# US 2017/0286372 A1 · Analysis and linking of a set of images

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0286372 A1
- Document ID: US20170286372A1
- Status: Published application
- Kind: A1
- Application number: 15/088,586
- Filed: 2016-04-01
- Published: 2017-10-05
- Earliest claimed: 2016-04-01
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Nithya Chellam; Rahul Kyamaji; Sruthi Madapoosi Ravi; Krithika Sairam; Pranav Shekhar Jha
- Web page: https://patentgrep.com/patent/US20170286372A1

## CPC

- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/0485: Scrolling or panning
- G06F 40/134: Hyperlinking
- G06Q 30/0601: Electronic shopping [e-shopping]
- G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units}
- G06F 2203/04806: Zoom, i.e. interaction techniques or interactors for controlling the zooming operation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A set of images is accessed from a server. The set is analyzed to identify objects in each image using object recognition algorithms. A primary image that includes more of the identified objects than any of the other images of the set is determined. For each of the identified objects in the primary image, a secondary image that includes the identified object and has a higher magnification than the primary image is determined. Links are inserted into the primary image at locations including an identified object that is also in a secondary image. The primary image is displayed and, upon receiving a selection of one of the links, the secondary image that includes the identified object at the location of the selected link is displayed. The set of images is ordered based on relative positons of the identified objects in each image and then linked together based on the ordering.

## Claims

### Claim 1

A system comprising:
an image processing module comprising one or more processors and configured to:
access a set of images from a server;
analyze the set of images to identify objects in each image using object recognition algorithms;
determine a primary image of the set that includes more of the identified objects than any of the other images of the set;
for each of the identified objects in the primary image, determine a secondary image of the set that includes the identified object and has a higher magnification than the primary image;
insert zooming links into the primary image at the locations in the primary image that include an identified object that is also in a secondary image;
show the primary image on a display;
show on the display, based on receiving a selection of one of the zooming links, the secondary image that includes the identified object at the location of the selected zooming link.

### Claim 2 (depends on 1)

The system of claim 1, the image processing module further configured to:
for each of the identified objects, analyze each image of the set of images to determine the relative location of at least one identified object in the image with respect to the location of the same at least one identified object in each of the other images;
based on the relative location of the at least one identified object in each image, determine an ordering of the images of the set starting from the primary image;
insert a traversal link into each image of the set at each of a right edge and a left edge of the image;
show the primary image on the display;
for each of the images of the set:
based on receiving a selection of the traversal link at the right edge of the image, show the image that follows in the ordering on the display;
based on receiving a selection of the traversal link at the left edge of the image, show the image that precedes in the ordering on the display; and
based on receiving a selection of the traversal link at the right edge of the last image in the ordering, show the primary image on the display.

### Claim 3 (depends on 2)

The system of claim 2, wherein the object recognition algorithms are selected from a group of contour matching algorithms or a group of template matching algorithms.

### Claim 4 (depends on 3)

The system of claim 3, wherein:
the server hosts an e-commerce website;
the set of images correspond to a product listing on the e-commerce website; and
the selection of the object recognition algorithms from a group is based on a category of the product listing on the e-commerce web site.

### Claim 5 (depends on 4)

The system of claim 4, the image processing module further configured to:
determine that no image of the set includes more of the identified objects than any of the other images of the set and all images of the set are of equivalent size;
reduce the size of each of the images of the set by a factor equal to the total number of images in the set;
generate a conglomerate image by including each of the images with reduced size in one image;
insert zooming links into the conglomerate image at the locations in the conglomerate image that include one of the images with reduced size;
show the conglomerate image on the display;
show on the display, based on receiving a selection of one of the zooming links, the image of the set that corresponds to the image with reduced size at the location of the selected zooming link.

### Claim 6 (depends on 5)

The system of claim 5, the image processing module further configured to:
for at least one of the identified objects in the primary image, determine that no other image of the set: includes the identified object and has a higher magnification than the primary image;
search a database of stored images to identify a stored image that: includes the identified object and has a higher magnification than the primary image;
insert a zooming link into the primary image at the location in the primary image that includes the identified object that is also in the stored image;
show the primary image on the display;
show on the stored image on the display based on receiving a selection of the zooming link at the location in the primary image that includes the identified object that is also in the stored image.

### Claim 7 (depends on 6)

The system of claim 6, the image processing module further configured to update the product listing on the e-commerce website with the images including the zooming and traversal links.

### Claim 8

A method comprising:
accessing a set of images from a server;
analyzing the set of images to identify objects in each image using object recognition algorithms;
determining a primary image of the set that includes more of the identified objects than any of the other images of the set;
for each of the identified objects in the primary image, determining a secondary image of the set that includes the identified object and has a higher magnification than the primary image;
inserting zooming links into the primary image at the locations in the primary image that include an identified object that is also in a secondary image;
showing the primary image on a display;
showing on the display, based on receiving a selection of one of the zooming
links, the secondary image that includes the identified object at the location of the selected zooming link.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
for each of the identified objects, analyzing each image of the set of images to determine the relative location of at least one identified object in the image with respect to the location of the same at least one identified object in each of the other images;
based on the relative location of the at least one identified object in each image, determining an ordering of the images of the set starting from the primary image;
inserting a traversal link into each image of the set at each of a right edge and a left edge of the image;
showing the primary image on the display;
for each of the images of the set:
based on receiving a selection of the traversal link at the right edge of the image, showing the image that follows in the ordering on the display;
based on receiving a selection of the traversal link at the left edge of the image, showing the image that precedes in the ordering on the display; and
based on receiving a selection of the traversal link at the right edge of the last image in the ordering, showing the primary image on the display.

### Claim 10 (depends on 9)

The method of claim 9, wherein the object recognition algorithms are selected from a group of contour matching algorithms or a group of template matching algorithms.

### Claim 11 (depends on 10)

The method of claim 10, wherein:
the server hosts an e-commerce website;
the set of images correspond to a product listing on the e-commerce website; and
the selection of the object recognition algorithms from a group is based on a category of the product listing on the e-commerce web site.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
determining that no image of the set includes more of the identified objects than any of the other images of the set and all images of the set are of equivalent size;
reducing the size of each of the images of the set by a factor equal to the total number of images in the set;
generating a conglomerate image by including each of the images with reduced size in one image;
inserting zooming links into the conglomerate image at the locations in the conglomerate image that include one of the images with reduced size;
showing the conglomerate image on the display;
showing on the display, based on receiving a selection of one of the zooming links, the image of the set that corresponds to the image with reduced size at the location of the selected zooming link.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
for at least one of the identified objects in the primary image, determining that no other image of the set: includes the identified object and has a higher magnification than the primary image;
searching a database of stored images to identify a stored image that: includes the identified object and has a higher magnification than the primary image;
inserting a zooming link into the primary image at the location in the primary image that includes the identified object that is also in the stored image;
showing the primary image on the display;
showing on the stored image on the display based on receiving a selection of the zooming link at the location in the primary image that includes the identified object that is also in the stored image.

### Claim 14 (depends on 13)

The method of claim 13, further comprising updating the product listing on the e-commerce website with the images including the zooming and traversal links.

### Claim 15

A non-transitory machine-readable medium storing instructions which, when executed by the at least one processor of a machine, cause the machine to perform operations comprising:
accessing a set of images from a server;
analyzing the set of images to identify objects in each image using object recognition algorithms;
determining a primary image of the set that includes more of the identified objects than any of the other images of the set;
for each of the identified objects in the primary image, determining a secondary image of the set that includes the identified object and has a higher magnification than the primary image;
inserting zooming links into the primary image at the locations in the primary image that include an identified object that is also in a secondary image;
showing the primary image on a display;
showing on the display, based on receiving a selection of one of the zooming links, the secondary image that includes the identified object at the location of the selected zooming link.

### Claim 16 (depends on 15)

The non-transitory machine-readable medium of claim 15, the operations further comprising:
for each of the identified objects, analyzing each image of the set of images to determine the relative location of at least one identified object in the image with respect to the location of the same at least one identified object in each of the other images;
based on the relative location of the at least one identified object in each image, determining an ordering of the images of the set starting from the primary image;
inserting a traversal link into each image of the set at each of a right edge and a left edge of the image;
showing the primary image on the display;
for each of the images of the set:
based on receiving a selection of the traversal link at the right edge of the image, showing the image that follows in the ordering on the display;
based on receiving a selection of the traversal link at the left edge of the image, showing the image that precedes in the ordering on the display; and
based on receiving a selection of the traversal link at the right edge of the last image in the ordering, showing the primary image on the display.

### Claim 17 (depends on 16)

The non-transitory machine-readable medium of claim 16, wherein:
the object recognition algorithms are selected from a group of contour matching algorithms or a group of template matching algorithms;
the server hosts an e-commerce website;
the set of images correspond to a product listing on the e-commerce website; and
the selection of the object recognition algorithms from a group is based on a category of the product listing on the e-commerce web site.

### Claim 18 (depends on 17)

The non-transitory machine-readable medium of claim 17, the operations further comprising:
determining that no image of the set includes more of the identified objects than any of the other images of the set and all images of the set are of equivalent size;
reducing the size of each of the images of the set by a factor equal to the total number of images in the set;
generating a conglomerate image by including each of the images with reduced size in one image;
inserting zooming links into the conglomerate image at the locations in the conglomerate image that include one of the images with reduced size;
showing the conglomerate image on the display;
showing on the display, based on receiving a selection of one of the zooming links, the image of the set that corresponds to the image with reduced size at the location of the selected zooming link.

### Claim 19 (depends on 18)

The non-transitory machine-readable medium of claim 18, the operations further comprising:
for at least one of the identified objects in the primary image, determining that no other image of the set: includes the identified object and has a higher magnification than the primary image;
searching a database of stored images to identify a stored image that: includes the identified object and has a higher magnification than the primary image;
inserting a zooming link into the primary image at the location in the primary image that includes the identified object that is also in the stored image;
showing the primary image on the display;
showing on the stored image on the display based on receiving a selection of the zooming link at the location in the primary image that includes the identified object that is also in the stored image.

### Claim 20 (depends on 19)

The non-transitory machine-readable medium of claim 19, the operations further comprising updating the product listing on the e-commerce website with the images including the zooming and traversal links.
