Analysis of Computer Vision Algorithms to Determine the Quality of Fermented Cocoa (Theobroma Cacao): Systematic Literature Review

Mite-Baidal, Karen; Solís-Avilés, Evelyn; Martínez-Carriel, Tayron; Marcillo-Plaza, Augusto; Cruz-Ibarra, Elicia; Baque-Bustamante, Wilmer

doi:10.1007/978-3-030-10728-4_9

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cacao beans with high variability affect the flavor of chocolate products produced. The variabilities of cacao beans are influenced by growth conditions, genetics, and drying processes [1]. One of the stages that also greatly affect the flavor and variability of cacao beans is the fermentation process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Determination of Acid Level (pH) and Moisture Content of Cocoa Beans at Various Fermentation Level Using Visible Near-Infrared (Vis-NIR) Spectroscopy

Priambodo

Saputro

Pahlawan

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Fermentation is critical in cacao processing which breakdowns sugar compounds in the pulp into organic acids. The produced organic acids stimulate enzymatic reactions in the beans which affect the flavor, taste, and color of the cacao beans. Acidity (pH) and moisture content of cacao beans influence the quality of cacao during fermentation. Those parameters are commonly measured using pH meter and gravimetric methods which are time-consuming and destructive.Therefore, the objective of this study was to develop non-destructive calibration models to predict the pH and moisture content of cacao beans at various fermentation levels using a visible near-infrared spectrometer and chemometric methods. The samples consisted of 315 cacao beans obtained from 3 regions (Lampung, Makasar, and Kulon Progo) at 3 levels of fermentation (non, half, full). The calibration and prediction models were performed by PLS regression which involves X variables (Vis/NIR measurement results) and Y variable (pH and moisture content). Smoothing, normalization baseline correction, standard normal variate (SNV), and multiplicative scattered correction (MSC) were used for spectra pre-processing. The research showed that the MSC method resulted in the best model for pH with the correlation coefficient of calibration ( R C 2 ) and prediction ( R P 2 ) were 0.76 and 0.68, respectively. Original and MSC methods resulted in the best model for moisture content with the same value of R C 2 of 0.55 and R P 2 of 0.41. The results showed the capability of Vis/NIR spectroscopy and the important role of chemometrics in developing models for predicting cacao bean quality parameters during fermentation.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Methods for measuring the quality of cacao beans have been reported to be successful using colorimetry and near infra-red (NIR) spectroscopy [1,3]. Colorimetry is a method of applying eye functions to determine color parameters in visible light areas such as RGB, XYZ, L*a*b*, and L*C*h [4].…”

Section: Introductionmentioning

confidence: 99%

Determination of Acid Level (pH) and Moisture Content of Cocoa Beans at Various Fermentation Level Using Visible Near-Infrared (Vis-NIR) Spectroscopy

Priambodo

Saputro

Pahlawan

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…We are seeing substantial improvement in the efficiency of CV techniques (He et al, 2016;Howard et al, 2017;Zhang et al, 2018) and, at least for now, computational resources continue to become more affordable (Mack, 2011). As a result, CV is becoming available to whole industries, not just areas of highest commercial value; for example, ML has been used with increasing regularity for tasks specific to cocoa (Theobroma cacao L.), such as the exploration and optimisation of aroma profiles (Fuentes et al, 2019), monitoring of cocoa bean fermentation (Parra et al, 2018;Oliveira et al, 2021), and bean quality classification (Mite-Baidal et al, 2019). While large research and development budgets for areas such as wheat (Triticum aestivum L.) production have allowed for the use of unpiloted aerial vehicle photography to identify disease outbreaks (Su et al, 2018;Chiu et al, 2020) and the use of multispectral satellite photography to monitor outbreaks of yellow rust (Puccinia striiformis) from space (Nagarajan et al, 1984), the application of ML to sectors with fewer financial resources has had to take a different form.…”

mentioning

confidence: 99%

Computer vision for plant pathology: A review with examples from cocoa agriculture

Sykes,

Denby,

Franks

2023

Appl Plant Sci

View full text Add to dashboard Cite

Plant pathogens can decimate crops and render the local cultivation of a species unprofitable. In extreme cases this has caused famine and economic collapse. Timing is vital in treating crop diseases, and the use of computer vision for precise disease detection and timing of pesticide application is gaining popularity. Computer vision can reduce labour costs, prevent misdiagnosis of disease, and prevent misapplication of pesticides. Pesticide misapplication is both financially costly and can exacerbate pesticide resistance and pollution. Here, we review the application and development of computer vision and machine learning methods for the detection of plant disease. This review goes beyond the scope of previous works to discuss important technical concepts and considerations when applying computer vision to plant pathology. We present new case studies on adapting standard computer vision methods and review techniques for acquiring training data, the use of diagnostic tools from biology, and the inspection of informative features. In addition to an in‐depth discussion of convolutional neural networks (CNNs) and transformers, we also highlight the strengths of methods such as support vector machines and evolved neural networks. We discuss the benefits of carefully curating training data and consider situations where less computationally expensive techniques are advantageous. This includes a comparison of popular model architectures and a guide to their implementation.

show abstract

Content-Based Image Retrieval Framework for Classification of Cocoa Beans

Appiah

Martey

Ninfaakanga

et al. 2021

2021 IEEE 8th International Conference on Adaptive Science and Technology (ICAST)

View full text Add to dashboard Cite

Analysis of Computer Vision Algorithms to Determine the Quality of Fermented Cocoa (Theobroma Cacao): Systematic Literature Review

Cited by 4 publications

References 21 publications

Determination of Acid Level (pH) and Moisture Content of Cocoa Beans at Various Fermentation Level Using Visible Near-Infrared (Vis-NIR) Spectroscopy

Determination of Acid Level (pH) and Moisture Content of Cocoa Beans at Various Fermentation Level Using Visible Near-Infrared (Vis-NIR) Spectroscopy

Computer vision for plant pathology: A review with examples from cocoa agriculture

Content-Based Image Retrieval Framework for Classification of Cocoa Beans

Contact Info

Product

Resources

About