Picture book identification method and apparatus and terminal device using the same

Patent metadata

Field	Value
Publication number	US-11074450-B2
Application number	US-201916726833-A
Country	US
Kind code	B2
Filing date	Dec 25, 2019
Priority date	Oct 24, 2019
Publication date	Jul 27, 2021
Grant date	Jul 27, 2021

Abstract

The present disclosure provides a picture hook identification method as well as an apparatus and a terminal device using the same. The method includes; determining geometric parameter(s) of an identification object based on image(s) collected b a camera and internal parameter(s) of the camera; comparing the geometric parameters of the identification object with geometric parameter(s) of a target picture book; and determining the identification object as the target picture book, if a difference between the geometric parameters of the identification object and the geometric parameters of the target picture book is within a preset range. In this manner, the target picture book is further filtered by matching the geometric parameters, which can reduce misidentification to improve the accuracy of identifying the picture book.

First claim

What is claimed is:

1. A computer-implemented picture book identification method, comprising executing on a processor steps of:
determining one more geometric parameters of an identification object based on one or more images collected by a camera and one or more internal parameters of the camera;
comparing the geometric parameters of the identification object with one or more geometric parameters of a target picture book; and
determining the identification object as the target picture book, in. response to a difference between the geometric parameters of the identification object and the geometric parameters of the target picture book being within a preset range;
wherein the step of determining the one or more geometric parameters of the identification object based on the one or more images collected by the camera and the one or more internal parameters of the camera comprises:
determining a side length of the identification object based on the collected images and the internal parameters of the camera, and determining a side length ratio of the identification object based on the determined side lentgh; and
determining one or more angles comprised in the identification object based on the collected images and the internal parameters of the camera.

2. The method of claim 1 , wherein the step of determining the side length of the identification object based on the collected images and the internal parameters of the camera comprises:
calculating the side length of the identification object based on the formula of d(A,B)=√{square root over (<A,A>−2<A,B>+<B,B >)}, where A and B are two adjacent vertices of the identification object, d (A, B) is a distance between the vertex A and the vertex B, <A, B> is an inner product of the vertex A and the vertex B and

〈

A
,
B

〉

=

h
2

*

a

′
⁢

⁢
T

⁡

(

r
1

⁢

r
1
T

+

r
2

⁢

r
2
T

)

⁢

b
′

a

′
⁢

⁢
T

⁢

r
3

⁢

r
3
T

⁢

b
′

,

(a, b) are two points corresponding to the above-mentioned vertices A and B on the collected images, R=[r 1 , r 2 , r 3 ] is a rotation matrix, a′=K −1 a, b′=K −1 b, and K is an internal parameter of the camera.

3. The method of claim 1 , wherein the step of determining the angle comprised in the identification object based on the collected images and the internal parameters of the camera comprises:
calculating a side length of a triangle comprising the angle based on the collected images and the internal parameters of the camera; and
calculating the angle through the cosine theorem based on the calculated side length of the triangle.

4. The method of claim l, wherein the angles comprised in the idenffication object comprise one or more angles formed by at least one of one or more angles of a page of the identification object and one or more angles composed of lines in the page of the identification object.

5. The method of claim 1 , wherein the side length ratio of the identification object is aside length ratio of two adjacent sides of the identification object.

6. The method of claim 1 , further comprising:
obtaining a similarity between a page image of the identification object and a page image of the target picture book, in response to the difference between the geometric parameters of the identification object and the geometric parameters of the target picture book being within the preset range; and
determining the identification object as the target picture book identification object, in response to the similarity being larger than a predetermined threshold.

7. A picture book identification apparatus, comprising:
a geometric parameter determining unit configured to determine one or more geometric parameters of an identification object based on one or more images collected by a camera and one or more internal parameters of the camera;
a geometric parameter comparing unit configured to comparing the geometric parameters of the identification object with one or more geometric parameters of a target picture book; and
a picture book identification unit configured to determine the identification object as the target picture book, in response to a difference between the geometric parameters of the identification object and the geometric parameters of the target picture book being within a preset range;
wherein the geometric parameter determining unit is configured to:
determine a side length of the identification object based on the collected images and the internal parameters of the camera, and determine a side length ratio of the identification object based an the determined side length; and
determine one or more angles comprised in the identification object based on the collected images and the internal parameters of the camera.

8. The apparatus of claim 7 , wherein the geometric parameter determining unit is configured to determine the side length of the identification object based On the collected images and the internal parameters of the camera by:
calculating the side length of the identification obj

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Li Yang
• Gu Jing
• Wang Yue
• Liu Ao
• Cheng Jun

Classifications

• G06V30/414

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06T7/74 Primary

  involving reference images or patches · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V10/42

  Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation · CPC title

• G06V20/20

  in augmented reality scenes · CPC title