Dataset Information

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

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

Project description:Forastero hybrid cocoa bean fermentations have been carried out in a box (B) and in a heap (H), with or without the inoculation of Saccharomyces cerevisiae and Torulaspora delbrueckii as starter cultures. The bacteria, yeasts, and microbial metabolites (volatile and nonvolatile organic compounds) were monitored during fermentation to assess the connection between microbiota and the release of metabolites during this process. The presence of starter cultures was detected, by means of culture-dependent analysis, during the first 2 days of both fermentations. However, no statistical difference was observed in any of the physicochemical or microbiological analyses. Plate counts revealed the dominance of yeasts at the beginning of both fermentations, and these were followed by acetic acid bacteria (AAB) and lactic acid bacteria (LAB). Hanseniaspora opuntiae, S. cerevisiae, Pichia pijperi, Acetobacter pasteurianus, and Lactobacillus fermentum were the most abundant operational taxonomic units (OTUs) during both fermentation processes (B and H), although different relative abundances were observed. Only the diversity of the fungal species indicated a higher level of complexity in the B fermentations than in the H fermentations (P < 0.05), as well as a statistically significant difference between the initially inoculated starter cultures (P < 0.01). However, the microbial metabolite analysis indicated different distributions of the volatile and nonvolatile compounds between the two procedures, that is, B and H (P < 0.05), rather than between the inoculated and noninoculated fermentations. The box fermentations showed faster carbohydrate metabolism and greater production of organic acid compounds, which boosted the formation of alcohols and esters, than did the heap fermentations. Overall, the microbial dynamics and associations between the bacteria, yeasts, and metabolites were found to depend on the type of fermentation.IMPORTANCE In spite of the limited effectiveness of the considered inoculated starter strains, this study provides new information on the microbial development of box and heap cocoa fermentations, under inoculated and noninoculated conditions, as we coupled yeast/bacterial amplicon-based sequencing data with microbial metabolite detection. The information so far available suggests that microbial communities have played an important role in the evolution of aroma compounds. Understanding the pathways that microorganisms follow during the formation of aromas could be used to improve the fermentation processes and to enhance chocolate quality.

Dataset Information

Image datasets of cocoa beans for taxonomy nuances evaluation.

Publications

Image datasets of cocoa beans for taxonomy nuances evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure