Touch and pressure-based apparel image searching

• US 10,586,263 B2
• Filed: 11/28/2016
• Issued: 03/10/2020
• Est. Priority Date: 11/28/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Raykar, Vikas, Saha, Amrita, Singh, Raghavendra
• Primary Examiner(s): Zukanovich, Brandy A
• Application Number:
  US15/361,613
• Publication Number:
  US 20180150891A1
• Time in Patent Office: 1,198 Days
• Field of Search: 705 261, 705 271
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Methods, systems, and computer program products for pressure-based apparel image searching are provided herein. A computer-implemented method includes determining an object of interest within an image displayed on a screen by detecting physical contact imparted by a user at a particular position on the screen corresponding to where the first object is located; quantifying the amount of pressure applied by the user via the physical contact; determining additional objects of interest based on the amount of pressure applied by the user by identifying objects that are located within a specified distance from the first object, and wherein the specified distance corresponds to the amount of pressure applied by the user; retrieving, from at least one electronic commerce website, images of products corresponding to the first object of interest and images of products corresponding to each of the additional objects of interest; and displaying the retrieved images on the screen.

Claims

1. A computer-implemented method, comprising:

determining a first object of interest within an image displayed on a screen, wherein said determining the first object of interest comprises (i) detecting physical contact imparted by a user at a particular position on the screen corresponding to where the first object of interest is located, and (ii) defining a Gaussian kernel centered on the particular position on the screen, wherein defining the Gaussian kernel comprises increasing the width of the Gaussian kernel based on the quantified amount of pressure applied by the user via the physical contact;

quantifying the amount of pressure applied by the user via the physical contact;

determining one or more additional objects of interest within the image based on the amount of pressure applied by the user via the physical contact, wherein said determining the additional objects of interest comprises identifying one or more objects that are located within a specified distance from the first object of interest in the image, and wherein the specified distance corresponds to the amount of pressure applied by the user via the physical contact;

retrieving, from at least one electronic commerce website, (i) one or more images of one or more products corresponding to the first object of interest and (ii) one or more images of one or more products corresponding to each of the one or more additional objects of interest; and

displaying the retrieved images on the screen;

wherein the method is carried out by at least one computing device.

2. The computer-implemented method of claim 1, wherein the first object of interest comprises an item of apparel.

3. The computer-implemented method of claim 1, wherein the first object of interest comprises an apparel accessory.

4. The computer-implemented method of claim 1, wherein the screen comprises a mobile device screen.

5. The computer-implemented method of claim 1, wherein the screen comprises a desktop computer screen.

6. The computer-implemented method of claim 1, wherein the physical contact comprises a touch by the user'"'"'s finger.

7. The computer-implemented method of claim 1, wherein the physical contact comprises a touch by a pointing device.

8. The computer-implemented method of claim 1, comprising:

weighting feature representations from multiple positions on the screen based on the Gaussian kernel.

9. The computer-implemented method of claim 8, comprising:

determining the feature representation for the particular position on the screen by summing the weighted feature representations from the multiple positions on the screen.

10. The computer-implemented method of claim 1, wherein the one or more additional objects of interest comprise one or more items of apparel.

11. The computer-implemented method of claim 1, wherein the one or more additional objects of interest comprise one or more apparel accessories.

12. The computer-implemented method of claim 1, wherein the at least one electronic commerce website comprises an apparel-selling website.

13. The computer-implemented method of claim 1, wherein the image displayed on the screen comprises an image derived from a source that is separate from the at least one electronic commerce website.

14. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:

determine a first object of interest within an image displayed on a screen, wherein said determining the first object of interest comprises (i) detecting physical contact imparted by a user at a particular position on the screen corresponding to where the first object of interest is located, and (ii) defining a Gaussian kernel centered on the particular position on the screen, wherein defining the Gaussian kernel comprises increasing the width of the Gaussian kernel based on the quantified amount of pressure applied by the user via the physical contact;

quantify an amount of pressure applied by the user via the physical contact;

determine one or more additional objects of interest within the image based on the amount of pressure applied by the user via the physical contact, wherein said determining the additional objects of interest comprises identifying one or more objects that are located within a specified distance from the first object of interest in the image, and wherein the specified distance corresponds to the amount of pressure applied by the user via the physical contact;

retrieve, from at least one electronic commerce website, (i) one or more images of one or more products corresponding to the first object of interest and (ii) one or more images of one or more products corresponding to each of the one or more additional objects of interest; and

display the retrieved images on the screen.

15. The computer program product of claim 14, wherein said determining the first object of interest comprises defining a Gaussian kernel centered on the particular position on the screen.

16. The computer program product of claim 15, wherein the program instructions further cause the device to:

weight feature representations from multiple positions on the screen based on the Gaussian kernel; and

determine the feature representation for the particular position on the screen by summing the weighted feature representations from the multiple positions on the screen.

17. A system comprising:

a memory; and

at least one processor operably coupled to the memory and configured for;

determining a first object of interest within an image displayed on a screen, wherein said determining the first object of interest comprises (i) detecting physical contact imparted by a user at a particular position on the screen corresponding to where the first object of interest is located, and (ii) defining a Gaussian kernel centered on the particular position on the screen, wherein defining the Gaussian kernel comprises increasing the width of the Gaussian kernel based on the quantified amount of pressure applied by the user via the physical contact;

quantifying the amount of pressure applied by the user via the physical contact;

determining one or more additional objects of interest within the image based on the amount of pressure applied by the user via the physical contact, wherein said determining the additional objects of interest comprises identifying one or more objects that are located within a specified distance from the first object of interest in the image, and wherein the specified distance corresponds to the amount of pressure applied by the user via the physical contact;

retrieving, from at least one electronic commerce website, (i) one or more images of one or more products corresponding to the first object of interest and (ii) one or more images of one or more products corresponding to each of the one or more additional objects of interest; and

displaying the retrieved images on the screen.