Differences

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

--- lindt:candybox:how_learning_works [2021/03/10 09:39]
superuser created
+++ lindt:candybox:how_learning_works [2023/06/05 08:59] (current)
superuser
@@ Line 6: / Line 6: @@
 ===== Day 1 =====
 ==== 1. Annotation ====
@@ Line 18: / Line 19: @@
 After the job is done i'm inspecting the images.
-{{ :lindt:candybox:1.gif?400 |}}
+{{ :lindt:candybox:1.gif |}}
+==== 2. Augmentation ====
+Just 15 images is not enough fo AI to understand all concepts of what candy is. So i'm using quite standard trick to extend the data set.
+To do that i'm addig small rotation in both directions. Together with "empty" images(with empty blister and truned over candies) this will generate a dataset of about 300 images(black images are masks with candy position and class, windows can't decode them propperly):
+{{ :lindt:candybox:2.png?nolink |}}
+==== 3. Learning ====
+After dataset is prepared the learning process starts. This takes about 6 hours. All this time i need to monitor the results. If AI learning not correctly i need to interrupt it, correct some parameters and arestart learning process.
+{{ :lindt:candybox:3.gif?nolink |}}
+==== 4. Monitoring ====
+Inavoidable part of learning process. As AI learns it tries to find relation between pixels on screen and masks drawn by student.
+If concept is understood incorrectly - most likely there is an error at annotation, dataset balance or model needs to be tweeked. If this happens - learning process must be restarted anfter problem is eliminated.
+{{ :lindt:candybox:4.gif?nolink |}}
+===== Day 2 =====
+==== 5. Recipe creation ====
+You can think of recipe as of some program that can work with only one type of blister. Recipes are done in separate programs for multiple reasons:
+  * stability. if there is a critical error in recipe this will not brake other recipes
+  * experiments. recipes can be made differently. this allows to experiment quicly with different models and approaches
+  * modularity. recipes can be added or deleted without modification of program itself
+Recipe is created from some sort of template. And in initial stage it's quite 'stupid' and can't even find a blister on image.
+{{ :lindt:candybox:5.png?nolink |}}
+==== 6. Configuration ====
+The goal of this step is to establish relation between blister position/angle and candy positions.
+After playing around with thansformation matrices i get result similar to this:
+{{ :lindt:candybox:5.1.png?nolink |}}
+These records are describing where candy is located, what type it is and what its size.
+If this 'table' is built correctly i will get something like this:
+{{ :lindt:candybox:6.png?nolink |}}
+==== 7. Voronoi segmentation ====
+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 ====
+Each candy is having different amount of different colors. This makes possible to generate a color combination pattern for each candy type for each candy position. But since each candy type may have variations - we are creating a database which contains several patterns for each candy type.
+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 ====
+Now it's time to test the recipe on good images that it's never seen. They should be all green:
+{{ :lindt:candybox:7.gif?nolink |}}
+==== 10. Coverage checking ====
+The last step before it's done. On this step i'm checking how confident AI about it's decisions.
+This allows to discover if there is possible problems with recognition on the line.
+{{ :lindt:candybox:8.gif?nolink |}}