Project SmartKitchen/ Experiment 7: Second Image Provider: Difference between revisions
Jump to navigation
Jump to search
(content) |
(new hypothesis) |
||
Line 6: | Line 6: | ||
===Hypothesis:=== | ===Hypothesis:=== | ||
* We believe that if we | * We believe that if we introduce a vendor 2, it will be able to recognize 50% of the images (including packaged items) than vendor 1 | ||
===Experiment Steps:=== | ===Experiment Steps:=== |
Latest revision as of 19:45, 24 August 2016
Status: In Progress
Leap Of Faith Assumption (LOFA) We Are Testing:
- (I) We assume that we can identify some percentage of food via image recognition
Hypothesis:
- We believe that if we introduce a vendor 2, it will be able to recognize 50% of the images (including packaged items) than vendor 1
Experiment Steps:
- Give 3 internal Mozilla users (not on the team) our prototype device
- Have them sign up for a Kik account
- Instruct them on how to provision their wifi
- Have them try to identify items in their kitchen with the device when they are done with their shopping
- Collect metrics on the accuracy of the item identification
Experiment Timeline:
8/18-8/26 | Add second image provider |
8/18-8/26 | Save images |
08/26 | Update trial agreements to save images |
08/26 | Work with legal to incent participants |
8/26-9/2 | Fixup the Bot to handle both services |
8/19-8/26 | Recruit two new participants |
09/06 | Give devices out to new participants and update software remotely |
Experiment Details
- coming soon
Results
- coming soon