Techniques for shape-based search of content

• US 8,718,369 B1
• Filed: 09/20/2011
• Issued: 05/06/2014
• Est. Priority Date: 09/20/2011
• Status: Active Grant

• Current Assignee: A9.com Incorporated (Amazon.com, Inc.)
• Original Assignee: A9.com Incorporated (Amazon.com, Inc.)
• Inventors: Tompkins, Stephen S., Dhua, Arnab S., Wang, Leslie K., Wah, Catherine L.
• Primary Examiner(s): Fitzpatrick, Atiba O
• Assistant Examiner(s): JAMES, THOMAS AIDEN
• Application Number:
  US13/237,099
• Time in Patent Office: 959 Days
• Field of Search: None
• US Class Current: 382/181
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06Q 30/0623 Item investigation

Abstract

Techniques for facilitating a shape-based search of content items are disclosed. In some situations, the techniques include receiving a request for search of content that includes an image of an item and a glyph input by the user on the image that indicates a shape of the first item, extracting features associated with the item from an area of the image on which the glyph is input; identifying a shape category of the first item based at least in part on the indicated shape of the glyph; and conducting a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category. The retrieved search results may be returned to a user.

Claims

1. A computer-implemented method for facilitating a shape-based search of content items, comprising:

under control of one or more computer systems configured with executable instructions,

receiving information from a request by a user for a search of content, the received information indicating an image of a first item and including a glyph that is input by the user on the image and that indicates a shape of the first item without tracing an outline of the first item in the image;

extracting one or more features associated with the first item from an area of the image on which the glyph is input;

identifying a shape category of the first item based at least in part on the indicated shape of the glyph;

conducting a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category;

providing search results including one or more additional items having features that match the extracted features of the first item, the provided search results including a second image for each of the one or more additional items;

receiving second information from a second search request by the user that indicates the second image for a second item of the one or more additional items, the received second information including a second glyph input by the user that indicates a second shape of the second item and that represents a refined shape of the first item;

identifying a second shape category based on the second shape indicated by the second glyph; and

conducting a second search for items among a plurality of items associated with the second shape category, the second search being based on at least one of the extracted one or more features associated with the first item, and one or more additional features extracted from the second image that are associated with the second item.

2. The computer-implemented method of claim 1, wherein the image is captured by a user device.

3. The computer-implemented method of claim 2, wherein the user device includes a display component configured to display images of items to the user and to receive user input comprising glyphs indicating shapes of the displayed item images.

4. The computer-implemented method of claim 1, wherein the image is provided to the user in response to the user browsing content items with the user device.

5. The computer-implemented method of claim 1, wherein the extracted features include at least one of a texture of the first item and a contour of the first item, and wherein the search for items having features that match the extracted features is based on calculating similarities between the respective features.

6. The computer-implemented method of claim 1, wherein the identifying of the shape category of the first item is based on comparing the indicated shape of the glyph with a plurality of predefined item shapes, each of the predefined item shapes being associated with an item shape category.

7. The computer-implemented method of claim 1, wherein the user input includes at least one attribute associated with the glyph indicating the shape of the first item, the at least one attribute including an indicated color of the first item, and wherein the search for items is further based on a search criterion associated with the at least one attribute, the associated search criterion indicating at least the indicated color of items to be searched.

8. The computer-implemented method of claim 1, wherein the glyph is a single-stroke figure.

9. A computer system for facilitating a shape-based search of content items, the system comprising:

at least one processor; and

at least one memory having computer-executable instructions that, when executed on the at least one processor, cause the at least one processor to;

receive information from a request by a user for a search of content, the received information indicating an image of a first item and including a glyph that is input by the user for the image and that indicates a shape of the first item;

extract one or more features associated with the first item from an area of the image corresponding to the glyph;

identify a shape category of the first item based at least in part on the indicated shape of the glyph;

conduct a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category;

provide search results indicating one or more additional items having features that match the extracted features of the first item;

receive second information from a second search request by the user that indicates a second image for a second item of the one or more additional items, the received second information including a second glyph input by the user that indicates a second shape of the second item and that represents a refined shape of the first item;

identify a second shape category based on the second shape indicated by the second glyph; and

conduct a second search for items among a plurality of items associated with the second shape category, the second search being based on at least one of the extracted one or more features associated with the first item, and one or more additional features extracted from the second image that are associated with the second item.

10. The computer system of claim 9, wherein the search request is received from a user device.

11. The computer system of claim 9, wherein the computer-executable instructions further cause the at least one processor to determine at least one attribute associated with the glyph indicating the shape of the first item and to conduct the search for items based at least in part on a search criterion associated with the at least one attribute.

21. The computer system of claim 9 wherein the computer system is a user device having an image capture component, and wherein the indicated image is generated by the image capture component.

22. The computer system of claim 21 further comprising a display component configured to display images of items to the user and to receive user input comprising glyphs indicating shapes of the displayed item images.

23. The computer system of claim 9 wherein the extracted features include a texture of the first item, a color of the first item, or a contour of the first item.

24. The computer system of claim 9 wherein the extracted features include a texture of the first item and a color of the first item, and wherein the search for items having features that match the extracted features includes calculating similarities between the features of the items and the extracted features.

25. The computer system of claim 9 wherein the identifying of the shape category of the first item is based on comparing the indicated shape of the glyph to a plurality of predefined item shapes that are each associated with an item shape category.

12. A non-transitory computer-readable medium having computer-executable instructions for facilitating a shape-based search of content items stored thereon that, when executed by a computer, cause the computer to:

receive information from a request by a user for a search of content, the received information indicating an image of a first item and including a glyph that is input by the user corresponding to the image, the glyph indicating a shape of the first item that corresponds to a partial contour of the first item in the image;

extract one or more features associated with the first item from an area of the image corresponding to the glyph;

identify a shape category of the first item based at least in part on the indicated shape of the glyph;

conduct a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category;

provide, to the user, search results indicating one or more additional items having features that match the extracted features of the first item;

receive second information from the user indicating a second glyph that is input by the user on a second image for a second item of the one or more additional items;

identify a second shape category based on a second shape indicated by the second glyph; and

conduct a second search for items among a plurality of items associated with the second shape category, the second search being based on at least one of the extracted one or more features associated with the first item and being based on one or more additional features associated with the second item.

13. The non-transitory computer-readable medium of claim 12, wherein the search request is received from a user device.

14. The non-transitory computer-readable medium of claim 12, wherein the user device includes a display component configured to display images of items to the user and to receive user input comprising glyphs indicating shapes of the displayed item images.

15. The non-transitory computer-readable medium of claim 12, wherein the computer-executable instructions that cause the computer to identify a shape category of the first item further cause the computer to determine a match between the glyph and at least one of a plurality of predefined item shapes, wherein each predefined item shape defines an item shape category.

16. The non-transitory computer-readable medium of claim 12, wherein the computer-executable instructions that cause the computer to identify a shape category of the first item further cause the computer to compare the shape indicated by the provided glyph with shapes of one or more other items distinct from the first item.

17. The non-transitory computer-readable medium of claim 12 wherein the extracted features include a texture of the first item, a color of the first item, or a contour of the first item.

18. The non-transitory computer-readable medium of claim 12 wherein the extracted features include a texture of the first item and a color of the first item, and wherein the search for items having features that match the extracted features includes calculating similarities between the features of the items and the extracted features.

19. The non-transitory computer-readable medium of claim 12 wherein the received information further includes at least one attribute associated with the glyph, and wherein the search for items is further based on a search criterion associated with the at least one attribute.

20. The non-transitory computer-readable medium of claim 12 wherein the identified second shape category is the identified shape category of the first item.