Image match for featureless objects

Patent metadata

Field	Value
Publication number	US-2016379080-A1
Application number	US-201615166973-A
Country	US
Kind code	A1
Filing date	May 27, 2016
Priority date	Jun 25, 2015
Publication date	Dec 29, 2016
Grant date	—

Abstract

Object identification through image matching can utilize ratio and other data to accurately identify objects having relatively few feature points otherwise useful for identifying objects. An initial image analysis attempts to locate a “scalar” in the image, such as may include a label, text, icon, or other identifier that can help to narrow a classification of the search, as well as to provide a frame of reference for relative measurements obtained from the image. By comparing the ratios of dimensions of the scalar with other dimensions of the object, it is possible to discriminate between objects containing that scalar in a way that is relatively robust to changes in viewpoint. A ratio signature can be generated for an object for use in matching, while in other embodiments a classification can identify priority ratios that can be used to more accurately identify objects in that classification.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
obtaining an image including a representation of an object; analyzing the image to identify a plurality of feature points corresponding to the representation of the object; determining a plurality of ratios of distances between pairs of the feature points; comparing the plurality of ratios against ratio data stored for each object of a set of objects to generate a similarity score for each comparison; determining a matching object from the set of objects associated with a highest similarity score; and displaying content corresponding to the matching object on a display screen of a computing device.

2 . The computer-implemented method of claim 1 , further comprising:
identifying, based at least in part upon the plurality of feature points, a scalar element contained within the representation of the object in the image, the scalar element associated with at least one classification of objects.

3 . The computer-implemented method of claim 2 , further comprising:
narrowing a search space for the object based at least in part upon at least one classification, wherein the set of objects is contained within the at least one classification.

4 . The computer-implemented method of claim 2 , further comprising:
determining the plurality of ratios based at least in part upon the at least one classification.

5 . The computer-implemented method of claim 2 , further comprising:
determining a relative weighting of at least a subset of the plurality of ratios based at least in part upon the at least one classification, the relative weighting for a ratio indicative of an association of the ratio with a distinctive characteristic of one or more of the set of objects in the classification.

6 . The computer-implemented method of claim 2 , wherein the scalar element includes at least one of a logo, a label, a letter, or text corresponding to at least one of a type of object or a family of objects.

7 . The computer-implemented method of claim 1 , further comprising:
segmenting the image into an object region and at least one non-object region, wherein the plurality of feature points correspond to the object region and include the representation of the object; and determining a color region in the representation of the object, wherein determining the matching object further includes locating data for an object having a similar color for a corresponding color region.

8 . The computer-implemented method of claim 1 , wherein comparing the plurality of ratios against the ratio data stored for each object of the set of objects includes comparing at least one of a bank of ratios, a ratio signature, an average ratio, a range of ratios, a distribution of ratios, or a histogram of ratios.

9 . The computer-implemented method of claim 1 , further comprising:
performing interpolation on at least a portion of the image to increase a precision of the ratio data.

10 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing device, cause the computing device to:
obtain an image including a representation of an object; analyze the image to identify a plurality of feature points corresponding to the representation of the object; determine a plurality of ratios of distances between pairs of the feature points; compare the plurality of ratios against ratio data stored for each object of a set of objects to generate a similarity score for each comparison; determine a matching object from the set of objects associated with a highest similarity score; and display content corresponding to the matching object on a display screen of a computing device.

11 . The non-transitory computer-readable storage medium of claim 10 , wherein the instructions when executed further cause the computing device to:
identify, based at least in part upon the plurality of feature points, a scalar element contained within the representation of the object in the image, the scalar element associated with at least one classification of objects; and narrow a search space for the object based at least in part upon the at least one classification, wherein the set of objects is contained within the at least one classification.

12 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions when executed further cause the computing device to:
determine the plurality of ratios based at least in part upon the at least one classification.

13 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions when executed further cause the computing device to:
determine a relative weighting of at least a subset of the plurality of ratios based at least in part upon the at least one classification, the relative weighting for a ratio indicative of an association of the ratio with a distinctive characteristic of one or more of the set of objects in the classification.

14 . The non-transitory computer-readable storage medium of claim 11 , wherein the scalar element includes at least one of a logo, a label, a letter, or text corresponding to at least one of a type of object or a family of objects pertaining to the set of objects.

15 . The non-transitory computer-readable storage medium of claim 11 , wherein at least a subset of the pairs of the feature points corresponds to feature points of the scalar element, wherein the scalar element functions as a reference for distance measurements.

16 . The non-transitory computer-readable storage medium of claim 11 , wherein the instructions when executed further cause the computing device to:
determine an amount of distortion of the scalar element in the image; performing a distortion removal process on the image based at least in part upon the amount of distortion; and determine new ratios of distances between pairs of the feature points after the distortion removal process is performed.

17 . A computer system, comprising:
at least one processor; and memory including instructions that, when executed by the processor, cause the computer system to: obtain an image including a representation of an object; analyze the image to identify a plurality of feature points corresponding to the representation of the object; determine a plurality of ratios of distances between pairs of the feature points; compare the plurality of ratios against ratio data stored for each object of a set of objects to generate a similarity score for each comparison; determine a matching object from the set of objects associated with a highest similarity score; and display content corresponding to the matching object on a display screen of a computing device.

18 . The computer system of claim 17 , wherein the memory further comprises instructions executed by the at least one processor to cause the computing system to:
identify, based at least in part upon the plurality of feature points, a scalar element contained within the representation of the object in the image, the scalar element associated with at least one classification of objects; and narrow a search space for the object based at least in part upon the at least one classification, wherein the set of objects is contained within the at least one classification.

19 . The computer system of claim 18 , wherein the memory further comprises instructions executed by the at least one processor to cause the computing system to: determine the plurality of ratios based at

Assignees

• A9 Com Inc

Inventors

• Yalniz Ismet Zeki
• Taylor Colin Jon
• Tek Mehmet Nejat
• Tsai Shanghsuan

Classifications

• G06V10/757 Primary

  Matching configurations of points or features · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• G06T7/408

  Physics · mapped topic

• G06K9/4676

  Physics · mapped topic

• G06T7/60

  Analysis of geometric attributes · CPC title