Soybean seeds selection based on computer vision

Runtao Wang, Changli Zhang, Junlong Fang, Shuwen Wang, Fang Yang, Lei Tian

Research output: Contribution to journalArticlepeer-review


To achieve the design of soybean selected model, the normal soybean, gray spot soybean, moldy soybean and worm-eaten soybean were chosen from the three kinds of soybean, (DongNong 405, DongNong 410, DongNong 634). The soybean images were obtained and analyzed with the intelligent camera working without PC. The 15 characteristic parameters of soybean image, such as shape, color and texture were extracted by means of separating the soybean and background with dynamic threshold separation algorithm. The average recognition accuracy of model reached 98% by building the BP neutral network classification model. The 2000 soybeans were used to test of selected device and the test results showed that the selected accuracy of normal soybean, gray spot soybean, moldy soybean and worm-eaten soybean were 98.3%, 93.4%, 92.2% and 95.9%, respectively. The selection rate was 300 per minute. Soybean selected device with machine vision technology was feasible.

Original languageEnglish (US)
Pages (from-to)355-359
Number of pages5
JournalNongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering
Issue number8
StatePublished - Aug 1 2011


  • BP neutral network
  • Computer vision
  • Image processing
  • Models
  • Soybean
  • Winnow

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Soybean seeds selection based on computer vision'. Together they form a unique fingerprint.

Cite this