Red , Green And Blue Research Articles

Supramolecular colorimetric sensor array combined with machine learning for benzimidazoles fungicides discrimination and prediction

Due to their slight structural differences, the rapid identification of benzimidazole fungicides is challenging. In this study, three benzimidazole fungicides (FBZ, CBZ and TBZ) with similar structures were added to the 2C30@3Q[8] host–guest complex. The solutions changed color, suggesting that a reaction occurred. Based on this host–guest interaction, a supramolecular colorimetric sensor array was constructed by extracting the red, green and blue (RGB) color change of the host–guest complex in response to fungicides. Linear discriminant analysis (LDA) identified and distinguished the benzimidazole fungicides with similar structures. The supramolecular colorimetric sensor array was in the 1–20 μM range. The Euclidean distance of the array showed excellent linear correlation with the fungicide concentration, with a 10−7 mol/L detection limit and a signal-to-noise ratio of 3. The colorimetric sensor array clearly distinguished between the binary and ternary fungicide mixes. The sensor array was integrated with machine learning to predict TBZ concentrations in river water. The applicability of the supramolecular colorimetry sensor array was verified by distinguishing and identifying three benzimidazole fungicides in river water and fruit skin.

Application of the high-resolution layer-stripping constrained seismic inversion method in thin reservoirs: a case study of Triassic reservoir prediction in Lunnan, Tarim Basin, NW China

The Lunnan Oilfield’s Triassic reservoir is a braided river delta deposition, exhibiting notable characteristics such as rapid lateral sand body changes, thin reservoir thickness, and deep reservoir burial. However, the conventional seismic inversion technique used in this geological context is hindered by the low accuracy of the low-frequency model, resulting in inversion outcomes with limited vertical resolution. Consequently, accurately characterizing the reservoir distribution becomes challenging, posing a significant obstacle for the subsequent exploration and development. In this study, we introduce an enhanced seismic inversion approach using high-resolution layer-stripping constraints. The process begins with the creation of a fine-grained layer sequence grid on wells through Integrated Prediction Error Filter Analysis (INPEFA) technology. Subsequently, this grid aids in interpreting high-resolution sequence layers on the seismic volume, obtained through a frequency division RGB (Red, Green, and Blue) fusion technique. Finally, a novel nonlinear stochastic inversion method is formulated, utilizing the high-resolution sequence to refine both the initial model and inverted results. This innovative seismic inversion technique significantly enhances accuracy, particularly in predicting thin reservoirs, approximately 3 meters thick. The application of this method in a case study on Triassic reservoir prediction in Lunnan, Tarim Basin, NW China, demonstrates its promising future applications.

Detection of forest disturbance across California using deep-learning on PlanetScope imagery

California forests have recently experienced record breaking wildfires and tree mortality from droughts, However, there is inadequate monitoring, and limited data to inform policies and management strategies across the state. Although forest surveys and satellite observations of forest cover changes exist at medium to coarse resolutions (30–500 m) annually, they remain less effective in mapping small disturbances of forest patches (<5 m) occurring multiple times a year. We introduce a novel method of tracking California forest cover using a supervised U-Net deep learning architecture and PlanetScope’s Visual dataset which provides 3-band RGB (Red, Green, and Blue) mosaicked imagery. We created labels of forest and non-forest to train the U-Net model to map tree cover based on a semi-unsupervised classification method. We then detected changes of tree cover and disturbance with the U-Net model, achieving an overall accuracy of 98.97% over training data set, and 95.5% over an independent validation dataset, obtaining a precision of 82%, and a recall of 74%. With the predicted tree cover mask, we created wall to wall monthly tree cover maps over California at 4.77 m resolution for 2020, 2021, and 2022. These maps were then aggregated in a post-processing step to develop annual maps of disturbance, while accounting for the time of disturbance and other confounding factors such as topography, phenological and snow cover variability. We compared our high-resolution disturbance maps with wildfire GIS survey data from CALFIRE, and satellite-based forest cover changes and achieved an F-1 score of 54% and 88% respectively. The results suggest that high-resolution maps capture variability of forest disturbance and fire that wildfire surveys and medium resolution satellite products cannot. From 2020 to 2021, California maintained 30,923.5 sq km of forest while 5,994.9 sq km were disturbed. The highest observed forest loss rate was located at the Sierra Nevada mountains at 21.4% of the forested area being disturbed between 2020 and 2021. Our findings highlight the strong potential of deep learning and high-resolution RGB optical imagery for mapping complex forest ecosystems and their changes across California, as well as the application of these techniques on a national to global scale.

Retrospective Study Regarding the Correlation between Dental Anxiety and Color Preferences in Children with Severe Early Childhood Caries.

Severe early childhood caries (S-ECC) is recognized as a significant chronic disease which affects the quality of life starting at very young ages and has a very rapid evolution towards pulp complication and loss of dental tissue. Children with a high caries index DMFT are more likely to develop high levels of dental anxiety, which will influence the degree of cooperation during dental procedures. Emotions play an important role in the psychosomatic development of children, and all the factors that contribute to the modeling of these emotional states must be known and taken into consideration. The aim of this study was to assess the association between dental anxiety in children with S-ECC and the color preferences for the components of the dental environment to reduce the levels of dental anxiety during medical visits. For this study, 91 children between 3 and 6 years of age diagnosed with S-ECC were selected from the Pediatric Dentistry Department of UMFST from Targu Mures and from a private dental office. The level of dental anxiety was determined by measuring the pulse rate, and a questionnaire was completed to establish the color preferences for the dental office environment and the dentist's attire. For this purpose, six different colors and their variants with three shades less intensity were chosen by using RGB (Red, Green, and Blue) identification codes for each color. The results showed that there was a statistically significant difference between the age of the subjects and dental anxiety levels, but there was no significant correlation between the DMFT score and dental anxiety. Also, the results showed that there was no significant difference between girls and boys when choosing the colors preferred by them for the dental office, but when comparing the colors that represented happiness, significant statistical difference was found between the girls' and boys' groups (p = 0.0039). For all the subjects, the colors associated with happiness were light yellow and pink, while the colors associated with anxiety were red and dark blue. The data obtained showed that dental anxiety is strongly influenced by age, and an important role in inducing positive emotions is played by the dental environment if dressed in specific colors in order to reduce dental anxiety and create familiar conditions, especially for young children with S-ECC.

High-Throughput Phenotyping for the Evaluation of Agronomic Potential and Root Quality in Tropical Carrot Using RGB Sensors

The objective of this study was to verify the genetic dissimilarity and validate image phenotyping using RGB (red, green, and blue) sensors in tropical carrot germplasms. The experiment was conducted in the city of Carandaí-MG, Brazil, using 57 tropical carrot entries from Seminis and three commercial entries. The entries were evaluated agronomically and two flights with Remotely Piloted Aircraft (RPA) were conducted. Clustering was performed to validate the existence of genetic variability among the entries using an artificial neural network to produce a Kohonen’s self-organizing map. The genotype–ideotype distance index was used to verify the best entries. Genetic variability among the tropical carrot entries was evidenced by the formation of six groups. The Brightness Index (BI), Primary Colors Hue Index (HI), Overall Hue Index (HUE), Normalized Green Red Difference Index (NGRDI), Soil Color Index (SCI), and Visible Atmospherically Resistant Index (VARI), as well as the calculated areas of marketable, unmarketable, and total roots, were correlated with agronomic characters, including leaf blight severity and root yield. This indicates that tropical carrot materials can be indirectly evaluated via remote sensing. Ten entries were selected using the genotype–ideotype distance (2, 15, 16, 22, 34, 37, 39, 51, 52, and 53), confirming the superiority of the entries.

Wearable, disposable and non-enzymatic fluorescence nanosensor for monitoring sweat glucose through smartphone

The promise of non-invasive health monitoring has fuelled the development of wearable biosensors for in situ detection of biological analytes in sweat. This paper presents a new fluorescent nanosensor probe based on boric acid functionalized and heteroatom doped carbon quantum dots (CQDs) embedded in paper-based analytical devices and integrated with a hydrophilic cotton thread-based microfluidic channel for the development of a flexible, wearable, biocompatible, and biodegradable sweat sensor for real-time measurement of sweat glucose concentration via smartphone readout. The morphological, physiochemical, compositional, crystallinity, and optical properties of nanosensors were extensively investigated. CQD particle sizes were found to be widely dispersed, ranging from 2.6 to 7.1 nm, with an average diameter of 4.38 nm. A dual response via fluorescence and colorimetric change was demonstrated for on-site sweat glucose monitoring using a smartphone camera to capture images in RGB (red, green, and blue) format and analyse them simultaneously by a customized android app, with quantitative results displayed on the smartphone. The limit of detection value for in situ measurement of sweat glucose concentration was 1.40 to 2.00 μM (25.25 to 36.13 μg/dL) and the limit of quantification value was 4.67 to 6.69 μM (84.16–120.44 μg/dL) in the pH range of 4.5 to 7.5. The developed sensor's performance metrics were validated using a standard clinical technique, which indicates strong correlation between two methods with Pearson correlation coefficient values of 0.83 and 0.80 for non-diabetic and type- II diabetes patients, respectively. Besides, interference, spike, and recovery studies were carried out with recovery rates ranging from 96.5 to 105.8 %, demonstrating good repeatability and reproducibility. Furthermore, feasible fluorescence quenching processes have been explored. In addition, the disposable and biodegradable nature of the nanosensor probe was studied by throwing it into the soil in the natural environment, where it dissolves almost spontaneously after three weeks.

Establishing an astaxanthin-rich live feed strain of Pseudodiaptomus annandalei

This study aimed to establish an astaxanthin-rich strain of the calanoid copepod Pseudodiaptomus annandalei, through selective breeding based on RGB (red, green and blue) value, a parameter indicating color intensity. We evaluated the RGB value frequency distributions of the copepod populations, and selected individuals with the highest 10% and the lowest 10% RGB value over six generations. The RGB value, nauplii production, clutch interval and clutch number were assessed, and the genetic gain was calculated across generations (G0-G5). Two strains of copepods were selected and defined as dark body copepod strain (DBS) and light body copepod strain (LBS) at the end of experiment. Results revealed significantly lower RGB values (male: 121.5 ± 14.1; female: 108.8 ± 15) in the G5 DBS population compared to the G0 (male: 163.9 ± 13.1; female: 162.2 ± 14.6), with higher genetic gains of RGB values during G0 to G2. While DBS females exhibited longer clutch intervals in the G3 and G4, there was no significant difference in nauplii production between the two strains across all generations. Significantly higher astaxanthin content was found in the DBS copepods (0.04 μg/ ind.) compared to the LBS copepods (0.01 μg/ ind.) and the non-selective copepods (0.02 μg/ ind.) 20 months post selective breeding, validating the stability of the desired trait in the DBS strain. This study successfully established an astaxanthin-rich strain of P. annandalei, which provides implications for enhancing marine and brackish larviculture production.

Smartphone-based dual inverse signal MOFs fluorescence sensing for intelligent on-site visual detection of malachite green

The development of intelligent, sensitive, and visual methods for the rapid detection of veterinary drug residues is essential to ensure food quality and safety. Here, a smartphone-based dual inverse signal MOFs fluorescence sensing system was proposed for intelligent in-site visual detection of malachite green (MG). A UiO-66-NH2@RhB-dual-emission fluorescent probe was successfully synthesized in one step using a simple one-pot method. The inner filter effect (IFE) quenches the red fluorescence, while hydrogen bonding interaction enhances the blue fluorescence, enabling highly sensitive, accurate, and visual detection of MG dual inverse signals through fluorescence analysis. The probe showed great linearity over a wide range of 0.1–100 μmol/L, with a limit of detection (LOD) of 20 nmol/L. By integrating smartphone photography and RGB (red, green, and blue) analysis, accurate quantitative analysis of MG in water and actual fish samples can be achieved within 5 min. This developed platform holds great promise for the on-site detection of MG in practical applications, with the advantages of simplicity, cost-effectiveness, and rapidity. Consequently, it may open up a new pathway for on-site evaluation of food safety and environmental health.

The development of color histogram method to identify air quality index based on sky images

Air quality index measurements in Indonesia are carried out by ministry of environment and forestry (KLHK). The Ministry divides air quality levels into 5 categories, namely good, moderate, unhealthy, very unhealthy and dangerous. In this study, 3 air quality categories were used as primary research data, namely good, moderate and unhealthy because the others, never occurred in Indonesia from the time this research was conducted until its completion. This research develops the color histogram method in order to recognize the shape of an object in an image. First stage in this research is inputting the sky image into the system. Then carry out pre-processing in the form of cropping the image to obtained is only an image of sky. Next, convert the red, green and blue (RGB) colored sky image to Grayscale, then image enhancement, then noise reduction. After that is processed using development of the color histogram method. Refinement of color histogram method has yielded an impressive accuracy level of 90%, validated through the analysis of 30 sky images. The method successfully detected 27 images accurately, while three images posed detection challenges. The findings of this research is color histogram method can be used to identify objects especially air pollution from sky images.

Early stroke disease prediction with facial features using convolutional neural network model

<span>Past researcher has proposed computed tomography (CT) and magnetic resonance image (MRI) scan images as the most efficient ways to diagnose stroke disease. These methods are not only hectic and take much time but are also costly. This paper proposes a new approach to diagnosing this disease and gives a time and cost-efficient solution. We have offered a two-step solution to diagnose stroke disease in a patient using only the patient’s facial image. In the first step, we gathered a dataset of several stroke patients and normal persons. Then we applied several pre-processing operations, including red, green and blue (RGB) to grayscale conversion, scaling/ resizing, and normalization on dataset images before training them. In the second step, we trained the cropped images of their face regions and trained them using a convolutional neural network (CNN). We have successfully achieved an efficiency of 98%. The accuracy, precision, recall, and f-measure of the results were measured at 98%, 97%, 99%, and 98% respectively.</span>

Multiresonant all-dielectric metasurfaces based on high-order multipole coupling in the visible.

In many cases, optical metasurfaces are studied in the single-resonant regime. However, a multiresonant behavior can enable multiband devices with reduced footprint, and is desired for applications such as display pixels, multispectral imaging and sensing. Multiresonances are typically achieved by engineering the array lattice (e.g., to obtain several surface lattice resonances), or by adopting a unit cell hosting one (or more than one) nanostructure with some optimized geometry to support multiple resonances. Here, we present a study on how to achieve multiresonant metasurfaces in the visible spectral range by exploiting high-order multipoles in dielectric (e.g., diamond or titanium dioxide) nanostructures. We show that in a simple metasurface (for a fixed particle and lattice geometry) one can achieve triple resonance occurring nearly at RGB (red, green, and blue) wavelengths. Based on analytical and numerical analysis, we demonstrate that the physical mechanism enabling the multiresonance behavior is the lattice induced coupling (energy exchange) between high-order Mie-type multipoles moments of the metasurface's particles. We discuss the influence on the resonances of the metasurface's finite size, surrounding material, polarization, and lattice shape, and suggest control strategies to enable the optical tunability of these resonances.

ResNet incorporating the fusion data of RGB & hyperspectral images improves classification accuracy of vegetable soybean freshness

The freshness of vegetable soybean (VS) is an important indicator for quality evaluation. Currently, deep learning-based image recognition technology provides a fast, efficient, and low-cost method for analyzing the freshness of food. The RGB (red, green, and blue) image recognition technology is widely used in the study of food appearance evaluation. In addition, the hyperspectral image has outstanding performance in predicting the nutrient content of samples. However, there are few reports on the research of classification models based on the fusion data of these two sources of images. We collected RGB and hyperspectral images at four different storage times of VS. The ENVI software was adopted to extract the hyperspectral information, and the RGB images were reconstructed based on the downsampling technology. Then, the one-dimensional hyperspectral data was transformed into a two-dimensional space, which allows it to be overlaid and concatenated with the RGB image data in the channel direction, thereby generating fused data. Compared with four commonly used machine learning models, the deep learning model ResNet18 has higher classification accuracy and computational efficiency. Based on the above results, a novel classification model named ResNet-R &H, which is based on the residual networks (ResNet) structure and incorporates the fusion data of RGB and hyperspectral images, was proposed. The ResNet-R &H can achieve a testing accuracy of 97.6%, which demonstrates a significant enhancement of 4.0% and 7.2% compared to the distinct utilization of hyperspectral data and RGB data, respectively. Overall, this research is significant in providing a unique, efficient, and more accurate classification approach in evaluating the freshness of vegetable soybean. The method proposed in this study can provide a theoretical reference for classifying the freshness of fruits and vegetables to improve classification accuracy and reduce human error and variability.

Color Analysis of Merkel Cell Carcinoma: A Comparative Study with Cherry Angiomas, Hemangiomas, Basal Cell Carcinomas, and Squamous Cell Carcinomas.

Merkel cell carcinoma (MCC) is recognized as one of the most malignant skin tumors. Its rarity might explain the limited exploration of digital color studies in this area. The objective of this study was to delineate color alterations in MCCs compared to benign lesions resembling MCC, such as cherry angiomas and hemangiomas, along with other non-melanoma skin cancer lesions like basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), utilizing computer-aided digital color analysis. This was a retrospective study where clinical images of the color of the lesion and adjacent normal skin from 11 patients with primary MCC, 11 patients with cherry angiomas, 12 patients with hemangiomas, and 12 patients with BCC/SCC (totaling 46 patients) were analyzed using the RGB (red, green, and blue) and the CIE Lab color system. The Lab color system aided in estimating the Individual Typology Angle (ITA) change in the skin, and these results are documented in this study. It was demonstrated that the estimation of color components can assist in the differential diagnosis of these types of lesions because there were significant differences in color parameters between MCC and other categories of skin lesions such as hemangiomas, common skin carcinomas, and cherry hemangiomas. Significant differences in values were observed in the blue color of RGB (p = 0.003) and the b* parameter of Lab color (p < 0.0001) of MCC versus cherry angiomas. Similarly, the mean a* value of Merkel cell carcinoma (MCC) compared to basal cell carcinoma and squamous cell carcinoma showed a statistically significant difference (p < 0.0001). Larger prospective studies are warranted to further validate the clinical application of these findings.

Color Night Light Remote Sensing Images Generation Using Dual-Transformation.

Traditional night light images are black and white with a low resolution, which has largely limited their applications in areas such as high-accuracy urban electricity consumption estimation. For this reason, this study proposes a fusion algorithm based on a dual-transformation (wavelet transform and IHS (Intensity Hue Saturation) color space transform), is proposed to generate color night light remote sensing images (color-NLRSIs). In the dual-transformation, the red and green bands of Landsat multi-spectral images and "NPP-VIIRS-like" night light remote sensing images are merged. The three bands of the multi-band image are converted into independent components by the IHS modulated wavelet transformed algorithm, which represents the main effective information of the original image. With the color space transformation of the original image to the IHS color space, the components I, H, and S of Landsat multi-spectral images are obtained, and the histogram is optimally matched, and then it is combined with a two-dimensional discrete wavelet transform. Finally, it is inverted into RGB (red, green, and blue) color images. The experimental results demonstrate the following: (1) Compared with the traditional single-fusion algorithm, the dual-transformation has the best comprehensive performance effect on the spatial resolution, detail contrast, and color information before and after fusion, so the fusion image quality is the best; (2) The fused color-NLRSIs can visualize the information of the features covered by lights at night, and the resolution of the image has been improved from 500 m to 40 m, which can more accurately analyze the light of small-scale area and the ground features covered; (3) The fused color-NLRSIs are improved in terms of their MEAN (mean value), STD (standard deviation), EN (entropy), and AG (average gradient) so that the images have better advantages in terms of detail texture, spectral characteristics, and clarity of the images. In summary, the dual-transformation algorithm has the best overall performance and the highest quality of fused color-NLRSIs.

Monitoramento da qualidade ambiental de restingas no litoral do sul do Brasil utilizando imagens de alta resolução: uma ferramenta para gestão ambiental

Abstract The aim of this study was to evaluate the environmental quality of the Atlantic coast restinga, in south Brazil, using red, green and blue (RGB) drone images obtained in September of 2020 and 2021. The generated orthoimage was classified into different vegetation classes like herbaceous, shrubs and arboreal as well as other classes such as degraded and constructed areas. Classification was performed using the Random Forest algorithm, available from the Dzetsaka plugin for Quantum GIS. Of the total assessed area of restinga (289.17 ha), in 2020, 61.54% were conserved and 36.72% were degraded. In 2021 there was a decrease in conserved areas to 59.56%, and an increase in degraded areas to 38.85%. Regarding the sectors (1–8) evaluated in the two different years, sector 6 had the smallest preserved area of restinga (5.40 and 8.14 ha in 2020 and 2021, respectively), and sector 2 had the largest preservation area, with 44.07 ha in 2020 and 43.55 ha in 2021. Sectors 1,2,4, and 5 showed a reduction in conserved restinga areas (on average, 6.75%). An increase in conserved areas was observed in sectors 6 and 7 (on average, 20.4%) and in sector 8 (2%). These results show the potential of using images obtained by drone, in multi-temporal analyses of fragile areas such as restingas, helping with protection and conservation measures for these ecosystems.

A portable fluorescence detection device based on a smartphone employing carbon nanodots for Mn2+ sensing.

The measurement of fluorescence emission for quantitative analysis is typically based on a traditional spectrofluorometer, which limits an onsite detection approach. Thus, an alternative device should be developed for fulfilling this analysis outside of the laboratory. Therefore, a low-cost, portable, and low-energy consumption fluorescence reader-based smartphone device was developed. An ultraviolet light-emitting diodes (UV-LED) was used to construct the fluorescence device-based smartphone as a low-power excitation light source. The smartphone camera was used as a detector for detecting photons from the fluorescence emission process of the fluorescence probe and was connected to a digital image platform. Transparent acrylic with orange and yellow colors was employed as a filter for reducing the interference from light source intensity. The obtained digital image was converted to red, green and blue (RGB) intensity using a custom-designed smartphone application. N,S-doped carbon nanodots (N,S-CDs) were demonstrated to be a good fluorescence indicator for determining trace quantities of Mn2+ in cosmetics. The approach exhibited high selectivity and sensitivity, detecting and quantifying analytes at 1-5 μM concentrations. Furthermore, the method's detection limit of 0.5 μM reflects its capacity to detect trace amounts of a target analyte. Mn2+ in cosmetic products was successfully analyzed using this device with high accuracy comparable with the results from inductively coupled plasma-optical emission spectroscopy (ICP-OES).

Time-Series Field Phenotyping of Soybean Growth Analysis by Combining Multimodal Deep Learning and Dynamic Modeling.

The rate of soybean canopy establishment largely determines photoperiodic sensitivity, subsequently influencing yield potential. However, assessing the rate of soybean canopy development in large-scale field breeding trials is both laborious and time-consuming. High-throughput phenotyping methods based on unmanned aerial vehicle (UAV) systems can be used to monitor and quantitatively describe the development of soybean canopies for different genotypes. In this study, high-resolution and time-series raw data from field soybean populations were collected using UAVs. The RGB (red, green, and blue) and infrared images are used as inputs to construct the multimodal image segmentation model-the RGB & Infrared Feature Fusion Segmentation Network (RIFSeg-Net). Subsequently, the segment anything model was employed to extract complete individual leaves from the segmentation results obtained from RIFSeg-Net. These leaf aspect ratios facilitated the accurate categorization of soybean populations into 2 distinct varieties: oval leaf type variety and lanceolate leaf type variety. Finally, dynamic modeling was conducted to identify 5 phenotypic traits associated with the canopy development rate that differed substantially among the classified soybean varieties. The results showed that the developed multimodal image segmentation model RIFSeg-Net for extracting soybean canopy cover from UAV images outperformed traditional deep learning image segmentation networks (precision = 0.94, recall = 0.93, F1-score = 0.93). The proposed method has high practical value in the field of germplasm resource identification. This approach could lead to the use of a practical tool for further genotypic differentiation analysis and the selection of target genes.

Holographic method for stress distribution analysis in photoelastic materials

&lt;p&gt;An alternative method to obtain the internal stress distribution in photoelastic materials using digital holography (DH) is presented. Two orthogonally polarized holograms were used to obtain the phase maps and analyzed using the proposed approach. This method directly determines the stress distributions from the phase differences obtained in the reconstructed phase maps, unlike methods obtained by photoelasticity. Optical information, such as index of refraction, phase differences, etc., are not measured directly in traditional photoelasticity. However, this approach was validated with both the finite element method and the RGB (red, green, and blue) photoelasticity method that is traditionally used.&lt;/p&gt;

White Blood Cell Type Detection Using K-means Clustering and Multicolor Spaces

The white blood cell (WBC) plays an instrumental role in protecting the human body from different infectious diseases and unknown biological invaders. Their count and cellular morphology drastically change when the body suffers from any such disease or abnormal conditions. This paper demonstrates the detection of five types of WBC present in human blood smear images. Several authors proposed WBC detection using only one color space. But this paper addresses WBC-type detection using four popular color spaces – RGB (red, green, and blue), HSV (hue, saturation, and intensity), YCbCr (luminance, chroma blue, and chroma red), and L*a*b* (luminosity, chromaticity layer “a*”, and chromaticity layer “b*”). The proposed methodology involves color thresholding, K-means clustering, nuclear region analysis, and the implementation of a feedforward neural network. The unsupervised machine learning algorithm, K-means clustering is used to segment nuclei from the blood smear images. The detection of WBC-type using four color spaces is compared in terms of accuracy, sensitivity, specificity, and positive predictive value. It is observed that HSV-based WBC-type detection methodology outperforms methodologies based on RGB, YCbCr, and L*a*b* color spaces. The same methodology mentioned above is then compared with the works proposed by other authors.

PCNN orchard heterologous image fusion with semantic segmentation of significance regions

The apple fruits captured from red green and blue (RGB) color camera cannot be accurately identified and localized under natural scenes of orchards due to lighting and shading. We propose a pulse coupled neural network (PCNN) orchard heterogeneous image fusion model for semantic segmentation of saliency regions. The purpose of the model is to improve the accuracy of image segmentation and the quality of heterogeneous source image fusion in complex orchard scenes. The model fuses the time of flight (ToF) and RGB images acquired from orchard scenes. This model consists of an orchard image semantic segmentation module, a parameter optimization module, and a dual PCNN image fusion module. Image semantic segmentation module extracts the significant regions of fruit targets in orchard images. And then, in parameter optimization module, we introduce tent chaos and ranking strategies into human mental search algorithm to optimize the parameters of PCNN model. Finally, we complete the fusion through a dual PCNN module. Six fusion algorithms were used to evaluate the fusion quality of public and self-built datasets. The results showed that the chaotic hierarchical mental search algorithm could better solve the problem of difficult-to-determine PCNN parameters. The improved DeeplabV3 + could also segment clearer and more complete apple regions. Compared with other six fusion algorithms, the fusion experimental results show that the fused images with clearer targets and more prominent textures could be obtained in the proposed model. The proposed model reduces the influence of light and other disturbing factors in fruit recognition. And the fused image contains rich and accurate image information, which is more in line with the perception habit of human eyes.