Browse
Submit Data
Databases
API
Help

Dataset Information

28 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Image datasets of cocoa beans for taxonomy nuances evaluation.

ABSTRACT: There are some classification methods that generate nuances in the final accuracy caused by objects positioning, framing and damage. These occurrences may result in a drop of accuracy in computer vision systems that were trained with structured static datasets and are intended to be used in day-to-day applications in which the images are not always as organized as the trained dataset, like some biometric classification systems such as iris and fingerprint. In this regard, this paper presents six image datasets processed with different methods to help researchers analyze the impact of object positioning, framing and damage in their taxonomies.

SUBMITTER: Santos FA

PROVIDER: S-EPMC6838416 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Image datasets of cocoa beans for taxonomy nuances evaluation.

Santos F A FA Palmeira E S ES Jesus G Q GQ

Data in brief 20191015

There are some classification methods that generate nuances in the final accuracy caused by objects positioning, framing and damage. These occurrences may result in a drop of accuracy in computer vision systems that were trained with structured static datasets and are intended to be used in day-to-day applications in which the images are not always as organized as the trained dataset, like some biometric classification systems such as iris and fingerprint. In this regard, this paper presents six ...[more]

PMID: 31720322

Similar Datasets

An image dataset of cut-test-classified cocoa beans.

Project description:Classifying cocoa beans, considering some specific standards, is required and regulated around the world, if commercialization is intended, or it can be very useful, in order to select the best ones for a given proposal. This article presents an image dataset of cut test classified cocoa beans, provided by experts following the Brazilian regulative norm for that process. Fourteen classes, with 100 images for each, were registered in a device designed with standard constant artificial lighting and capturing settings and will be present in this paper. Images are hosted in the Núcleo de Biologia Computacional from Universidade Estadual de Santa Cruz, under the "tedais" name.

| S-EPMC6484946 | biostudies-literature

Analytical dataset of Ecuadorian cocoa shells and beans.

Project description:Full analytical data of Ecuadorian cocoa wastes (raw shells) and beans (as benchmark), are herein reported. A detailed characterization of production residues may pave the road to a zero-waste strategy for the cocoa industry. Multiple analytical techniques have been exploited to define the composition of the matrices, among them: elemental analyses, FTIR, Py-GC/MS/FID and UHPLC-ESI-MS/MS. Quali-quantitative data of carbohydrates, lipids, lignin, polyphenols, alkaloids and proteins have been obtained by Py-GC/MS/FID and UHPLC-ESI-MS/MS. Assignations are fully supported by literature references. The FAMEs composition of lipophilic UAE extract is also reported for sake of comparison with cocoa butter. This data collection completes a wider valorization work, "Cocoa bean shell waste valorisation; extraction from lab to pilot-scale cavitational reactors" (Grillo et al., 2018).

| S-EPMC6297061 | biostudies-literature

Molecular Changes during Germination of Cocoa Beans, Part 1.

Project description:Some germination is known to occur during the process of fermentation in cocoa beans. The impact of this biological process on the course of cocoa fermentation is not known and was thus investigated. In order to determine the impact of germination at the molecular level as well as on flavor, an untargeted metabolomics approach using Ultra Performance Liquid Chromatography-Electrospray Ionization-Time of Flight-Mass Spectrometry (UPLC-ESI-ToF-MS) with simultaneous acquisition of low- and high-collision energy mass spectra (MSe) was performed. Extracts of raw and germinated cocoa beans of the same origin were measured and compared for characteristic differences by unsupervised principal component analysis. OPLS-DA revealed 12-hydroxyjasmonic acid (HOJA) sulfate, (+)-catechin and (-)-epicatechin as most down-regulated compounds as well as two hydroxymethylglutaryl (HMG) glucosides A and B among others as decisive up-regulated compounds in the germinated material. Additionally, further HMG glucosides and 12-hydroxyjasmonic acid could be identified in cocoa for the first time by coelution with isolated and synthesized reference compounds. HOJA sulfate, which has been postulated in cocoa, and HOJA were revealed to impart bitter and astringent taste qualities.

| S-EPMC11342359 | biostudies-literature

Molecular Changes during Germination of Cocoa Beans, Part 2.

Project description:A recently published untargeted metabolomics approach toward marker compounds of cocoa germination revealed and identified 12-hydroxyjasmonic acid sulfate, (+)-catechin, and (-)-epicatechin as the most downregulated compounds and two hydroxymethylglutaryl glucosides (HMG gluc) A and B, among others, as the decisive upregulated compounds in the germinated material. These findings were quantitatively evaluated using ultrahigh-performance liquid chromatography-tandem mass spectrometry not only in previously examined sample material but also in a vastly expanded array of cocoa samples of different provenience and process and in cocoa products such as cocoa liquor and chocolate. Hereby, yields of newly identified HMG gluc derivatives could be determined in raw, fermented, germinated, and alternatively processed cocoa, and isomers of HMG gluc A and B could be established as key process indicators. Based on unsupervised clustering and supervised classification, models could identify germinated samples in testing sets consisting of raw, fermented, and germinated samples.

| S-EPMC11311213 | biostudies-literature

Microbiota dynamics and diversity at different stages of industrial processing of cocoa beans into cocoa powder.

Project description:We sampled a cocoa powder production line to investigate the impact of processing on the microbial community size and diversity at different stages. Classical microbiological methods were combined with 16S rRNA gene PCR-denaturing gradient gel electrophoresis, coupled with clone library construction, to analyze the samples. Aerobic thermoresistant spores (ThrS) (100°C; 10 min) were also isolated and characterized (identity, genetic diversity, and spore heat resistance), in view of their relevance to the quality of downstream heat-treated cocoa-flavored drinks. In the nibs (broken, shelled cocoa beans), average levels of total aerobic microorganisms (TAM) (4.4 to 5.6 log CFU/g) and aerobic total spores (TS) (80°C; 10 min; 4.3 to 5.5 log CFU/g) were significantly reduced (P < 0.05) as a result of alkalizing, while fungi (4.2 to 4.4 log CFU/g) and Enterobacteriaceae (1.7 to 2.8 log CFU/g) were inactivated to levels below the detection limit, remaining undetectable throughout processing. Roasting further decreased the levels of TAM and TS, but they increased slightly during subsequent processing. Molecular characterization of bacterial communities based on enriched cocoa samples revealed a predominance of members of the Bacillaceae, Pseudomonadaceae, and Enterococcaceae. Eleven species of ThrS were found, but Bacillus licheniformis and the Bacillus subtilis complex were prominent and revealed great genetic heterogeneity. We concluded that the microbiota of cocoa powder resulted from microorganisms that could have been initially present in the nibs, as well as microorganisms that originated during processing. B. subtilis complex members, particularly B. subtilis subsp. subtilis, formed the most heat-resistant spores. Their occurrence in cocoa powder needs to be considered to ensure the stability of derived products, such as ultrahigh-temperature-treated chocolate drinks.

| S-EPMC3318835 | biostudies-literature

Assessment of greenhouse technologies on the drying behavior of cocoa beans.

Project description:Cocoa beans (Theobroma cacao L.) are the principal raw material for chocolate manufacture. Before cocoa beans are ready for the chocolate industry, farm-based fermentation and drying processes are key determinants of bean quality and hence the price. To improve its value, cocoa beans were dried in a modified greenhouse (MGHD), conventional greenhouse (CGHD), and open sun (OSD) dryers. The drying behavior, kinetics, and quality were evaluated. The MGHD was constructed by modifying a conventional greenhouse with a fleece of black polyester material. Evaluation of air properties of the dryers without and with cocoa beans showed that the MGHD had average temperatures of 2 and 8°C above, and relative humidity of 12.28% and 25.48% below the CGHD and OSD, respectively. The drying data were fitted to four thin layer mathematical models. The Page and Overhult models gave favorable ranges of R 2 (.976 to .987), chi-square (3.7 × 10-4 to 9.9 × 10-4), and root mean square (RMSE; 0.0188 to 0.0307) for the three dryers. The cocoa beans dried in the MGHD took a shorter time to reach the expected 5%-8% moisture content and were of grade one quality.

| S-EPMC7300052 | biostudies-literature

Total lipid prediction in single intact cocoa beans by hyperspectral chemical imaging.

Project description:This work aimed to explore the possibility of predicting total fat content in whole dried cocoa beans at a single bean level using hyperspectral imaging (HSI). 170 beans randomly selected from 17 batches were individually analysed by HSI and by reference methodology for fat quantification. Both whole (i.e. in-shell) beans and shelled seeds (cotyledons) were analysed. Partial Least Square (PLS) regression models showed good performance for single shelled beans (R2 = 0.84, external prediction error of 2.4%). For both in-shell beans a slightly lower prediction error of 4.0% and R2 = 0.52 was achieved, but fat content estimation is still of interest given its wide range. Beans were manually segregated, demonstrating an increase by up to 6% in the fat content of sub-fractions. HSI was shown to be a valuable technique for rapid, non-contact prediction of fat content in cocoa beans even from scans of unshelled beans, enabling significant practical benefits to the food industry for quality control purposes and for obtaining a more consistent raw material.

| S-EPMC7814379 | biostudies-literature

Functional Biodiversity of Yeasts Isolated from Colombian Fermented and Dry Cocoa Beans.

Project description:Yeasts play an important role in the cocoa fermentation process. Although the most relevant function is the degradation of sugars and the production of ethanol, there is little understanding of the enzyme activities and attributes that allow them to survive even after drying. The present study explored the functional biodiversity of yeasts associated with Criollo Colombian cocoa fermented beans, able to survive after drying. Twelve species belonging to 10 genera of osmo-, acid-, thermo-, and desiccation-tolerant yeasts were isolated and identified from fermented and dry cocoa beans, with Pichia kudriavzevii and Saccharomyces cerevisiae standing out as the most frequent. For the first time, we reported the presence of Zygosaccharomyces bisporus in cocoa fermented beans. It was found that resistance to desiccation is related to the different degradation capacities of fermentation substrates, which suggests that associative relationships may exist between the different yeast species and their degradation products. Besides, the increased thermotolerance of some species was related to the presence of polyphenols in the medium, which might play a fundamental role in shaping the microbial community composition.

| S-EPMC7409280 | biostudies-literature

Yeast metagenome (26S) from fermented cocoa beans

Project description:Yeast metagenome (26S) from fermented cocoa beans

| PRJNA475867 | ENA

Vehicle image datasets for image classification.

Project description:Vehicle image recognition is a critical research area with diverse traffic management, surveillance, and autonomous driving systems applications. Accurately classifying and identifying vehicles from images play a crucial role in these domains. This work presents two vehicle image datasets: the vehicle type image dataset version 2 (VTID2) and the vehicle make image dataset (VMID). The VTID2 Dataset comprises 4,356 images of Thailand's five most used vehicle types, which enhances diversity and reduces the risk of overfitting problems. This expanded dataset offers a more extensive and varied collection for robust model training and evaluation. This dataset will be valuable for researchers focusing on vehicle image recognition tasks. With an emphasis on sedans, hatchbacks, pick-ups, SUVs, and other vehicles, the dataset allows for developing and evaluating algorithms that accurately classify different types of vehicles. The VMID Dataset contains 2,072 images of logos (called vehicle make) from eleven prominent vehicle brands in Thailand. The proposed dataset will facilitate the development of computer vision algorithms and the evaluation of learning algorithm model performance metrics. These two datasets provide valuable resources to the research community that will foster possible research advancements in vehicle recognition, vehicle logo detection or localization, and vehicle segmentation, contributing to the development of intelligent transportation systems.

| S-EPMC10859268 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data