Digital Image Analysis for the Colorimetric Determination of Aluminum, Total Iron, Nitrite and Soluble Phosphorus in Waters

Barros, Juan A. V. A.; Oliveira, Fagner Moreira de; Santos, Guilherme de O.; Wisniewski, Célio; Luccas, Pedro Orival

doi:10.1080/00032719.2016.1182542

Cited by 30 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Light from a white light source (2) passes through a substance in a cell and enters a light-sensitive sensor (3), which decomposes this light into spectra of three colors (red, green, blue) and forms a digital signal that characterizes the color of the liquid in the cell. This digital signal is fed to the microprocessor data processing unit (4), where it is processed and analyzed.…”

Section: Methodsmentioning

confidence: 99%

“…In [12] a device was made -a digital colorimeter that determines the iron content with an implemented software application that registers the components of the color scheme, preserving the values of red, green and blue, and calculates the values of hue, brightness and transparency, using standard theory colors, and in [6] developed a budget portable device for colorimetric analysis in place. The authors' research [4] is conducted using a webcam that determines the iron content in water using digital image colorimetry. The main method of this study is the regression of least squares to obtain a quadratic equation based on red, green and blue hues, color saturation and brightness, which allowed to evaluate the most accurate analysis.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Spectrophotometric Method for Coagulant Determining in a Stream Based on an Artificial Neural Network

Safonyk

Mishchanchuk

Hrytsiuk

2021

Lecture Notes in Computational Intelligence and Decision Making

View full text Add to dashboard Cite

Spectrophotometric analysis based on artificial neural network (ANN), partial least squares regression (PLS) and basic component regression (PCR) models has been proposed to simultaneously determine coagulant (Fe) during the electrocoagulation process. An experimental laboratory installation was created to study the processes of photometric research with a device that analyzes the color and intensity of light in real time. The color sensor determines the color parameters: RGB, which, based on ANN, are translated into the HSL color space. Software for determining the concentration of iron in the coagulant using artificial intelligence, which is a web application for displaying the color parameters of the coagulant, the determined concentration of iron in the coagulant, as well as saving the history of all measurements in the database. ANN, trained using different teaching methods. An optimizer was selected for the appropriate process, the standard deviation (RMSE) is 6.91%.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Spectrophotometric Method for Coagulant Determining in a Stream Based on an Artificial Neural Network

Safonyk

Mishchanchuk

Hrytsiuk

2021

Lecture Notes in Computational Intelligence and Decision Making

View full text Add to dashboard Cite

show abstract

“… 10 , 11 Some of these variations such as the lighting condition and object-camera distance can be minimized using a controlled environment that is only possible in laboratory settings. 12 − 15 However, PADs are ultimately meant to be used in field settings by a minimally trained user, during which the criteria of controlled assay and imaging conditions may not be achieved, resulting in less accurate results.…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning-Assisted Analysis of Colorimetric Assays on Paper Analytical Devices

et al. 2021

View full text Add to dashboard Cite

Paper-based analytical devices (PADs) employing colorimetric detection and smartphone images have gained wider acceptance in a variety of measurement applications. PADs are primarily meant to be used in field settings where assay and imaging conditions greatly vary, resulting in less accurate results. Recently, machine-learning (ML)-assisted models have been used in image analysis. We evaluated a combination of four ML models—logistic regression, support vector machine (SVM), random forest, and artificial neural network (ANN)—as well as three image color spaces, RGB, HSV, and LAB, for their ability to accurately predict analyte concentrations. We used images of PADs taken at varying lighting conditions, with different cameras and users for food color and enzyme inhibition assays to create training and test datasets. The prediction accuracy was higher for food color than enzyme inhibition assays in most of the ML models and color space combinations. All models better predicted coarse-level classifications than fine-grained concentration classes. ML models using the sample color along with a reference color increased the models’ ability to predict the result in which the reference color may have partially factored out the variation in ambient assay and imaging conditions. The best concentration class prediction accuracy obtained for food color was 0.966 when using the ANN model and LAB color space. The accuracy for enzyme inhibition assay was 0.908 when using the SVM model and LAB color space. Appropriate models and color space combinations can be useful to analyze large numbers of samples on PADs as a powerful low-cost quick field-testing tool.

show abstract

“…Therefore, research about the application of digital image colorimetry has bloomed in the past decade. These studies have tried to quantify the metal cations [ 14 , 15 , 16 , 17 ], nitrate (trinitrotoluene (TNT) [ 18 ], ammonium nitrate [ 19 ]), phosphorus [ 17 ], chlorine [ 14 , 20 , 21 ] in water through digital images by using either camera, smartphone or webcams, but without a comparable method to correct light influence or using different color values, which makes it difficult to make a comparison. Details of the literature are shown in Table S1 .…”

Section: Introductionmentioning

confidence: 99%

A Low-Cost Digital Colorimetry Setup to Investigate the Relationship between Water Color and Its Chemical Composition

Zeng

Mannaerts

Shang

2021

Sensors

View full text Add to dashboard Cite

Developments in digital image acquisition technologies and citizen science lead to more water color observations and broader public participation in environmental monitoring. However, the implications of the use of these simple water color indices for water quality assessment have not yet been fully evaluated. In this paper, we build a low-cost digital camera colorimetry setup to investigate quantitative relationships between water color indices and concentrations of optically active constituents (OACs). As proxies for colored dissolved organic matter (CDOM) and phytoplankton, humic acid and algae pigments were used to investigate the relationship between water chromaticity and concentration. We found that the concentration fits an ascending relationship with xy chromaticity values and a descending relationship with hue angle. Our investigations permitted us to increase the information content of simple water color observations, by relating them to chemical constituent concentrations in observed waters.

show abstract

Digital Image Analysis for the Colorimetric Determination of Aluminum, Total Iron, Nitrite and Soluble Phosphorus in Waters

Cited by 30 publications

References 21 publications

Spectrophotometric Method for Coagulant Determining in a Stream Based on an Artificial Neural Network

Spectrophotometric Method for Coagulant Determining in a Stream Based on an Artificial Neural Network

Machine-Learning-Assisted Analysis of Colorimetric Assays on Paper Analytical Devices

A Low-Cost Digital Colorimetry Setup to Investigate the Relationship between Water Color and Its Chemical Composition

Contact Info

Product

Resources

About