NOA: A Search Engine for Reusable Scientific Images Beyond the Life Sciences

Abstract

NOA is a search engine for scientific images from open access publications based on full text indexing of all text referring to the images and filtering for disciplines and image type. Images will be annotated with Wikipedia categories for better discoverability and for uploading to WikiCommons. Currently we have indexed approximately 2,7 Million images from over 710 000 scientific papers from all fields of science.

Predicting Word Concreteness and Imagery

“…A practical application, that in fact was our initial motivation for this research, is the annotation of images (Charbonnier et al, 2018). We need to find terms in the caption (and surrounding text) of an image that describe that image.…”

SlideImages: A Dataset for Educational Image Classification

“…Prior information retrieval publications have used, or could make use of, document figure classification. Charbonnier et al [6] built a search engine which allows user to filter images based on type, Aletras & Mittal [7] automatically label topics in photos, Kembhavi et al [8] build a system for extracting the relationships between entities in a diagram, which assumes that the input figure is a diagram, Hiippala & Orekhova extended their dataset by annotating it semantically in terms of Relational Structure Theory, which implies that the same visual features communicate the same semantic relationships, and de Herrera et al [9] seek to classify image types to filter their search for medical professionals.…”

Delineating Knowledge Domains in the Scientific Literature Using Visual Information

“…DiagramFlyer [7], introduced by Chen et al, is a search engine for data-driven diagrams. VizioMetrix [27] and NOA [6] are both scienti c gures search engines with big scholar data, while they both work by examining the captions around the gures. We see visual-based models for demarcating knowledge domains as a next step in this area of research.…”