Image quality assessment to merchandise an item

Patent metadata

Field	Value
Publication number	US-9519918-B2
Application number	US-201414180255-A
Country	US
Kind code	B2
Filing date	Feb 13, 2014
Priority date	Nov 18, 2010
Publication date	Dec 13, 2016
Grant date	Dec 13, 2016

Abstract

Image-based features may be significantly correlated with click-through rates of images that depict a product, which may provide a more formal basis for the informal notion that good quality images will result in better click-through rates, as compared to poor quality images. Accordingly, an image assessment machine is configured to analyze image-based features to improve click-through rates for shopping search applications (e.g., a product search engine). Moreover, the image assessment machine may rank search results based on image quality factors and may notify sellers about low quality images. This may have the effect of improving the brand value for an online shopping website and accordingly have a positive long-term impact on the online shopping website.

First claim

What is claimed is:

1. A method comprising:
receiving an image that has a visual characteristic quantifiable by an analysis of the image;
performing the analysis of the image based on a pixel count of the image, the performing being performed by a processor of a machine;
determining a score that quantifies the visual characteristic, the determining of the score being performed by the processor of the machine based on the analysis of the image;
determining the shape of an item depicted in the image by segmenting the image;
accessing a database that correlates the shape of the item with a stored description of the item; and
providing a suggestion, at a user interface of a device of an uploader of the image, that the received image be replaced with an alternative image stored by the machine, the alternative image scoring higher than the determined score of the received image, the received image and the alternative image both depicting a same subject, the suggestion being provided based on the determined score of the received image and including the stored description of the item.

2. The method of claim 1 , wherein:
the same subject depicted in the received image and the alternative image is an item available for sale by the uploader of the image.

3. The method of claim 1 , wherein:
the receiving of the image receives the image as a submission for inclusion in an advertisement of an item depicted in the image; and
the providing of the suggestion provides the suggestion with a warning that the image is of low quality.

4. The method of claim 1 , wherein:
the visual characteristic is an average brightness of the image; and
the providing of the suggestion provides the suggestion with a warning that the image is too dark.

5. The method of claim 1 , wherein:
the visual characteristic is a dynamic range for brightness within the image; and
the providing of the suggestion provides the suggestion with a warning that the image has poor dynamic range for brightness.

6. The method of claim 1 , wherein:
the visual characteristic is a contrast level within the image; and
the providing of the suggestion provides the suggestion with a warning that the image has poor contrast.

7. The method of claim 1 , wherein:
the visual characteristic is a dynamic range for contrast within the image; and
the providing of the suggestion provides the suggestion with a warning that the image has poor dynamic range for contrast.

8. The method of claim 1 further comprising:
the visual characteristic is an aspect ratio of the image; and
the providing of the suggestion provides a suggestion with a warning that the image has a poor aspect ratio.

9. The method of claim 1 further comprising:
segmenting the image into a foreground portion that depicts an item and a background portion that depicts no part of the item; wherein
the visual characteristic is a uniformity of the foreground portion of the image; and
the providing of the suggestion provides the suggestion with a warning that the foreground portion has poor uniformity.

10. The method of claim 1 further comprising:
segmenting the image into a foreground portion that depicts an item and a background portion that depicts no part of the item; wherein
the visual characteristic is a uniformity of the background portion of the image; and
the providing of the suggestion provides the suggestion with a warning that the background portion has poor uniformity.

11. The method of claim 1 further comprising:
segmenting the image into a foreground portion that depicts an item and a background portion that depicts no part of the item; wherein
the visual characteristic is a ratio of foreground pixels to background pixels within the image; and
the providing of the suggestion provides a suggestion with a warning that an item depicted in the image is too small within the image.

12. The method of claim 1 further comprising:
receiving a submitted description of the item from the uploader of the image; and wherein
the providing of the suggestion provides the suggestion with a warning that the submitted description does not describe the item.

13. The method of claim 1 further comprising:
receiving a submitted description of the item from the uploader of the image; and wherein
the providing of the suggestion provides the suggestion with a further suggestion that the item be described by the stored description instead of the submitted description.

14. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
receiving an image that has a visual characteristic quantifiable by an analysis of the image;
performing the analysis of the image based on a pixel count of the image;
determining a score that quantifies the visual characteristic, the determining of the score being based on the analysis of the image;
determining the shape of an item depicted in the image by segmenting the image;
accessing a database that correlates the shape of the item with a stored description of the item; and
providing a suggestion to an uploader of the image that the received image be replaced with an alternative image stored by the machine, the alternative image scoring higher than the determined score of the received image, the received image and the alternative image both depicting a same subject, the suggestion being provided based on the determined score of the received image and including the stored description of the item.

15. The non-transitory machine-readable storage medium of claim 14 , wherein:
the receiving of the image receives the image as a submission for inclusion in an advertisement of an item depicted in the image; and
the providing of the suggestion provides the suggestion with a warning that the image is of low quality.

16. A system comprising:
one or more processors, and a memory including instructions, which when executed by the one or more processors, cause the one or more processors to:
receive an image that has a visual characteristic quantifiable by an analysis of the image;
perform the analysis of the image based on a pixel count of the image;
determine a score that quantifies the visual characteristic, the determining of the score being based on the analysis of the image;
determine the shape of an item depicted in the image by segmenting the image;
access a database that correlates the shape of the item with a stored description of the item; and
provide a suggestion to an uploader of the image that the received image be replaced with an alternative image stored by the machine, the alternative image scoring higher than the determined score of the received image, the received image and the alternative image both depicting a same subject, the suggestion being provided based on the determined score of the received image and include the stored description of the item.

17. The system of claim 16 , wherein:
the same subject depicted in the received image and the alternative image is an item available for sale by the uploader of the image.

Assignees

• Ebay Inc

Inventors

• Goswami Anjan
• Chittar Naren
• Dasdan Ali
• Ghatare Sanjay Pundlkrao
• Gaikwad Sandip Namdeo
• Chung Sung Hwan

Classifications

• G06F16/24578

  using ranking · CPC title

• G06F16/5854

  using shape and object relationship · CPC title

• G06F16/58

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06Q30/0276 Primary

  Advertisement creation · CPC title

• G06T2207/30168

  Image quality inspection · CPC title