Red-green-blue Research Articles

I2-FaçadeNet: An Illumination-invariant Façade Recognition Network Leveraging Sparsely Gated Mixture of Multi-color Space Experts for Aerial Oblique Imagery

Façade image recognition under complex illumination conditions is crucial for various applications, including urban three-dimensional modeling and building identification. Existing methods relying solely on Red-Green-Blue (RGB) images are prone to texture ambiguity in complex illumination environments. Furthermore, façades display varying orientations and camera viewing angles, resulting in performance issues within the RGB color space. In this study, we introduce an illumination-invariant façade recognition network (I2-FaçadeNet) that leverages sparsely gated multi-color space experts for enhanced façade image recognition in challenging illumination environments. First, RGB façade images are converted into multi-color spaces to eliminate the ambiguous texture in complex illumination. Second, we train expert networks using separate channels of multi-color spaces. Finally, a sparsely gated mechanism is introduced to manage the expert networks, enabling dynamic activation of expert networks and the merging of results. Experimental evaluations leveraging both the International Society for Photogrammetry and Remote Sensing benchmark data sets and the Shenzhen data sets reveal that our proposed I2 -FaçadeNet surpasses various depths of ResNet in façade recognition under complex illumination conditions. Specifically, the classification accuracy for poorly illuminated façades in Zurich improves by nearly 8%, while the accuracy for over-illuminated areas in Shenzhen increases by approximately 3%. Moreover, ablation studies conducted on façade images with complex illumination indicate that compared to traditional RGB-based ResNet, the proposed network achieves an accuracy improvement of 3% to 4% up to 100% for overexposed images and an accuracy improvement of 3% to 10% for underexposed images.

IRFR-Net: Interactive Recursive Feature-Reshaping Network for Detecting Salient Objects in RGB-D Images.

Using attention mechanisms in saliency detection networks enables effective feature extraction, and using linear methods can promote proper feature fusion, as verified in numerous existing models. Current networks usually combine depth maps with red-green-blue (RGB) images for salient object detection (SOD). However, fully leveraging depth information complementary to RGB information by accurately highlighting salient objects deserves further study. We combine a gated attention mechanism and a linear fusion method to construct a dual-stream interactive recursive feature-reshaping network (IRFR-Net). The streams for RGB and depth data communicate through a backbone encoder to thoroughly extract complementary information. First, we design a context extraction module (CEM) to obtain low-level depth foreground information. Subsequently, the gated attention fusion module (GAFM) is applied to the RGB depth (RGB-D) information to obtain advantageous structural and spatial fusion features. Then, adjacent depth information is globally integrated to obtain complementary context features. We also introduce a weighted atrous spatial pyramid pooling (WASPP) module to extract the multiscale local information of depth features. Finally, global and local features are fused in a bottom-up scheme to effectively highlight salient objects. Comprehensive experiments on eight representative datasets demonstrate that the proposed IRFR-Net outperforms 11 state-of-the-art (SOTA) RGB-D approaches in various evaluation indicators.

Real-Time Sign Language Fingerspelling Recognition using Convolutional Neural Network

: Sign language allows mute people to communicate, problem occurs when a conversationalist fails to understand it. Despite efforts to address this problem, an effective solution is not yet found. In this work, Convolutional Neural Network (CNN) was trained on two different datasets separately- binary and Red Blue Green )RGB(, each contains 25,900 images of Nigerian Sign Language. A deep neural pre-trained module was used to detect hand gestures in the video feed which tackled the issue of complex backgrounds, also showed excellent detection in dimly lit areas. The accuracies of (98.95%, 76%) and (98.87%, 98.85%) were obtained respectively on the training and the validation sets. The real time system developed implemented both models as a single system which makes it a unique one.

Real-Time Sign Language Fingerspelling Recognition using Convolutional Neural Network

Sign Language allows mute people to communicate, problem occurs when a conversationalist fails to understand it. Despite efforts to address this problem, an effective solution is not yet found. In this work, Convolutional Neural Network was trained on two different datasets separately- Binary and Red Blue Green )RGB(, each contains 25,900 images of Nigerian Sign Language. A Deep Neural pre-trained module was used to detect hand gestures in the video feed which tackled the issue of complex backgrounds, also showed excellent detection in dimly lit areas. The accuracies of (98.95%, 76%) and (98.87%, 98.85%) were obtained respectively on the training and the validation sets. The real time system developed implemented both models as a single system which makes it a unique one.

Measurement of Fe and Mn concentrations using image processing techniques based on color intensity approach

Water quality monitoring is an important activity to create a good environment quality with clean and healthy water sources. Various monitoring methods that are generally used such as spectrometry-based instruments certainly have various limitations, such as expensive, requiring a lot of reagents, sensitive instruments, and takes quite a long to get measurement results. Due to the development of population growth and the increasing of water pollutant, water quality monitoring technology that cheap, practical, quick and accurate is important to be made. The main subject in this work was to develop a water quality monitoring method based on multiparameter image processing techniques. This method utilizes the approach of color intensity, light, and number/size/shape of particles. This work will be focus on iron (Fe) and manganese (Mn) concentration measurement by color intensity approach performed using ColorSlurp and Microsoft Excel in its RGB (Red, Green, Blue) matrices. The correlation between the parameter concentration and color intensity was obtained by transforming the RGB into greyscale intensity (GI) value. A linear response was observed in the Fe concentration range 0 to 2.4 mg L−1 with the highest R2 = 0.971, and in the Mn concentration range between 0 to 1.6 mg L−1 with the highest R2 = 0.9432. This work demonstrates that image processing techniques provide a great promise as water quality monitoring method.

Semantic-Region Aware Model Predictive Trajectory Tracking in Automated Guided Vehicles

Autonomous routing through curved path for point-to-point mobile robot is a well-established challenging problem in the area of intelligent path navigation. Point-to-point collision-free locomotion of AGV (Automated Guided Vehicle) requires precise differentiation of movable path from other environmental visual noise. As these path navigating depend on various visual cues and precepts, naturally the semantic meaning of path in contrast to other closely available objects on the visual window requires significant amount of understanding of the input from precepts. In this paper, it is experimentally established that semantic segmentation has proved to be a concise method in making comparative better segregation of paths from midway structured obstacles that are with high computational cost. The claims are also evident from surveyed works. The challenge of reducing high computational performance with efficient segmentation of movable area has been addressed in this research work with a focus on deriving better filtered accessible paths with a degree of algorithmic confidence. Further, this segmented result is taken for curved trajectory tracking by the AGV. A systematic percept mediated deep based Semantic-region Aware Model Predictive Trajectory Tracking(SAMP-TT)Algorithm has been proposed to solve the problem of precise obstacle detection on curved path trajectories. RGB (Red, Green Blue) image of outdoor multi-sectioned area has been collected by Intel Realsense D455 which worked as input feed to the respective neural network models. The performance of the proposed technique has been benchmarked with existing segmentation models including ENET (Efficient Neural Network), U-NET to confirm the considerable reliability and accuracy of the presented algorithm. It has been followed by the state-of-art comparative visual result analysis of different taken models with the proposed architecture.

Portable paper-based probe for on-site ratiometric fluorescence determination of total flavonol glycosides in plant extract using smartphone imaging.

A smartphone-assisted, paper-based ratio fluorescence probe is presented for the rapid, low-cost and on-site quantification of total flavonol glycosides in Ginkgo biloba extracts (GBE). The Al3+/Eu-MOF/paper-based probe utilizes lanthanide metal-organic framework (Ln-MOF) nanoparticles immobilized on Whatman filter paper along with Al3+ for detecting flavonols, which are the hydrolyzed products of flavonol glycosides. The color change of the paper-based fluorescence image from red to orange depends on the concentration of the target analyte in the sample solution. The smartphone equipped with a red, green, blue (RGB) color detector measured the fluorescence signal intensity on the paper substrate after adding flavonol. The analytical variables affecting the performance of the probe, including the addition sequence of the aluminum nitrate solution, its concentration, that of the Ln-MOF solution, the drying time of the paper probe, the reaction time and the sensitivity parameters of the mobile phone camera (ISO), were optimized. Under optimal conditions, the Al3+/Eu-MOF/paper-based probe has good linear response in the concentration range 7 ~ 80µg mL- 1 and a lower detection limit of 2.07µg mL- 1. The results obtained with the paper-based ratio fluorescence probe and smartphone combination were validated by comparing them with high-performance liquid chromatography (HPLC) measurements. This study provides a potential strategy for fabricating Al3+/Eu-MOF/paper-based probe used for total flavonol glycosides determination.

Corrigendum to: Utilisation of unmanned aerial vehicle imagery to assess growth parameters in mungbean (Vigna radiata (L.) Wilczek)

Context Unmanned aerial vehicles (UAV) with red–green–blue (RGB) cameras are increasingly used as a monitoring tool in farming systems. This is the first field study in mungbean (Vigna radiata (L.) Wilzcek) using UAV and image analysis across multiple seasons. Aims This study aims to validate the use of UAV imagery to assess growth parameters (biomass, leaf area, fractional light interception and radiation use efficiency) in mungbean across multiple seasons. Methods Field experiments were conducted in summer 2018/19 and spring–summer 2019/20 for three sowing dates. Growth parameters were collected fortnightly to match UAV flights throughout crop development. Fractional vegetation cover (FVC) and computed vegetation indices: colour index of vegetation extraction (CIVE), green leaf index (GLI), excess green index (ExG), normalised green-red difference index (NGRDI) and visible atmospherically resistant index (VARI) were generated from UAV orthomosaic images. Key results (1) Mungbean biomass can be accurately estimated at the pre-flowering stage using RGB imagery acquired with UAVs; (2) a more accurate relationship between the UAV-based RGB imagery and ground data was observed during pre-flowering compared to post-flowering stages in mungbean; (3) FVC strongly correlated with biomass (R2 = 0.79) during the pre-flowering stage; NGRDI (R2 = 0.86) showed a better ability to directly predict biomass across the three experiments in the pre-flowering stages. Conclusion UAV-based RGB imagery is a promising technology to replace manual light interception measurements and predict biomass, particularly at earlier growth stages of mungbean. Implication These findings can assist researchers in evaluating agronomic strategies and considering the necessary management practices for different seasonal conditions.

Open Data Sources for Post-Consumer Plastic Sorting: What We Have and What We Still Need

The global plastic crisis is a significant concern. Addressing it requires a multi-faceted approach involving legislative, social, and technological measures to reduce post-consumer plastic waste and increase the recycling rate and material circularity. The EU Packaging Directive mandates a 50% recycling rate for plastics by the end of 2025 and 55% by 2030. Machine learning techniques are increasingly being explored to improve the efficiency of waste sorting, thereby contributing to achieving the aforementioned recycling rate goals. However, their effectiveness relies on the availability of high-quality and comprehensive datasets. One of the challenges in this field is the need for suitable datasets for training and testing machine learning models. Furthermore, access to detailed and real-world data, such as information from recycling plants, is often restricted due to paywalls, limiting the accessibility of critical data for research and development. This review sheds light on the situation of RGB (red, green, blue) image datasets and NIR (near-infrared) data availability to identify current dataset gaps and advocate for open access to relevant data sources. The target is to promote collaboration and innovation to combat the plastic crisis and promote sustainable practices collaboratively.

Depth-Quality Purification Feature Processing for Red Green Blue-Depth Salient Object Detection

With the advances in deep learning technology, Red Green Blue-Depth (RGB-D) Salient Object Detection (SOD) based on convolutional neural networks (CNNs) is gaining more and more attention. However, the accuracy of current models is challenging. It has been found that the quality of the depth features profoundly affects the accuracy. Several current RGB-D SOD techniques do not consider the quality of the depth features and directly fuse the original depth features and Red Green Blue (RGB) features for training, resulting in enhanced precision of the model. To address this issue, we propose a depth-quality purification feature processing network for RGB-D SOD, named DQPFPNet. First, we design a depth-quality purification feature processing (DQPFP) module to filter the depth features in a multi-scale manner and fuse them with RGB features in a multi-scale manner. This module can control and enhance the depth features explicitly in the process of cross-modal fusion, avoiding injecting noise or misleading depth features. Second, to prevent overfitting and avoid neuron inactivation, we utilize the RReLU activation function in the training process. In addition, we introduce the pixel position adaptive importance (PPAI) loss, which integrates local structure information to assign different weights to each pixel, thus better guiding the network’s learning process and producing clearer details. Finally, a dual-stage decoder is designed to utilize contextual information to improve the modeling ability of the model and enhance the efficiency of the network. Extensive experiments on six RGB-D datasets demonstrate that DQPFPNet outperforms recent efficient models and delivers cutting-edge accuracy.

Application of Computer Vision for Real-Time Detection of Fruit Color and Size in Fruit Sorter

Computer vision aims to build a computer that can see like humans. Humans can immediately recognize and define an object after seeing and recording an object. This is different from computer visual systems, where camera recordings cannot be directly translated, defined, and recognized by computers, therefore digital image processing is needed first. In this study, computer vision technology was used to detect fruit based on color, size, and shape in real time. The fruit is placed on a conveyor belt, then the fruit object is captured by a webcam using object tracking. Computer vision algorithms and programs can detect fruit objects and recognize ripe and unripe fruits by converting RGB (Red, Green, Blue) colors into HSV (Hue, Saturation, Value) for the color segmentation process. After the detection process, a selector is placed at the end of the conveyor which is used to sort the fruit into 2 categories, namely ripe and unripe. In addition, this study also determines the size and shape of the fruit. From design, realization, and testing, it was found that the success rate of detecting ripe fruit was 97.33% and unripe fruit was 93.33%. To get maximum results, it needs to be supported by room lighting settings that are kept constant.

GrainPointNet: A deep-learning framework for non-invasive sorghum panicle grain count phenotyping

Grain count is an important trait in sorghum because it is highly correlated to the potential yield. By accurately phenotyping the number of grains per panicle, farmers and agronomists can better monitor crop development. Additionally, mapping the spatial variability of grain count can help identify areas of the field with higher or lower potential yields, allowing for targeted management strategies. This study introduces a method for predicting grain count for sorghum panicles by employing a deep learning-based regression framework for point clouds and Red Green Blue (RGB) images. The framework integrates global features derived from a point cloud model of the panicle and grain counts detected from a sequence of RGB images. The models were evaluated on a paired dataset of point cloud models and RGB images collected for 147 sorghum panicles, which included a variety of panicle structures and grain counts. The point cloud models were constructed via a proximal structure-from-motion-based photogrammetry workflow. The model uses PointNet as the backbone network for processing the point clouds and YoloV5 for detecting grains from RGB images. Following the grain detection step, a scaled dot product attention module is integrated into the network to process the grain counts obtained from the RGB image sequence. Finally, the global features for the point cloud model and the grain counts are combined to predict the total grain count for the panicle. Furthermore, the models are also evaluated on downscaled low-resolution point clouds to assess their potential to be adapted in the future for point cloud models for panicles acquired in the field. The models were able to predict grain counts for the high-resolution point cloud dataset with a mean absolute percent error of 6.5% and 6.8% for the low-resolution point cloud dataset. The results serve as a proof of concept to demonstrate the viability of using a multimodal approach based on point clouds and RGB images to estimate grain count per panicle. Additional enhancements to the model like the inclusion of a module to register the point cloud and the RGB images, and evaluating more point cloud backbone networks can help further strengthen the method.

Monocular 3D object detection for construction scene analysis

AbstractThree‐dimensional (3D) object detection, that is, localizing and classifying all critical objects in a 3D space, is essential for downstream construction scene analysis tasks. However, accurate instance segmentation, few 2D object segmentation and 3D object detection data sets, high‐quality feature representations for depth estimation, and limited 3D cues from a single red‐green‐blue (RGB) image pose significant challenges to 3D object detection and severely hinder its practical applications. In response to these challenges, an improved cascade‐based network with a transformer backbone and a boundary‐patch‐refinement method is proposed to build hierarchical features and refine object boundaries, resulting in better results in 2D object detection and instance segmentation. Furthermore, a novel self‐supervised monocular depth learning method is proposed to extract better feature representations for depth estimation from construction site video data with unknown camera parameters. Additionally, a pseudo‐LiDAR point cloud method and a 3D object detection method with a density‐based clustering algorithm are proposed to detect 3D objects in a construction scene without help from 3D labels, which will serve as a good foundation for other downstream 3D tasks. Finally, the proposed model is evaluated for object instance segmentation and depth estimation on the moving objects in construction sites (MOCS) and construction scene data sets. It brings a 9.16% gain in terms of mean average precision (mAP) for object detection and a 4.92% gain in mask mAP for object instance segmentation. The average order accuracy and relative mean error for depth estimation are improved by 0.94% and 60.56%, respectively. This study aims to overcome the challenges and limitations of 3D object detection and facilitate practical applications in construction scene analysis.

A locally weighted, correlated subdomain adaptive network employed to facilitate transfer learning

Domain adaptation has found extensive applications in diverse fields, including transfer learning, deep learning, and image processing, to effectively address the challenge of mismatched data distributions. Nevertheless, persistent challenges such as limited transfer data and the occurrence of negative transfer continue to exist. These issues not only increase the complexity of model learning but also affect the accuracy of the transfer results. To tackle these challenges, this paper introduces a novel approach called the Related Weighted Subdomain Adaptive Network (RWSAN). This network constructs related subdomain clusters in the source domain to encompass a wider spectrum of associated information. It aims to align target domain subdomains with the related subdomain clusters in the source domain as closely as possible, thus increasing the number of transferable samples from the source domain and solving insufficient transferable samples in some adaptations. To address the issue of negative transfer arising from irrelevant subdomains in the source domain during the transfer process, a related weighted maximum mean discrepancy method is introduced. This method optimizes transfer weights, minimizes the feature distribution disparity between the target domain and the source domain, and mitigates the negative impact of irrelevant subdomains on the target domain, thereby enhancing the accuracy of domain adaptation during transfer. To evaluate the proposed RWSAN method, comprehensive performance tests were conducted using widely used red-green-blue (RGB) and hyperspectral image (HIS) image datasets. The results demonstrate that the RWSAN method effectively resolves insufficient transfer data and negative transfer, proving its high reliability. Additionally, it exhibits excellent performance in error analysis, network convergence analysis, data visualization, and distribution difference.

A New Remote Sensing Desert Vegetation Detection Index

Land desertification is a key environmental problem in China, especially in Northwest China, where it seriously affects the sustainable development of natural resources. In this paper, we combine high-resolution satellite remote sensing images and UAV (unmanned aerial vehicle) visible light images to extract desert vegetation data and quickly locate and accurately monitor land desertification in relevant areas according to changes in vegetation coverage. Due to the strong light and dry climate of deserts in Northwest China, which results in deeper vegetation shadow texture and mostly dry shrubs with fewer stems and leaves, the accuracy of the vegetation index commonly used in visible remote sensing image classification is not able to meet the requirements for monitoring and evaluating land desertification. For this reason, in this paper, we took the Hangjin Banner in Bayannur as an example and constructed a new vegetation index, the HSVGVI (hue–saturation–value green enhancement vegetation index), based on the HSV (hue–saturation–value) color space using channel enhancement that can improve the extraction accuracy of desert vegetation and reduce misclassification. In addition, in order to further test the extraction accuracy, samples of densely vegetated and multi-shaded areas were divided in the study area according to the accuracy-influencing factors. At the same time, the HSVGVI was compared with the vegetation indices EXG (excess green index), RGBVI (red–green–blue vegetation index), MGRVI (modified green–red vegetation index), NGBDI (normalized green–red discrepancy index), and VDVI (visible-band discrepancy vegetation index) constructed based on the RGB (red–green–blue) color space. The experimental results show that the extraction accuracy of the EXG and other vegetation indices constructed in RGB color space can only reach 70%, while the extraction accuracy of the HSVGVI can reach more than 95%. In summary, the HSVGVI proposed in this paper can better realize the extraction of desert vegetation data and can provide a reliable technical tool for monitoring and evaluating land desertification.

Smartphone based colorimetric approach for quantitative determination of uric acid using Image J

Recently, significant attention has been directed towards digital image colorimetry DIC using mobile applications or available software programs, which offer the advantage of analyzing samples without the need for sophisticated instruments. One such image processing program is Image J, widely used for obtaining quantitative information from scientific images. Image J could measure the color intensities by quantifying of the RGB (red–green–blue) gray levels across the images of colored substances. These values are correlated to the color intensities through conversion to CMY (cyan–magenta–yellow) values which are proportional to the color intensities. The objective of this study is to develop an innovative analytical method for the quantitative determination of uric acid using Image J for color quantification. Image J was utilized to analyze images captured by smart phone for successive concentrations of uric acid that were previously treated with phosphotungstate to develop a blue color. The proposed method has been applied for determination of uric acid in real urine using standard addition method and the results were compared with UV/VIS spectrophotometry as a reference method. In this research, we will also assess the effectiveness of quantitative analysis using Image J in comparison to a mobile application, namely RGB Color Detector.

Facile, sensitive and reagent-saving smartphone-based digital image colorimetric assay of captopril tablets enabled by long-pathlength RGB acquisition

A new assay of captopril (CTP) tablets was developed based on digital image colorimetry using Ellman’s reagent. For the first time, a facile technique of increasing the analytical path was applied in this work to enhance the sensitivity. For this purpose, the reaction solutions were photographed using a smartphone while they were contained in two 1-cm pathlength cuvettes which were placed side by side. The Red-Green-Blue (RGB) in term of [B/(R+G+B)] was used to plot a standard curve. Compared to using a single cuvette, double cuvettes resulted in more precise analytical signals and better linearity (r2 of 0.9992). Additionally, CTP could be analyzed at low concentrations (2.5–25 µM) with LOD of 0.70 µM and LOQ of 2.13 µM, thus lowering the reagent consumption. The assay was proven to be valid, and it was greener, faster, and more affordable than the pharmacopeial chromatographic method, thereby suitable for pharmaceutical quality control.

A framework for national-scale predictions of forage dry mass in Senegal: UAVs as an intermediate step between field measurements and Sentinel-2 images

ABSTRACT Monitoring available feed for livestock is a key factor for developing pastoralism in the Sahel, and satellite images has proven useful in monitoring dry mass on large spatial scales. This approach requires field measurements of dry mass (herbaceous and woody plants) to calibrate such models based on Earth observation data. However, the need for representative field measurements can be a challenge when considering the low spatial resolution of available satellite data. Unmanned Aerial Vehicles (UAV) can produce very high-resolution images, so we tested UAVs as an intermediate step between field measurements and satellite images, to bridge the difference in spatial scale. We used 43 orthomosaics from a red-green-blue (RGB) UAV sensor in combination with field measurements of herbaceous and woody dry biomass at sites located primarily in the northern/central and southernmost parts of Senegal. We developed a dry mass model trained with filed observed measurements to be applied on the UAV orthomosaics. The dry mass information obtained from these UAV maps was subsequently related to vegetation indices derived from Sentinel-2 data to produce a national-scale 10 m spatial resolution baseline map of herbaceous and woody dry mass for Senegal in 2020. We obtained a high correlation between dry mass derived from UAV and Sentinel-2 indices (R² = 0.91), suggesting a robust basis for national-scale mapping. Lastly, our map was compared with a state-of-the-art annual reference map based on satellite remote sensing. This comparison showed a difference of 21 million tons of dry mass at national level. We concluded that bridging the spatial gap between field and satellite observations using spatially representative UAV data collection is a cost-effective approach for accurate mapping of dry mass at national level using freely available Sentinel-2 satellite data.

Development of Microfluidic Paper-Based Analytical Devices (µPADs) for Determination of Cd2+, Pb2+, and Cu2+ Ions in Mineral Water

Microfluidic paper-based analytical devices (µPADs) have been successfully developed using dual detection: electrochemical and colorimetric systems. The µPADs have the potential to be used as Pb(II), Cd(II), and Cu(II) sensors to test the quality of water. The fabrication process uses hot embossing and screen-printing methods. The working electrode in the electrochemical zone was enhanced by the bismuth metal deposition process, while in the colorimetric zone, the gold nanoparticles modified with thioctic acid and dansylhydrazine (TA-Au-DNS) were used as a colorimetric sensor to detect Cu. The basic material of µPADs was characterized using a Fourier-transform infrared (FTIR) and a contact angle meter (CAM). In the electrochemical zone, the signals of square wave anodic stripping voltammetry (SWASV) resulted in good detection of Pb(II) and Cd(II) (from 0 to 100 ppb) with a limit of detection of 1.588 and 1.42 ppb, respectively. In the colorimetric zone, the performance of TA-Au-DNS for detecting Cu metal was obtained from readings through the red-green-blue (RGB) sensor as a miniature of µPADs reader. The LOD, LOQ, and average Vx0 (linearity values) in the detection of Cu(II) (from 58 to 100 ppb) are 8.51 ppb, 28.36 ppb, and 0.41%, respectively.

Specific separation and sensitive detection of foodborne pathogens by phage-derived bacterial-binding protein-nano magnetic beads coupled with smartphone-assisted paper sensor

Foodborne pathogen infection poses a significant threat to public health and is considered as one of the most serious hazards in global food safety. Herein, a sensitive and efficient method for on-site monitoring of foodborne pathogens was developed by using a smartphone-assisted paper-sensor combined with phage-derived bacterial-binding proteins-nano magnetic beads (PBPs-MBs). PBPs including tail fiber protein (TFP:gp13), cell-wall binding domain (CBD) of endolysin and tailspike protein (TSP) coated on the surface of MBs were applied for rapid separation and enrichment of targeted bacteria (Escherichia coli O157:H7, Staphylococcus aureus and Salmonella typhimurium, respectively) from food samples in 20 min before detection on paper-based sensors. The paper-based sensor was loaded with the lytic agent (polymyxin B) to induce bacterial lysis and release specific endogenous enzymes. Subsequently, three distinct chromogenic substrates were hydrolyzed by their corresponding enzymes, resulting in characteristic color changes on the paper, respectively. In addition, a smartphone APP for red-green-blue (RGB) color analysis of paper was able to directly detect three foodborne pathogens. As a result, the limit of detection (LOD) values for three foodborne pathogens were found to be 2.44 × 102, 2.68 × 104 and 4.62 × 103 CFU/mL, respectively, which were much lower than other studies (106–108 CFU/mL) based on enzymes. Moreover, the feasibility of this approach was further assessed through the successful detection of targeted bacteria in real samples with satisfactory recovery rates. In conclusion, this smartphone-assisted biosensor offers promising application potential for point-of-care testing (POCT) of foodborne pathogens in resource-scarce areas.