IP Library › Granted Patent US 11,663,642
Granted Patent B2
US 11,663,642 · App. 16/594,241 · Granted May 30, 2023

Systems and methods of multicolor search of images

Inventors: Michael Sollami (Cambridge, MA); Yang Zhang (Cambridge, MA)
Assignee: Salesforce, Inc.
G06Q30/0625G06F16/535G06F18/22G06N3/04G06N3/08G06T7/194G06T7/90G06T2207/20081G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,663,642
App. No.
16/594,241
Granted
May 30, 2023
Kind
B2
Abstract

Systems and methods are provided for receiving at least a first query color, and searching an electronic catalog including a plurality of product images for the first query color to determine a similarity measure between the first query color and a product image of a plurality of product images. The similarity measure may be determined by determining a Euclidean distance between values in a three-dimensional color space for the first query color and a target color of the product image, and determining the similarity measure between the query color and the product image by determining a sum of the similarity measures from all target colors on the product image, weighted by the coverage of each target color. The search results may be transmitted based on the searching of the electronic catalog including the plurality of product images for the first query color.

Claims (15)

1. A method comprising:

receiving, at a server, at least a first query color and a second query color;

searching, at the server, an electronic catalog including a plurality of product images stored in at least one storage device communicatively coupled to the server for the first query color to determine a similarity measure between the first query color, the second query color, and a product image of a plurality of product images, wherein the similarity measure is determined by:

determining, at the server, a Euclidean distance between values in a three-dimensional color space for the first query color, the second query color, and a target color of the product image; and

determining, at the server, the similarity measure between the first query color, the second query color, and the product image by:

determining a sum of the similarity measures from all target colors on the product image, weighted by the coverage of each target color; and

weighting the similarity measure of each product image by its entropy to prioritize product images with color values more evenly distributed among the first query color and the second query color; and

transmitting, via a communications network coupled to the server, search results based on the searching of the electronic catalog including the plurality of product images for the first query color and the second query color.

2. The method of claim 1 , wherein the determining the similarity measure further comprises:

transforming coverage of each target color by a logarithmic function to upsample color with smaller coverage to prioritize multicolor product images.

3. A system comprising:

at least one storage device to store an electronic catalog including the plurality of product images; and

a server communicatively coupled to the at least one storage device to receive at least a first query color and a second query color, to search the electronic catalog including the plurality of product images for the first query color, to determine a similarity measure between the first query color, the second query color, and a product image of a plurality of product images, wherein the similarity measure is determined by a Euclidean distance between values in a three-dimensional color space for the first query color, the second query color, and a target color of the product image, and the similarity measure between the first query color, the second query color, and the product image by determining a sum of the similarity measures from all target colors on the product image, weighted by the coverage of each target color, and by weighting the similarity measure of each product image by its entropy to prioritize product images with color values more evenly distributed among the first query color and the second query color,

wherein the server transmits, via a communications network coupled to the server, search results based on the searching of the electronic catalog including the plurality of product images for the first query color and the second query color.

4. The system of claim 3 , wherein the server determines the similarity measure by transforming coverage of each target color by a logarithmic function to upsample color with smaller coverage to prioritize multicolor product images.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 7, 2019
From: SOLLAMI, MICHAEL; ZHANG, YANG
To: SALESFORCE.COM, INC.
Reel/Frame 050637/0278 →
Continuity (1)
Related Publication 20210103969A1 · Apr 8, 2021
Cited By (1)
US 12,254,501