People

• YoungJeansKR
• haen-su
• ch9eri

Language / IDE

• 
• 
• 
• 
• 
• 
• 
• 

Dataset

• 2140 images
• 2140 xml files

Model

• YOLO (You Only Look Once)
  • View the entire image only once
  • Region proposal, Feature extraction, Classification, Bbox regression
  • Because it learns surrounding information and processes the entire image, less background error
  • High detection accuracy even for new images not seen in the training phase

Result

• plate: 89%