Anatomical features of Fagaceae wood statistically extracted by computer vision approaches: Some relationships with evolution.

ABSTRACT: The anatomical structure of wood is complex and contains considerable information about its specific species, physical properties, growth environment, and other factors. While conventional wood anatomy has been established by systematizing the xylem anatomical features, which enables wood identification generally up to genus level, it is difficult to describe all the information comprehensively. This study apply two computer vision approaches to optical micrographs: the scale-invariant feature transform algorithm and connected-component labelling. They extract the shape and pore size information, respectively, statistically from the whole micrographs. Both approaches enable the efficient detection of specific features of 18 species from the family Fagaceae. Although the methods ignore the

SUBMITTER: Kobayashi K 

PROVIDER: S-EPMC6690550 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature