Constructing Self-Labeled Materials Imaging Datasets from Open Access Scientific Journals with EXSCLAIM!
- Argonne National Lab. (ANL), Argonne, IL (United States); Northwestern Univ., Evanston, IL (United States)
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Northwestern Univ., Evanston, IL (United States)
Due to recent improvements in image resolution and acquisition speeds, materials microscopy is experiencing an explosion in imaging data. Yet, despite the volume of images generated, the overall accessibility landscape is highly fragmented, as researchers who do release images to the public, often only do so as snapshots of their larger private dataset in context of scientific journal publications. The effort to automatically consolidate images and descriptive information from web-based platforms has garnered broad attention from the computer vision, language technologies, and chemistry/materials informatics communities. However, these methods are problematic for scientific figures because over 30% of figures are compound in nature, and it is the individual images themselves, paired with relevant context, that are necessary for construction a proper labeled dataset. To this end, we outline in this paper the design of a software pipeline for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific figures (EXSCLAIM!). Successful consolidation of materials imaging across literature sources will enhance navigation and searchability of materials microscopy images for both novice and experienced researchers, as well as establish the framework necessary for users to search by images, text, or some combination of both.
- Research Organization:
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Laboratory Directed Research and Development (LDRD) Program
- Grant/Contract Number:
- AC02-06CH11357
- OSTI ID:
- 1756073
- Journal Information:
- Microscopy and Microanalysis, Vol. 26, Issue S2; ISSN 1431-9276
- Publisher:
- Microscopy Society of America (MSA)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Harvesting Image Databases from the Web
|
journal | April 2011 |
OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning
|
journal | July 2009 |
In-plane Aligned Colloidal 2D WS2 Nanoflakes for Solution-Processable Thin Films with High Planar Conductivity
|
journal | June 2019 |
Similar Records
Automated Cache Performance Analysis And Optimization
Preparing PNNL Reports with LaTeX