Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
lindt:candybox:how_learning_works [2023/06/05 08:17]
superuser
lindt:candybox:how_learning_works [2023/06/05 08:59] (current)
superuser
Line 67: Line 67:
  
 When two candies are close to each other or touchng AI thinks that this is one single candy. This creates false-positives. To avoid this Voronoi segmentation is used. It puts virtual borders between candies ensuring that touching candies are separate. When two candies are close to each other or touchng AI thinks that this is one single candy. This creates false-positives. To avoid this Voronoi segmentation is used. It puts virtual borders between candies ensuring that touching candies are separate.
 +
 +{{:​lindt:​candybox:​9.png?​400|}}
  
 ==== 8. Color feature classification ==== ==== 8. Color feature classification ====
Line 73: Line 75:
  
 During analysis each candy is compared against database of patterns expected at specified position. If the distance is close enough - the candy is good. During analysis each candy is compared against database of patterns expected at specified position. If the distance is close enough - the candy is good.
 +
 +{{:​lindt:​candybox:​10.png?​400|}}
  
 ==== 9. Validation ==== ==== 9. Validation ====
  • lindt/candybox/how_learning_works.1685953030.txt.gz
  • Last modified: 2023/06/05 08:17
  • by superuser