...
Subtasks: To accomplish this, users must first take a photo of the object they wish to identify. Next, the next annotate the object by drawing a box around the object of interest. After deploying modern computer vision algorithms, the product is identified from a massive database. The user is then shown a screen with the product information.
Preconditions: User is in a store.
Question 1: What is the best way for a user to annotate an object? Bounding box, ellipse, tapping, or enclosing hull?
...
Subtasks: Users again take a photos of the objects they want product information for. In order to specify which objects to compare, they must annotate multiple objects. After recognizing both objects, a comparison screen is shown.
Preconditions: User is in a store and has two products he is considering.
Question 3: What is the best way for a user to annotate multiple objects?
...
Subtasks: After our application recognizes the products, the user should be able to choose which sources are trustworthy for this particular product.
Preconditions: User is in a store, but has had bad experiences with reviews before.
Question 5: How do you instill confidence in users that the product results are unbiased?
...