Automatic separation of overlapping seedlings by network optimization

Authors: Xu, L.; Fujimura, K.; McDonald, M.B.

Source: Seed Science and Technology, Volume 35, Number 2, July 2007 , pp. 337-350(14)

Publisher: International Seed Testing Association

Buy & download fulltext article:

OR

Price: $38.00 plus tax (Refund Policy)

Abstract:

A computer software approach was developed to automatically separate overlapping seedlings. The software took scanned images of germinated seedlings on a paper towel as input; measured an individual seedling's length and outputted an overall vigour index based on seedling length data. If overlapped seedlings were detected, an overlapping algorithm was activated to measure each seedling independently. The algorithm used concepts similar to network optimization algorithms in computer science to select the optimal solution. In this study, cotton seedlings were used to illustrate this approach, but the algorithm can also be applied to other crops as well.

Document Type: Research article

Publication date: 2007-07-01

More about this publication?
  • Seed Science and Technology (SST) is one of the leading international journals featuring original papers and review articles on seed quality and physiology as related to seed production, harvest, processing, sampling, storage, distribution and testing. This widely recognised journal is designed to meet the needs of researchers, advisers and all those involved in the improvement and technical control of seed quality.
  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Membership Information
  • ingentaconnect is not responsible for the content or availability of external websites
Related content

Tools

Key

Free Content
Free content
New Content
New content
Open Access Content
Open access content
Subscribed Content
Subscribed content
Free Trial Content
Free trial content

Text size:

A | A | A | A
Share this item with others: These icons link to social bookmarking sites where readers can share and discover new web pages. print icon Print this page