Dataset Information

Low-Cost Prototype to Automate the 3D Digitization of Pieces: An Application Example and Comparison.

ABSTRACT: This work is aimed at describing the design of a mechanical and programmable 3D capturing system to be used by either 3D scanner or DSLR camera through photogrammetry. Both methods are widely used in diverse areas, from engineering, architecture or archaeology, up to the field of medicine; but they also entail certain disadvantages, such as the high costs of certain equipment, such as scanners with some precision, and the need to resort to specialized operatives, among others. The purpose of this design is to create a robust, precise and cost-effective system that improves the limitations of the present equipment on the market, such as robotic arms or rotary tables. For this reason, a preliminary study has been conducted to analyse the needs of improvement, later, we have focused on the 3D design and prototyping. For its construction, there have been used the FDM additive technology and structural components that are easy to find in the market. With regards to electronic components, basic electronics and Arduino-based 3D printers firmware have been selected. For system testing, the capture equipment consists of a Spider Artec 3D Scanner and a Nikon 5100 SLR Camera. Finally, 3D models have been developed by comparing the 3D meshes obtained by the two methods, obtaining satisfactory results.

SUBMITTER: Gonzalez-Merino R

PROVIDER: S-EPMC8067622 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Low-Cost Prototype to Automate the 3D Digitization of Pieces: An Application Example and Comparison.

González-Merino Ramón R Sánchez-López Elena E Romero Pablo E PE Rodero Jesús J Hidalgo-Fernández Rafael E RE

Sensors (Basel, Switzerland) 20210407 8

This work is aimed at describing the design of a mechanical and programmable 3D capturing system to be used by either 3D scanner or DSLR camera through photogrammetry. Both methods are widely used in diverse areas, from engineering, architecture or archaeology, up to the field of medicine; but they also entail certain disadvantages, such as the high costs of certain equipment, such as scanners with some precision, and the need to resort to specialized operatives, among others. The purpose of thi ...[more]

PMID: 33916989

Similar Datasets

Project description:BackgroundEvidence-based medicine requires synthesis of research through rigorous and time-intensive systematic literature reviews (SLRs), with significant resource expenditure for data extraction from scientific publications. Machine learning may enable the timely completion of SLRs and reduce errors by automating data identification and extraction.MethodsWe evaluated the use of machine learning to extract data from publications related to SLRs in oncology (SLR 1) and Fabry disease (SLR 2). SLR 1 predominantly contained interventional studies and SLR 2 observational studies. Predefined key terms and data were manually annotated to train and test bidirectional encoder representations from transformers (BERT) and bidirectional long-short-term memory machine learning models. Using human annotation as a reference, we assessed the ability of the models to identify biomedical terms of interest (entities) and their relations. We also pretrained BERT on a corpus of 100,000 open access clinical publications and/or enhanced context-dependent entity classification with a conditional random field (CRF) model. Performance was measured using the F1 score, a metric that combines precision and recall. We defined successful matches as partial overlap of entities of the same type.ResultsFor entity recognition, the pretrained BERT+CRF model had the best performance, with an F1 score of 73% in SLR 1 and 70% in SLR 2. Entity types identified with the highest accuracy were metrics for progression-free survival (SLR 1, F1 score 88%) or for patient age (SLR 2, F1 score 82%). Treatment arm dosage was identified less successfully (F1 scores 60% [SLR 1] and 49% [SLR 2]). The best-performing model for relation extraction, pretrained BERT relation classification, exhibited F1 scores higher than 90% in cases with at least 80 relation examples for a pair of related entity types.ConclusionsThe performance of BERT is enhanced by pretraining with biomedical literature and by combining with a CRF model. With refinement, machine learning may assist with manual data extraction for SLRs.

Dataset Information

Low-Cost Prototype to Automate the 3D Digitization of Pieces: An Application Example and Comparison.

Publications

Low-Cost Prototype to Automate the 3D Digitization of Pieces: An Application Example and Comparison.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets