Logo picture processing method, apparatus, device and medium

Patent metadata

Field	Value
Publication number	US-11610396-B2
Application number	US-202117375468-A
Country	US
Kind code	B2
Filing date	Jul 14, 2021
Priority date	Dec 25, 2020
Publication date	Mar 21, 2023
Grant date	Mar 21, 2023

Abstract

The present disclosure provides a logo picture processing method, apparatus, device and medium, and relates to technical field of image processing, and specifically to the technical field of artificial intelligence such as deep learning and computer vision. The logo picture processing method includes: obtaining a logo picture including: a current logo graph and current text information; performing text recognition on the logo picture to obtain the current text information; searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture. The present disclosure may improve the accuracy of the matched picture of the logo picture and thereby improve the logo picture recognition accuracy.

First claim

What is claimed is:

1. A computer-implemented logo picture processing method, comprising:
obtaining a logo picture including: a current logo graph and current text information;
performing text recognition on the logo picture to obtain the current text information; and
searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture,
wherein at least one candidate picture is pre-stored in a picture library, and the candidate picture comprises: a candidate logo picture and candidate text information, and the searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture comprises:
calculating a graphic similarity between the current logo graph and each candidate logo graph;
comparing the candidate text information corresponding to the respective candidate logo graphs in turn with the current text information in a descending order of the graphic similarities; and
regarding a candidate picture corresponding to the candidate text information that is the same as the current text information, as the matched picture.

2. The method according to claim 1 , wherein each candidate feature vector corresponding to each candidate logo graph is pre-stored in the picture library, and the calculating a graphic similarity between the current logo graph and each candidate logo graph comprises:
extracting a current feature vector of the current log graph;
respectively calculating distance values between the current feature vector and the candidate feature vectors, and determining the graph similarities according to the distance values.

3. The method according to claim 1 , wherein the obtaining a logo picture comprises:
determining a logo area in an original picture;
cropping, from the original picture, a picture corresponding to the logo area, as the logo picture.

4. The method according to claim 1 , wherein the performing text recognition on the logo picture to obtain the current text information comprises:
performing Optical Character Recognition (OCR) on the logo picture to obtain an OCR result; and
taking the OCR recognition result as the current text information if a confidence of the OCR result is greater than or equal to a preset threshold.

5. The method according to claim 1 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

6. The method according to claim 2 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

7. The method according to claim 3 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

8. The method according to claim 4 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

9. An electronic device, comprising:
at least one processor; and
a memory communicatively connected with the at least one processor;
wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a logo picture processing method, wherein the method comprises:
obtaining a logo picture including: a current logo graph and current text information;
performing text recognition on the logo picture to obtain the current text information; and
searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture,
wherein at least one candidate picture is pre-stored in a picture library, and the candidate picture comprises: a candidate logo picture and candidate text information, and the searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture comprises:
calculating a graphic similarity between the current logo graph and each candidate logo graph;
comparing the candidate text information corresponding to the respective candidate logo graphs in turn with the current text information in a descending order of the graphic similarities; and
regarding a candidate picture corresponding to the candidate text information that is the same as the current text information, as the matched picture.

10. The electronic device according to claim 9 , wherein each candidate feature vector corresponding to each candidate logo graph is pre-stored in the picture library, and the calculating a graphic similarity between the current logo graph and each candidate logo graph comprises:
extracting a current feature vector of the current log graph; and
respectively calculating distance values between the current feature vector and the candidate feature vectors, and determining the graph similarities according to the distance values.

11. The electronic device according to claim 9 , wherein the obtaining a logo picture comprises:
determining a logo area in an original picture;
cropping, from the original picture, a picture corresponding to the logo area, as the logo picture.

12. The electronic device according to claim 9 , wherein the performing text recognition on the logo picture to obtain the current text information comprises:
performing Optical Character Recognition (OCR) on the logo picture to obtain an OCR result; and
taking the OCR recognition result as the current text information if a confidence of the OCR result is greater than or equal to a preset threshold.

13. The electronic device according to claim 9 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

14. The electronic device according to claim 10 , further comprising:
obtaining a recognition result according to the matched picture, the recognition result including: the matched picture, and/or a tag corresponding to the matched picture.

15. A non-transitory computer readable storage medium with computer instructions stored thereon, wherein the computer instructions are used for causing a computer to perform a logo picture processing method, wherein the method comprises:
obtaining a logo picture including: a current logo graph and current text information;
performing text recognition on the logo picture to obtain the current text information; and
searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture,
wherein at least one candidate picture is pre-stored in a picture library, and the candidate picture comprises: a candidate logo picture and candidate text information, and the searching for a picture that matches both the current logo graph and the current text information, to obtain a matched picture comprises:
calculating a graphic similarity between the current logo graph and each candidate logo graph;
comparing the candidate text information corresponding to the respective candidate logo graphs in turn with the current text information in a descending order of the graphic similarities; and
regarding a candidate picture corresponding to the candidate text information that is the same as the current text information, as the ma

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Cui Cheng
• Wei Kai
• Yang Min

Classifications

• G06V30/147

  Determination of region of interest · CPC title

• G06V20/00 Primary

  Scenes; Scene-specific elements (control of digital cameras H04N23/60) · CPC title

• G06V30/10

  Character recognition · CPC title

• G06V2201/09

  Recognition of logos · CPC title

• G06F16/5846

  using extracted text · CPC title