Garment size mapping
Techniques for mapping size information associated with a client to target brands, garments, sizes, shapes, and styles for which there is no standardized correlation. The size information associated with a client may be generated by modeling client garments, accessing computer aided drawing (CAD) files associated with client garments, or by analyzing a history of garment purchases associated with the client. Information for target garments may be generated in a similar fashion. A system may then create a standardized scale with a set of sizes for a target, and map a client base size to that standardized size scale. Similar matching and mapping may also be done with shape and style considerations. A recommendation based on the mapping may then be communicated to the client.
1. A computer implemented method, comprising one or more computers executing the following steps:
receiving, from a user device, a match request comprising a preference of a user and a base client size of the user;
identifying, based on analyzing a garment database, one or more matching garments having a threshold level of similarity to the preference of the user;
generating, using a boundary detection algorithm, one or more three-dimensional garment models for at least one matching garment of the one or more matching garments by:
comparing respective pixel values of each pixel in an image of the at least one matching garment to a boundary threshold value;
detecting, within the image, at least one boundary comprising a set of pixels that satisfy the boundary threshold value; and
joining a set of vertices corresponding to the set of pixels to obtain at least one partial shape of the at least one matching garment, wherein the one or more three-dimensional garment models include the at least one partial shape;
generating, using a standardized size scale and the one or more three-dimensional garment models, a size map of the base client size to a set of target garment sizes;
generating, based on the size map and the one or more matching garments, a match communication indicating:
information associated with the one or more matching garments and, for each matching garment of the one or more matching garments, a match value indicating how closely the matching garment matches the preference of the user, and
a target garment size, from the set of target garment sizes, having a closest match to the base client size; and causing
communication, to the user device, of the match communication.
2. The computer implemented method of claim 1 , further comprising: receiving, from the user device, an indication of a selection of a first matching garment, of the one or more matching garments, in the target garment size; and initiating, in response to the indication of the selection, an order of the first matching garment in the target garment size.
3. The computer implemented method of claim 1 , wherein the match request indicates a target geographical region, and wherein the one or more matching garments originates from the target geographical region.
4. The computer implemented method of claim 1 , wherein identifying the one or more matching garments having the threshold level of similarity to the preference of the user comprises: identifying, based on analyzing the garment database, a set of matching garments satisfying the match request; determining, based on analyzing a history of return information associated with the user, a confidence value corresponding to each matching garment of the set of matching garments; and identifying the one or more matching garments based on determining that the confidence value corresponding to a matching garment, of the set of matching garments, satisfies a threshold value.
5. The computer implemented method of claim 4 , wherein the match value is based on a linear or weighted analysis of physical dimensions associated with the preference of the user and physical dimensions associated with the matching garment.
6. The computer implemented method of claim 1 , wherein the base client size is associated with a first country, and wherein garment sizes of the set of target garment sizes are associated with a second country that is different from the first country.
7. The computer implemented method of claim 1 , further comprising: determining that the match request is associated with a first language; and determining that at least one matching garment, of the one or more matching garments, is associated with a website in a second language that is different from the first language, wherein generating the match communication comprises: translating information associated with the at least one matching garment from the second language to the first language, wherein the second information associated with the one or more matching garments indicated in the match communication comprises the translated information associated with the at least one matching garment.
8. The computer implemented method of claim 1 , further comprising determining the base client size based on analyzing one or more returned garment sizes associated with a garment purchase history of the user.
9. The computer implemented method of claim 1 , further comprising: identifying computer-aided design (CAD) files for garments associated with a garment purchase history of the user; and determining, based on analyzing dimensions of the garments from the CAD files, the base client size.
10. The computer implemented method of claim 1 , further comprising determining the base client size based on: generating, based on a first image depicting a first view of a garment associated with the user, a first partial shape of the garment; generating, based on a second image depicting a second view of the garment, a second partial shape of the garment; determining, based on comparing the first partial shape and the second partial shape to a database comprising reference garment shapes, a type of garment; generating, based on the determined type of garment and by joining the first partial shape and the second partial shape, a generated three-dimensional garment model comprising a first group of vertices; and determining, from the generated three-dimensional garment model and using a reference object placed near the garment in the first image, the base client size.
11. The computer implemented method of claim 1 , wherein the one or more three-dimensional garment models comprise the set of target garment sizes, and wherein generating the size map comprises analyzing the one or more three-dimensional garment models for the at least one matching garment to associate the standardized size scale and the base client size.
12. A server device, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the server device to:
receive, from a user device, a match request comprising a preference of a user and a base client size of the user;
identify, based on an analysis of a garment database, one or more matching garments having a threshold level of similarity to the preference of the user;
generate, using a boundary detection algorithm, one or more three-dimensional garment models for at least one matching garment of the one or more matching garments by:
comparing respective pixel values of each pixel in an image of the at least one matching garment to a boundary threshold value;
detecting, within the image, at least one boundary comprising a set of pixels that satisfy the boundary threshold value; and
joining a set of vertices corresponding to the set of pixels to obtain at least one partial shape of the at least one matching garment, wherein the one or more three-dimensional garment models include the at least one partial shape;
generate, using a standardized size scale and the one or more three-dimensional garment models, a size map of the base client size to a set of target garment sizes;
generate, based on the size map and the one or more matching garments, a match communication indicating:
information associated with the one or more matching garments and, for each matching garment of the one or more matching garments, a match value indicating how closely the matching garment matches the preference of the user, and
a target garment size, from the set of target garment sizes, having a closest match to the base client size; and
cause communication, to the user device, of the match communication.
13. The server device of claim 12 , wherein the instructions, when executed by the one or more processors, further cause the server device to:
receive, from the user device, an indication of a selection of a first matching garment, of the one or more matching garments, in the target garment size; and
initiate, in response to the indication of the selection, an order of the first matching garment in the target garment size.
14. The server device of claim 12 , wherein, to identify the one or more matching garments having the threshold level of similarity to the preference of the user, the instructions, when executed by the one or more processors, cause the server device to:
identify, based on an analysis of the garment database, a set of matching garments satisfying the match request;
determine, based on an analysis of a history of return information associated with the user, a confidence value corresponding to each matching garment of the set of matching garments; and
identify the one or more matching garments based on a determination that the confidence value corresponding to a matching garment, of the set of matching garments, satisfies a threshold value.
15. The server device of claim 13 , wherein the match value is based on a linear or weighted analysis of physical dimensions associated with the preference of the user and physical dimensions associated with the matching garment.
16. The server device of claim 12 , wherein the instructions, when executed by the one or more processors, further cause the server device to:
determine that the match request is associated with a first language; and
determine that at least one matching garment, of the one or more matching garments, is associated with a website in a second language that is different from the first language, and
wherein, to generate the match communication, the instructions, when executed by the one or more processors, cause the server device to:
translate information associated with the at least one matching garment from the second language to the first language, wherein the information associated with the one or more matching garments indicated in the match communication comprises the translated information associated with the at least one matching garment.
17. The server device of claim 12 , wherein the instructions, when executed by the one or more processors, further cause the server device to:
identify computer-aided design (CAD) files for garments associated with a garment purchase history of the user; and
determine, based on an analysis of dimensions of the garments from the CAD files, the base client size.
18. A non-transitory, computer-readable medium storing instructions that, when executed by one or more processors, cause a server device to:
receive, from a user device, a match request comprising a preference of a user and a base client size of the user;
identify, based on analyzing a garment database, one or more matching garments having a threshold level of similarity to the preference of the user;
generate, using a boundary detection algorithm, one or more three-dimensional garment models for at least one matching garment of the one or more matching garments by:
comparing respective pixel values of each pixel in an image of the at least one matching garment to a boundary threshold value;
detecting, within the image, at least one boundary comprising a set of pixels that satisfy the boundary threshold value; and
joining a set of vertices corresponding to the set of pixels to obtain at least one partial shape of the at least one matching garment, wherein the one or more three-dimensional garment models include the at least one partial shape;
generate, using a standardized size scale and the one or more three-dimensional garment models, a size map of the base client size to a set of target garment sizes;
generate, based on the size map and the one or more matching garments, a match communication indicating:
information associated with the one or more matching garments and, for each matching garment of the one or more matching garments, a match value indicating how closely the matching garment matches the preference of the user, and
a target garment size, from the set of target garment sizes, having a closest match to the base client size; and
causing communication, to the user device, of the match communication.
19. The non-transitory, computer-readable medium of claim 18 , wherein the instructions, when executed by the one or more processors, further cause the server device to:
receive, from the user device, an indication of a selection of a first matching garment, of the one or more matching garments, in the target garment size; and
initiate, in response to the indication of the selection, an order of the first matching garment in the target garment size.
20. The non-transitory, computer-readable medium of claim 18 , wherein the instructions to identify the one or more matching garments having the threshold level of similarity to the preference of the user, when executed by the one or more processors, further cause the server device to:
identify, based on analyzing the garment database, a set of matching garments satisfying the match request;
determine, based on analyzing a history of return information associated with the user, a confidence value corresponding to each matching garment of the set of matching garments; and
identify the one or more matching garments based on determining that the confidence value corresponding to a matching garment, of the set of matching garments, satisfies a threshold value.