gamut volume of xvYCC can be better analyzed than before. In addition, the xvYCC color gamut has been compared with the volume of typical three types of CRT-, LED-, and Laser-displays.