Identifying bottle sizes based on bottle proportions

1. A system for processing images captured in a retail store, the system comprising:

at least one processor configured to:

receive an image depicting a store shelf having a first product comprising at least one bottle and a second product displayed thereon, a type of the first product being different from a type of the second product;

analyze the image to detect a representation in the image of the at least one bottle, wherein the at least one bottle has an outline design;

identify in the image two outline elements being associated with the outline design of the at least one bottle, wherein each of the two outline elements has a specific length;

determine a size of the at least one bottle of the first product based on a comparison of the lengths of the two outline elements; and

determine, based on the determined sized of the at least one bottle of the first product, a type of the second product.

2. The system of claim 1 , wherein the two outline elements are selected from a group including: a top of a bottle, an orifice of the bottle, a lip of the bottle, a collar of the bottle, a neck of the bottle, a heel of the bottle, and a base of the bottle.

3. The system of claim 1 , wherein the at least one processor is further configured to determine the size of a bottle when at least 50% of the outline design of the bottle is obscured.

4. The system of claim 1 , wherein the at least one processor is further configured to determine a product type of the at least one bottle based on the determined size.

5. The system of claim 1 , wherein the at least one processor is further configured to:

analyze the image to obtain a distribution of lengths of a group of outline elements, the group of outline elements comprising at least the two outline elements associated with the outline design of the at least one bottle; and

use a property of the distribution of the lengths of the group of outline elements to determine the size of the at least one bottle.

6. The system of claim 1 , wherein the at least one processor is further configured to:

determine a confidence level for the determined size;

when the confidence level is below a predetermined threshold, analyze the image to identify another product on the store shelf, wherein the other product includes another outline element associated with a specific length; and

confirm the size of the bottle based on a comparison of the specific length of the other outline element of the other product and the length of one of the two outline elements of the at least one bottle.

7. The system of claim 1 , wherein the at least one processor is further configured to:

determine a confidence level for the determined size;

when the confidence level is below a threshold, identify another outline element of the at least one bottle, the other outline element having a specific length; and

confirm the size of the bottle based on a comparison of the specific length of the other outline element of the at least one bottle and the length of one of the two outline elements of the at least one bottle.

8. The system of claim 1 , wherein the at least one processor is further configured to:

determine a confidence level for the determined size;

when the confidence level is below a threshold, analyze the image to identify a label attached to the store shelf, wherein the label includes a textual element associated with a specific length; and

confirm the size of the bottle based on a comparison of the specific length of the textual element of the label and the length of one of the two outline elements of the at least one bottle.

9. The system of claim 1 , wherein the image depicts a first bottle and a second bottle located adjacent each other, wherein the first and second bottles are associated with a common brand, but wherein the first and second bottles have different sizes.

10. The system of claim 9 , wherein the at least one processor is further configured to use a same two outline elements for the first and second bottles to determine a first product size for the first bottle and a second product size for the second bottle differs than the first product size.

11. The system of claim 5 , wherein the at least one processor is further configured to use a Fano factor of the distribution of the lengths of the group of outline elements to determine the size of the at least one bottle.

12. The system of claim 9 , wherein the at least one processor is further configured to use different two outline elements for the first and second bottles to determine a first product size for the first bottle and a second product size for the second bottle differs than the first product size.

13. The system of claim 9 , wherein the at least one processor is further configured to:

perform a first action associated with the first bottle; and

perform a second action associated with the second bottle, wherein the second action differs from the first action when the determined size of the second bottle differs from the determined size of the first bottle.

14. The system of claim 1 , wherein the at least one processor is further configured to determine a product type of the at least one bottle based on the determined size of the at least one bottle and at least one of: a brand associated with the at least one bottle, a logo associated with the at least one bottle, text associated with the at least one bottle, a price associated with the at least one bottle, and a shape of the at least one bottle.

15. A method for processing images captured in a retail store, the method comprising:

receiving an image depicting a store shelf having a first product comprising at least one bottle and a second product displayed thereon, a type of the first product being different from a type of the second product;

analyzing the image to detect a representation in the image of the at least one bottle, wherein the bottle has an outline design;

identifying in the image two outline elements being associated with the outline design of the at least one bottle, wherein each of the two outline elements has a specific length;

determining a size of the at least one bottle of the first product based on a comparison of the lengths of the two outline elements; and

determining, based on the determined sized of the at least one bottle of the first product, a type of the second product.

16. The method of claim 15 , wherein the two outline elements are selected from a group including: an orifice of a bottle, a lip of the bottle, a collar of the bottle, a neck of the bottle, a heel of the bottle, and a base of the bottle.

17. The method of claim 15 , further comprising:

determining a product type of the at least one bottle based on the determined size.

18. The method of claim 15 , further comprising:

analyzing the image to obtain a distribution of lengths of a group of outline elements, the group of outline elements comprising at least the two outline elements associated with the outline design of the at least one bottle; and

using a property of the distribution of the lengths of the group of outline elements to determine the size of the at least one bottle.

19. The method of claim 15 , further comprising:

determining a confidence level for the determined size;

when the confidence level is below a threshold, attempt to recognize the product type of the at least one bottle based on at least one of: a brand associated with a detected bottle, a logo associated with the detected bottle, text associated with the detected bottle, a price associated with the bottle, and a shape of the detected bottle; and

confirm the size of the detected bottle based on the product type.

20. A computer program product for processing images captured in a retail store embodied in a non-transitory computer-readable medium and executable by at least one processor, the computer program product including instructions for causing the at least one processor to execute a method comprising:

receiving an image depicting a store shelf having a first product comprising at least one bottle and a second product displayed thereon, a type of the first product being different from a type of the second product;

analyzing the image to detect a representation in the image of the at least one bottle, wherein the at least one bottle has an outline design;

identifying in the image two outline elements being associated with the outline design of the at least one bottle, wherein each of the two outline elements has a specific length;

determining a size of the at least one bottle of the first product based on a comparison of the lengths of the two outline elements; and

determining, based on the determined sized of the at least one bottle of the first product, a type of the second product.