Identifying products based on proportions of nearby bottles
A system for acquiring images of products in a retail store is disclosed. The system may include at least one first housing configured for location on a retail shelving unit, and at least one image capture device included in the at least one first housing and configured relative to the at least one first housing such that an optical axis of the at least one image capture device is directed toward an opposing retail shelving unit when the at least one first housing is fixedly mounted on the retail shelving unit. The system may further include a second housing configured for location on the retail shelving unit separate from the at least one first housing, the second housing may contain at least one processor configured to control the at least one image capture device and also to control a network interface for communicating with a remote server. The system may also include at least one data conduit extending between the at least one first housing and the second housing, the at least one data conduit being configured to enable transfer of control signals from the at least one processor to the at least one image capture device and to enable collection of image data acquired by the at least one image capture device for transmission by the network interface.
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 and a second product displayed thereon, wherein a type of the first product is different from a type of the second product;
analyze the image to detect a representation in the image of the first product, wherein the first product has an outline design;
determine a size of the first product;
determine a confidence level for the determined size;
when the confidence level does not meet a threshold, attempt to recognize the type of the first product based on at least one of a brand associated with the first product, a logo associated with the first product, text associated with the first product, a price associated with the first product, and a shape of the first product;
confirm the size of the first product based on the recognized type of the first product;
identify in the image two outline elements associated with the outline design of the first product, wherein each of the two outline elements has a specific length; and
determine a type of the second product based on a comparison of the lengths of the two outline elements.
2. The system of claim 1 , wherein the two outline elements are selected from a group including: a top of the first product, an orifice of the first product, a lip of the first product, a collar of the first product, a neck of the first product, a heel of the first product, and a base of the first product.
3. The system of claim 1 , wherein the at least one processor is further configured to determine the size of the first product based on a comparison of the lengths of the two outline elements.
4. The system of claim 3 , wherein the at least one processor is further configured to determine the size of the first product when at least 50% of the outline design of the first product is obscured.
5. The system of claim 3 , 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, wherein the group of outline elements comprises at least the two outline elements associated with the outline design of the first product; and
use a property of the distribution of the lengths of the group of outline elements to determine the size of the first product.
6. The system of claim 3 , wherein the at least one processor is further configured to:
when the confidence level does not meet 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
the confirmation of the size of the first product is further 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 first product.
7. The system of claim 3 , wherein the at least one processor is further configured to:
when the confidence level does not meet a predetermined threshold, identify another outline element of the first product, wherein the another outline element has a specific length; and
the confirmation of the size of the first product is further based on a comparison of the specific length of the another outline element of the first product and the length of one of the two outline elements of the first product.
8. The system of claim 3 , wherein the at least one processor is further configured to:
when the confidence level does not meet a predetermined 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
the confirmation of the size of the first product is further 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 first product.
9. The system of claim 1 , wherein:
the first product comprises a first item and a second item;
the image depicts the first item and the second item located adjacent each other; and
the first and second items are associated with a common brand, but wherein the first and second items have different sizes.
10. The system of claim 9 , wherein the at least one processor is further configured to determine a first size for the first item and a second size for the second item based on two outline elements associated with an outline design of the first item and two corresponding outline elements associated with an outline design of the second item.
11. The system of claim 9 , wherein the at least one processor is further configured to determine a first size for the first item and a second size for the second item based on two first outline elements associated with an outline design of the first item and two second outline elements associated with an outline design of the second item, wherein at least one of the first outline elements is different from the second outline elements.
12. The system of claim 9 , wherein the at least one processor is further configured to:
perform a first action associated with the first item; and
perform a second action associated with the second item, wherein the second action is different from the first action.
13. The system of claim 3 , 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 first product.
14. A method for processing images captured in a retail store, the method comprising:
receiving an image depicting a store shelf having a first product and a second product displayed thereon, wherein a type of the first product is different from a type of the second product;
analyzing the image to detect a representation in the image of the first product, wherein the first product has an outline design;
determining a size of the first product;
determining a confidence level for the determined size;
when the confidence level does not meet a threshold, attempting to recognize the type of the first product based on at least one of a brand associated with the first product, a logo associated with the first product, text associated with the first product, a price associated with the first product, and a shape of the first product;
confirming the size of the first product based on the recognized type of the first product;
identifying in the image two outline elements associated with the outline design of the first product, wherein each of the two outline elements has a specific length; and
determining a type of the second product based on a comparison of the lengths of the two outline elements.
15. The method of claim 14 , wherein the two outline elements are selected from a group including: an orifice of the first product, a lip of the first product, a collar of the first product, a neck of the first product, a heel of the first product, and a base of the first product.
16. The method of claim 14 , wherein determining size of the first product comprises:
analyzing the image to obtain a distribution of lengths of a group of outline elements, wherein the group of outline elements comprises at least the two outline elements associated with the outline design of the first product; and
using a property of the distribution of the lengths of the group of outline elements to determine the size of the first product.
17. 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 and a second product displayed thereon, wherein a type of the first product is different from a type of the second product;
analyzing the image to detect a representation in the image of the first product, wherein the first product has an outline design;
determining a size of the first product;
determining a confidence level for the determined size;
when the confidence level does not meet a threshold, attempting to recognize the type of the first product based on at least one of a brand associated with the first product, a logo associated with the first product, text associated with the first product, a price associated with the first product, and a shape of the first product;
confirming the size of the first product based on the recognized type of the first product;
identifying in the image two outline elements associated with the outline design of the first product, wherein each of the two outline elements has a specific length; and
determining a type of the second product based on a comparison of the lengths of the two outline elements.