Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Plant Genetics Research » Research » Publications at this Location » Publication #194397
Title: A FRAMEWORK OF COMPLEX QUERIES FOR PLANT PHENOTYPE IMAGE DATABASES

Author
item SHYU, CHI-REN - UNIVERSITY OF MISSOURI
item GREEN, JASON - UNIVERSITY OF MISSOURI
item FARMER, CYNTHIA - UNIVERSITY OF MISSOURI
item KAZIC, TONI - UNIVERSITY OF MISSOURI
item COE, EDWARD - RETIRED USDA-ARS
item Schaeffer, Mary
item Lawrence, Carolyn
item Millard, Mark
item Cyr, Pete
item Gardner, Candice

Submitted to: Plant and Animal Genome VX Conference Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 10/5/2005
Publication Date: 1/14/2006
Citation: Shyu, C., Green, J., Farmer, C., Kazic, T., Coe, E.H., Schaeffer, M.L., Lawrence, C.J., Millard, M.J., Cyr, P.D., Gardner, C.A. 2006. A framework of complex queries for plant phenotype image databases [abstract]. Plant and Animal Genome XIV: Final Abstract Guide. p. 875.

Interpretive Summary:

Technical Abstract: Discoveries in biology often require extensive knowledge of the genetics of an organism, a keen eye for phenotypes, a deep understanding of related species, and efficient strategies for collecting, combining, analyzing, and comparing data. Currently, public database tools that retrieve phenotypic and genomic information allow only relatively simplistic queries, and viable software tools to capture, parse, and return information from digital images are lacking. We hope to enable biologists to simultaneously query phenotype data by, e.g., image example, sequence, ontology, genetic and physical map information, and text annotations by developing the first Web-based visual phenotypic information management system to allow such complex queries. We anticipate that the database framework will consist of six modules: (1) a library of computer vision and image processing algorithms to extract and quantify low-level features from phenotype images; (2) a high-dimensional database indexing structure to manage and cluster images for real-time retrievals; (3) a linking hub to correlate visual features already attributed to a given locus with relevant genetic and physical maps; (4) a text mining and ontology utilization system to provide free text search; (5) a biometric information analysis and retrieval system; and (6) a results visualization system. Our test bed includes standardized images of whole maize ears, ear cross-sections, and kernels from the North Central Regional Plant Introduction Station (NCRPIS) under controlled environments and other images from MaizeGDB and the Germplasm Resource Information Network (GRIN). CRS, JG, and CF are supported by NSF CAREER Award grant #DBI-0447794.