Smartphone Images Research Articles

A smartphone-assisted microarray immunosensor coupled with GO-based multi-stage signal amplification strategy for high-sensitivity detection of okadaic acid

Okadaic acid (OA) is one of the main virulence factors of diarrheal shellfish toxins (DSP), which can cause acute carcinogenic or teratogenic effects after ingestion of contaminated shellfish. Therefore, high-sensitivity and fast detection of OA is a key to preventing the occurrence of safety accidents. In this paper, we effectively established a smartphone-assisted microarray immunosensor combined with an indirect competitive ELISA (iELISA) for quantitative colorimetric detection of OA. To further improve the detection sensitivity and match the smartphone imaging, a novel graphene oxide (GO) composite probe was developed to realize the multi-stage signal amplification. The system exhibited a wide linear range for the detection of OA (0.02–33.6 ng ·mL−1) with low detection limit of 0.02 ng ·mL−1. The recovery of OA in spiked shellfish samples was in the range of 80%–103.5%, which indicates the good applicability of this biosensor. The whole detection system has advantages of simplicity, low cost, high sensitivity and portability, which is expected to be a powerful alternative tool for on-site detecting and early warning of the pollution of marine products.

Development and Validation of Extractive Spectrophotometric Method for Estimation of Hydroxychloroquine Sulphate by using Smartphone Application

A simple, sensitive, accurate, precise and reproducible extractive spectrophotometric method was developed for estimation of Hydroxychloroquine Sulphate (HCQS) in bulk and pharmaceutical dosage form. The method is based on formation of ion pair complex of Hydroxychloroquine Sulphate with Bromocresol green dye in acidic medium. This complex extracted in chloroform and measured quantitatively at 421nm for estimation of Hydroxychloroquine Sulphate present in the sample. In this method estimation was also done by using Smartphone Application known as PhotoMetrix pro. Beer Lambert’s law obeyed over a range of 2-10 μg/ml for HCQS by UV spectrophotometric (r²=0.9988) and by SmartPhone Image analysis (r²=0.999) method. The developed method was successfully applied for estimation of Hydroxychloroquine Sulphate in three commercial product tablet dosage form without interference from common additives. The assay was found to be 100.09%, 100.8%, 98.6% by UV and 99.2%, 101.46%, 101.1% using PhotoMetrix for three formulation containing Hydroxychloroquine Sulphate. The developed method was also validated according to ICH Q2 guideline for linearity, range, accuracy, and precision. Comparison for both method UV and PhotoMetrix done by performing t-test, result shows that there is no significant difference between both method so PhotoMetrix can be used as alternative to UV for routine analysis of Hydroxychloroquine Sulphate.
 Keywords: Hydroxychloroquine Sulphate, Bromocresol green, Potassium Hydrogen Phthalate buffer, UV spectrophotometric, PhotoMetrix.

Stateful-Service-Based Pupil Recognition in Natural Light Environments.

Smartphones are currently extensively used worldwide, and advances in hardware quality have engendered improvements in smartphone image quality, which is occasionally comparable to the quality of medical imaging systems. This paper proposes two algorithms for pupil recognition: a stateful-service-based pupil recognition mechanism and color component low-pass filtering algorithm. The PRSSM algorithm can determine pupil diameters in images captured in indoor natural light environments, and the CCLPF algorithm can determine pupil diameters in those captured outdoors under sunlight. The PRSSM algorithm converts RGB colors into the hue saturation value color space and performs adaptive thresholding, morphological operations, and contour detection for effectively analyzing the diameter of the pupil. The CCLPF algorithm derives the average matrix for the red components of eye images captured in outdoor environments. It also performs low-pass filtering, morphological and contour detection operations, and rule-of-thumb correction. This algorithm can effectively analyze pupil diameter in outdoor natural light. Traditional ruler-based measurements of pupil diameter were used as the reference to verify the accuracy of the PRSSM and CCLPF algorithms and to compare their accuracy with that of the other algorithm. The errors in pupil diameter data were smaller for the PRSSM and CCLPF algorithms than for the other algorithm.

The mediatic dimension of images: visual semiotics faced with Gerhard Richter’s artwork

In this article, the author endeavours to analyse Gerhard Richter’s photo-paintings for the way they build an intersemiotic dialogue between photography and painting. On the one hand, he tries to characterize the modalities of this dialogue and to provide an original interpretation of Richter’s work. On the other hand, he uses the special case of Richter’s work as a starting point for a conceptual renewal in the analysis of visual languages, notably with regard to semiotic approaches. In particular, the author aims to define the mediatic dimension of images, which is concerned with the substances, substrates and devices through which images are produced. He does this in order to integrate the achievements of visual semiotics in regard to the compositional dimension of colours, shapes and figures. He takes into account the way in which the material and the substances of expression of images impact the construction of meaning, in accordance with the hypothesis of a superposition of technical and semantic aspects. The confrontation with Richter’s production leads him to go beyond plastic and figurative readings as he proposes the concepts of technical formats and techno-perceptions of images. While the former concern the historical recognition of images on the basis of the devices having produced their substance – leading to identifications such as ‘early cinema images’, ‘smartphone images’, ‘surveillance camera images’, etc. – the latter concern the perceptive configurations resulting from the formative work of the technical devices.

Exhibition of Noise-Aided Stochastic Resonance by Discontinuity Detectors in Smartphone Images

The use of smartphone cameras for capturing photographs has seen an exponential growth in the last decade. The noise present in these photographs significantly deviates from the popular Independently Identically Distributed (i.i.d.) Additive White Gaussian Noise (AWGN) noise, and thus the conclusions drawn from simulated-AWGN cannot be directly applied to the smartphone’s true noise. This paper is the first reporting of the exhibition of Stochastic Resonance (SR) or noise-induced threshold-crossing in three genres of discontinuity detectors used in image processing — corner detector, line detector, and edge detector for real-world smartphone images. For the images under investigation, the performance of these detectors is quantified w.r.t. parameters representing intrinsic noise. Observations suggest that all these detectors inherently exhibit the phenomenon of SR due to the fundamental assistance offered by controlled amount of noise in crossing detector thresholds. The manifestations of SR — constant parameter value with varying noise and varying parameter value with constant noise — are demonstrated to exhibit SR in each of the three detectors.

Creating a secure clinical 'Bring Your Own Device' BYOD photography service to document and monitor suspicious lesions in the lid oncology clinic.

BackgroundOphthalmic examinations are mostly documented using sketches and written descriptions. Improvements in app security and IT infrastructure mean that high-quality anterior segment photographs can be routinely collected with smartphones alone. The lid oncology team relied on pre-operative formal slit-lamp imaging in the one-stop biopsy clinic, a lengthy process with capacity limitations, that risked delays to care.MethodsA Bring Your Own Device (BYOD) photography service was developed through a series of iterations and collaborations. Healthcare Assistants took photographs on iPhone SE with Quikvue lens attachments in Pando app. Lesions requiring a slit lamp were photographed by the doctor. Images were uploaded to the patient record twice weekly. The service was evaluated using time–motion studies, imaging quality and utility grading, and patient feedback.ResultsBYOD photography saved lid oncology patients 41 min (one-third of total appointment time) and reduced delays to treatment to zero. A patient survey reflected the acceptability of the service, with 100% feeling photography was important at every visit. In terms of utility, 97.5% of smartphone images were suitable for monitoring lesions and making management decisions. The management plan based on the smartphone photographs was consistent with the management plan formulated face-to-face in clinic in 92.5% images.ConclusionBYOD photography has replaced formal slit-lamp imaging in the lid oncology service. This sustainable, cost-effective BYOD solution requires little training and can be adapted, reproduced, and scaled globally. BYOD photography can offer detailed records to monitor progress, contribute to remote care models, improve patient experience, and reducing medical error.

ColoriSens: An open-source and low-cost portable color sensor board for microfluidic integration with wireless communication and fluorescence detection

Microfluidic colorimetric biosensors have shown promising potential for detecting metal cations, anions, organic dyes, drugs, pesticides. As for today, most colorimetric sensors are read by a smartphone or professional optical imaging system, and there is still a lack of an affordable and reliable colorimetric detector for the microfluidic chip. Integrating those reading and detection capabilities into a microfluidic system is essential for point-of-care (POC) detection and can enable more complex microfluidic operations, such as lab-on-a-chip experiments or programmable microfluidics. We developed an open-source colorimetric detection sensor board that can be integrated into the existing microfluidic system. This sensor board has a built-in UV source that enables fluorescence detection. With built-in USB and Wi-Fi connectivity and a set of simple APIs, microfluidic systems can communicate directly with this sensor board, even wirelessly. The sensor was designed for low-cost. With a total build cost of less than 12 EUR per unit, it is ideal for low-cost systems and DIY microfluidic users. Along with the sensor board, we also designed a companion microfluidic chip carrier cartridge which can be modified depending on the chip’s dimension. To demonstrate the sensor, we also developed a cross-platform open-source client application to demonstrate the communication APIs and the functionality of the sensor board.

Quantitative thin layer chromatography for the determination of medroxyprogesterone acetate using a smartphone and open-source image analysis

Intramuscular medroxyprogesterone acetate (MPA) products are commonly used to treat endometriosis and are the most widely used injectable contraceptives worldwide. Therefore, dependable quality screening of MPA injectables is a crucial measure necessary for ensuring that consumers are provided with safe and effective medications. Here, a thin-layer chromatography (TLC) method for MPA identification is combined with image analysis using a smartphone, 3D-printed light box, and open-source ImageJ software. The method's validation included two brands of MPA injectables, both at 150 mg mL−1 dosage. The TLC procedure used was based on the identity test found in The International Pharmacopoeia's Medroxyprogesterone injection monograph. Spots produced on the TLC plates were then photographed using a smartphone camera and quantified using ImageJ's image analysis software. The pixel data collected from each plate's standard spots were compared to the data generated from its sample spots. Data sets collected across multiple TLC plates and numerous days of method performance were evaluated to assess linearity, accuracy, precision, specificity, and robustness. Across the range of 75–125% of the target concentration, the method was found to have linearity of standard spots (with R2 generally greater than 0.99), overall accuracy of 101.0% (4.1% RSD), repeatability pooled standard deviation of 2.44%, intermediate precision pooled standard deviation of 3.68%, and observed demonstration of specificity and robustness. In low and middle-income countries (LMICs), quality screening of pharmaceutical products like MPA injectables can be challenging when testing resources are expensive, difficult to procure, or complex to utilize. The results of the TLC/ImageJ method validation suggest that this simple procedure that requires minimal resources may serve as a viable option for reliable quality screening of MPA levels in injectable suspensions.

Visual Positioning System Based on 6D Object Pose Estimation Using Mobile Web

Recently, the demand for location-based services using mobile devices in indoor spaces without a global positioning system (GPS) has increased. However, to the best of our knowledge, solutions that are fully applicable to indoor positioning and navigation and ensure real-time mobility on mobile devices, such as global navigation satellite system (GNSS) solutions, cannot achieve remarkable researches in indoor circumstances. Indoor single-shot image positioning using smartphone cameras does not require a dedicated infrastructure and offers the advantages of low price and large potential markets owing to the popularization of smartphones. However, existing methods or systems based on smartphone cameras and image algorithms encounter various limitations when implemented in indoor environments. To address this, we designed an indoor visual positioning system for mobile devices that can locate users in indoor scenes. The proposed method uses a smartphone camera to detect objects through a single image in a web environment and calculates the location of the smartphone to find users in an indoor space. The system is inexpensive because it integrates deep learning and computer vision algorithms and does not require additional infrastructure. We present a novel method of detecting 3D model objects from single-shot RGB data, estimating the 6D pose and position of the camera and correcting errors based on voxels. To this end, the popular convolutional neural network (CNN) is improved by real-time pose estimation to handle the entire 6D pose estimate the location and direction of the camera. The estimated position of the camera is addressed to a voxel to determine a stable user position. Our VPS system provides the user with indoor information in 3D AR model. The voxel address optimization approach with camera 6D position estimation using RGB images in a mobile web environment outperforms real-time performance and accuracy compared to current state-of-the-art methods using RGB depth or point cloud.

Fast DNA biosensing based on isothermal amplification, unmodified gold nanoparticles, and smartphone detection

The protection of the consumer against foodborne illnesses and fraudulent practices requires methods capable of detecting critical components. Classical instrumental and DNA-based technologies have assay time, portability, and cost limitations. Thus, food control needs alternative methodologies for massive and cost-effective screening. Herein, we report an instrument-free method based on detecting genes that encode proteins related to food allergies and ingredients associated with illegal practices. Tailed recombinase polymerase amplification (tailed-RPA) provided the selective isothermal amplification of target regions. A reproducible and fast optical detection was developed based on the salt-induced aggregation of 15 nm gold nanoparticles (AuNPs). The target presence was directly observed (naked-eye detection) and quantified using a smartphone and RGB image decomposition. The advantages arise from the effective formation of a hybrid complex between non-functionalized nanoparticles and amplification products with a single-strand tail, featuring short incubation time, simplicity, and low sample and reagent volumes. As proof of concept, two targets were determined: trnL gene and ITS region. The first sequence is located in the chloroplast genome of cereals and is valuable to control the adulteration of meat products. The second is a fragment common to the three main gluten-containing cereals, applicable to the indirect detection of this allergen. The novelty also is the integration of a low-cost assay platform and a straightforward interpretation system to foster its implementation in the industry. The RPA-AuNP assay offered a good sensitivity (genomic DNA 0.8 ng), selectivity (absence of unspecific response), reproducibility (standard deviation 2–11%), and accuracy in marketed food products (100%). Therefore, a competitive biosensing system enables better control according to food industry/consumers demands from Farm to Fork strategy.

Skin cancer diagnosis using convolutional neural networks for smartphone images: A comparative study

In the past few years many researches investigated algorithms to diagnose skin cancer lesions where melanoma is the deadliest type of skin cancer. In this paper, we propose three different methods for binary classification (melanoma and nevus) using smartphone images since there is a lack in research on it. The applied methods depend on different versions of CNN architectures namely; Alex-net, Mobilenet-V2, and Resnet-50. These three methods are divided into two groups; one group is the three nets with transfer learning applied on the original data, and the second group is the same methods used for group one but applied on augmented data. The proposed methods are applied on PAD-UFES-20 which is a smartphone images dataset. The augmented data have improved the performance of each method relative to its performance for original data. The best performance is achieved when using Alex-net with transfer learning (TL) and data augmentation, as it achieved 99% for accuracy, 96.364% for sensitivity, 99.792% for specificity, 99.167% for precision, and 97.661% for F1-score. Mobilenet-V2 with TL on augmented dataset achieved promising results if it used as a mobile application as it achieved 94.071% for accuracy, 84.547% for sensitivity, 96.25% for specificity, 84.223% for precision, and 84.2% for F1-score. And finally, Resnet-50 with TL on augmented dataset achieved 94.918% for accuracy, 77.275% for sensitivity, 98.918% for specificity, 95.192% for precision, and 84.737% for F1-score.

Static smartphone images supplemented by videoconferencing for breast telepathology

BackgroundBoth static images and videoconferencing by smartphone have been tried for telepathology. Combining the two approaches for telepathology might offset some of the limitations of both techniques. MethodsA total of 150 cases of breast pathology were retrieved and were photographed by a trained junior pathologist using a smartphone camera and binocular microscope and the images were sent as Google photos attachments with email to three pathologists. The pathologists opened the emailed attachments during separate prescheduled google meet videoconferencing sessions and rendered the diagnosis verbally to the junior pathologist. The pathologists were given the option of asking for live dynamic images of the cases during the meet which were transmitted using the rear camera of the smartphone with the video option of google meet. ResultsThe overall concordance rates for the three pathologists were 96.6%, 99.3% and 98.0% (Mean 98.0%). The reporting pathologists asked for dynamic live images in 23, 20 and 18 cases respectively. Out of these 61 cases, a discrepant diagnosis was made in 7 cases (11.4%). The reporting pathologist was satisfied with the quality of static images (Mean Likert score 4.2/5). However, concerns were raised on the consistency of video quality (Mean Likert score 2.5/5). The screen share option of Google meet was found useful to discuss specific features of the case. (Mean Likert Score 4.6/5) ConclusionThe combined approach to telepathology has shown some promise and it is hoped that with adequate training the discordance can be reduced.

Print-and-stick unibody microfluidics coupled surface plasmon resonance (SPR) chip for smartphone imaging SPR (Smart-iSRP)

The design of a smartphone imaging surface plasmon resonance (Smart-iSPR) system integrated with an affordable 3D-printed microfluidic SPR chip fabricated via a facile manufacturing approach could pave the way towards the development of miniaturized and integrated smartphone iSPR biosensors for emerging point-of-use applications. Conventional smartphone-based SPR systems using soft photolithography for the fabrication of microfluidics SPR chips are costly, labour-intensive and required a specially-equipped light-controlled environment, that is inadequate and mismatched with the consumer-based smartphone detection platform. Herein, we report the design, fabrication and testing of an innovative print-and-stick unibody microfluidics coupled SPR chip for smartphone iSPR. The 3D-printed microfluidics (∼€0.006) is assembled via an aptly-sized adhesive tape with the gold SPR sensing surface. Such a simple integrated microfluidic SPR chip with the print-and-stick configuration has a high resistance to fluid leakages at the channel-to-sensor interface with pressure up to 66.9 Pa and the tubing-to-inset interfaces with pressure up to 86.9 Pa. The smartphone iSPR platform weighs 138 g and with a dimension of around 70 × 60 × 40 mm3, and its performance was characterized using a standard Biacore® β2-microglobulin calibration kit. The sensorgrams obtained by the smartphone iSPR show all the typical characteristics for surface functionalization, association and dissociation events. The smartphone iSPR responds linearly to β2-microglobulin within the range of 10–200 nM (R2 = 0.986) with a limit-of-detection (LOD) of 1.5 nM. Given the miniaturized feature and simple camera-based imaging smartphone iSPR, the analytical performance is satisfactory when compared with the analytical dynamic range of 2–32 nM described in the Biacore® protocol.

Intelligently design primary aromatic amines derived carbon dots for optical dual-mode and smartphone imaging detection of nitrite based on specific diazo coupling

Primary aromatic amines derived carbon dots (PAA-CDs) with the protonated amino groups and high quantum yield of 46% were favorably obtained by one-step solvothermal treatment of m-phenylenediamine (m-PDA) in acidic environment. The interaction between the PAA-CDs and nitrite (NO2-) was inherited the characteristic reaction of m-PDA (a primary aromatic amine) and NO2-, resulting in strong fluorescence quenching and obvious absorption variation of the PAA-CDs. Meanwhile, a chromogenic reaction of diazo coupling can cause significant color changes. Hence, the PAA-CDs were developed for an optical dual-mode and smartphone imaging sensor for NO2- detection in the range of 3.0 ~ 40.0 μM with high selectivity, good sensitivity, and excellent anti-interference capability. A limit of detection (LOD) of 0.024 μM and 0.16 μM was implemented by fluorometry and colorimetry, respectively. For smartphone imaging colorimetry, the LODs of 0.46 μM (visible color) and 0.99 μM (fluorescence color) were acquired. More importantly, the established sensor has been successfully applied for the dynamic detection of NO2- in various food samples with the satisfying results. A smartphone imaging colorimetry method based on the CDs was firstly proposed to visually and quantitatively detect NO2-, which will broaden the application range of the CDs in food safety inspection.

Rayleigh anomaly-enabled mode hybridization in gold nanohole arrays by scalable colloidal lithography for highly-sensitive biosensing

Abstract Plasmonic sensors exhibit tremendous potential to accomplish real-time, label-free, and high-sensitivity biosensing. Gold nanohole array (GNA) is one of the classic plasmonic nanostructures that can be readily fabricated and integrated into microfluidic platforms for a variety of applications. Even though GNA has been widely studied, new phenomena and applications are still emerging continuously expanding its capabilities. In this article, we demonstrated narrow-band high-order resonances enabled by Rayleigh anomaly in the nanohole arrays that are fabricated by scalable colloidal lithography. We fabricated large-area GNAs with different hole diameters, and investigated their transmission characteristics both numerically and experimentally. We showed that mode hybridization between the plasmon mode of the nanoholes and Rayleigh anomaly of the array could give rise to high-quality decapole resonance with a unique nearfield profile. We experimentally achieved a refractive index sensitivity, i.e., RIS up to 407 nm/RIU. More importantly, we introduced a spectrometer-free refractive index sensing based on lens-free smartphone imaging of GNAs with (intensity) sensitivity up to 137%/RIU. Using this platform, we realized the label-free detection of BSA molecules with concentration as low as 10−8 M. We believe our work could pave the way for highly sensitive and compact point-of-care devices with cost-effective and high-throughput plasmonic chips.

Nutrient and Food Group Prediction as Orchestrated by an Automated Image Recognition System in a Smartphone App (CALO mama): Validation Study

BackgroundA smartphone image recognition app is expected to be a novel tool for measuring nutrients and food intake, but its performance has not been well evaluated.ObjectiveWe assessed the accuracy of the performance of an image recognition app called CALO mama in terms of the nutrient and food group contents automatically estimated by the app.MethodsWe prepared 120 meal samples for which the nutrients and food groups were calculated. Next, we predicted the nutrients and food groups included in the meals from their photographs by using (1) automated image recognition only and (2) manual modification after automatic identification.ResultsPredictions generated using only image recognition were similar to the actual data on the weight of meals and were accurate for 11 out of 30 nutrients and 4 out of 15 food groups. The app underestimated energy, 19 nutrients, and 9 food groups, while it overestimated dairy products and confectioneries. After manual modification, the predictions were similar for energy, accurately capturing the nutrients for 29 out of 30 of meals and the food groups for 10 out of 15 meals. The app underestimated pulses, fruits, and meats, while it overestimated weight, vitamin C, vegetables, and confectioneries.ConclusionsThe results of this study suggest that manual modification after prediction using image recognition improves the performance of the app in assessing the nutrients and food groups of meals. Our findings suggest that image recognition has the potential to achieve a description of the dietary intakes of populations by using “precision nutrition” (a comprehensive and dynamic approach to developing tailored nutritional recommendations) for individuals.

Agreement of anthropometric and body composition measures predicted from 2D smartphone images and body impedance scales with criterion methods

Background/objectivesBody composition and anthropometry assessment from two-dimensional smartphone images is possible through advancement of computational hardware and artificial intelligence (AI) techniques. This study established agreement of a novel smartphone assessment, compared with traditional bioelectrical impedance analysis (BIA), and criterion measures. Subjects/methodsBody composition of 929 adults was measured using DXA (GE lunar iDXA), a foot-to-foot BIA machine (TANITA BC-313), and predictions from two-dimensional smartphone images. Anthropometry measures were also collected. Body composition and anthropometry estimates were compared via concordance coefficient correlation (CCC), equivalence testing, Bland–Altman analysis, and root mean square error (RMSE). Results2D smartphone image predictions for percent body fat (%BF) (males: CCC = 0.90 and RMSE = 2.9, and females: CCC = 0.90 and RMSE = 2.8) reported greater agreement with DXA measures than the BIA measures (males: CCC = 0.66 and RMSE = 5.6, and females: CCC = 0.79 and RMSE = 4.6). All anthropometry 2D smartphone image predictions had a strong agreement with criterion measurements (CCC ≥ 0.84 and RMSE ≤ 3.3). Body composition and anthropometry measures predicted by the 2D smartphone images were clinically equivalent at ±2.5 and ±5.0% thresholds. BIA %BF was not equivalent at either threshold; with only female BIA fat-free mass equivalent at the ±5% threshold. ConclusionBody composition predictions from 2D smartphone application images provide a promising alternative to BIA scales for in-home body composition assessment. Future research should assess the validity of this method for longitudinally tracking body composition and indicating an individual’s potential risk of chronic diseases.

Assessing grass water use efficiency through smartphone imaging and ImageJ analysis

Overwatering and underwatering grass are widespread issues with environmental and financial consequences. Current approaches to assessing grass water use efficiency (WUE) are inaccessible to the public. We developed an accessible method to assess grass WUE: combining smartphone imaging with open access color unmixing analysis. Images were converted from the RGB color space to the CIELAB color space using ImageJ—an open access, user-friendly software—to correct for uneven lighting without compromising image detail. We obtained parameters a* (unmixes green-to-red vector) and b* (unmixes blue-to-yellow vector). We hypothesized that WUE can be accurately determined from grass color and growth, which can be analyzed using CIELAB color unmixing. We tested how nine watering levels (100–900 mL every 4–5 days) affected Stenotaphrum secundatum (St. Augustine grass) over one month in Orange County, Southern California. Color was quantified using a*:b* ratios, growth was tracked using grass area, and pigment composition was analyzed using plot profiles. We analyzed whole samples in the uncontrolled real-world environment, individual leaves in a controlled homemade imaging box, and extracted pigments before and after paper chromatography. Results were clustered using Gaussian finite mixture models, implemented by R package ‘mclust’. Overall trends for grass coverage, a*:b* ratios, and pigment composition were consistent with real-world observations. Cluster analyses were consistent across image types, identified an ideal watering range (600–700 mL), and differentiated between underwatered and overwatered grass. Our hypothesis was supported. Our method can be applied in automated irrigation systems or apps, providing grass WUE assessment for regular consumer use.

Analysis of brand visibility on smartphone images with three-stage model using eye-tracking and EEG: a decision-making study in neuromarketing

Analysis of brand visibility on smartphone images with three-stage model using eye-tracking and EEG: a decision-making study in neuromarketing

Smartphone Imaging Devices for Screening of Diabetic Retinopathy: A Review

Background: Innovative solutions are needed for retinal fundus examination in diabetic individuals as a result of the projected rise in the global prevalence of Diabetic Retinopathy (DR) in the near future. Early detection of DR will help to prevent avoidable blindness and lead to improvement of eyecare services for diabetic individuals. Currently, smartphone fundoscopy is emerging as new form of retinal examination because of the several advantages it offers, such as lower cost and portability, compared to the conventional desktop cameras. This review seeks to describe the characteristics of commercially available smartphone imaging devices.Methodology: The Google search engine was used to investigate the details of different smartphone imaging devices currently available for fundus examination. Studies that have evaluated these devices for the detection of DR were also reported. Results: Findings from this investigation revealed that some of these devices have the potential to detect features of DR which could be beneficial to diabetic individuals living in developing nations. Conclusion: Further research comparing various smartphone imaging devices for DR detection should be carried out by health care professionals across various populations.