SciELO

A multiple model machine learning approach for soil classification from cone penetration test data

The most popular methods for soil classification from cone penetration test (CPT) data are based on examining two-dimensional charts. In the last years, several authors have dedicated efforts on ...
GitHub

Swin-chart: An efficient approach for chart classification

Swin-Chart is a Swin Transformer-based model for chart classification across various datasets. It achieved first place in the chart classification task at the ICDAR 2023 CHART Infographics competition ...
Minnesota Daily

Camera traps in Serengeti provide wild animal classifications, public learning opportunities

A University of Minnesota study turned citizen science revolution, Snapshot Serengeti, developed into a database that aids in wild animal classification. Alexandra Swanson, a postdoctoral fellow at ...
IEEE

Supervised and unsupervised learning in animal classification

Abstract: In this work, we have developed a supervised and unsupervised based classification system to classify the animals. Initially, the animal images are segmented using maximal region merging ...
IEEE

Recognition and classification of animals based on texture features through parallel computing

Abstract: In this work, we proposed an efficient system for animal recognition and classification based on texture features which are obtained from the local appearance and texture of animals. The ...
Marine Link

Lloyd’s Register, Latsco Chart New Digital Course for Ship Classification

Lloyd’s Register (LR) and Latsco have successfully completed a proof-of-concept for a new standard in digital class assurance with data-driven surveys. This collaboration aims to demonstrate how ...