Picture ranking method, and terminal

• US 10,242,250 B2
• Filed: 05/21/2018
• Issued: 03/26/2019
• Est. Priority Date: 03/12/2014
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Jiang, Zhuolin, Yang, Qiang
• Primary Examiner(s): Liew, Alex Kok S
• Application Number:
  US15/984,735
• Publication Number:
  US 20180268205A1
• Time in Patent Office: 309 Days
• Field of Search: 382115-118
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/179 metadata assisted face recognition

Abstract

A picture ranking method and a terminal comprises acquiring pictures stored in a terminal, detecting whether the pictures are first-type pictures, where a first-type picture refers to a picture including a human face, and when the pictures are first-type pictures, ranking the pictures according to a social relation model, or when the pictures are not first-type pictures, ranking the pictures according to a preset rule.

Claims

1. A picture ranking method, comprising:

acquiring pictures stored in a terminal;

detecting first-type pictures from the pictures stored in the terminal, the first-type pictures comprising one or more human faces;

determining contacts corresponding to the first-type pictures according to the one or more human faces in the first-type pictures;

acquiring, according to a social relation model, social relation categories for the contacts corresponding to the first-type pictures, the social relation categories identifying different types of social relations between the contacts corresponding to the first-type pictures and a user of the terminal; and

ranking the first-type pictures according to the social relations.

2. The method of claim 1, wherein before acquiring the social relation categories for the contacts corresponding to the first-type pictures, the method further comprises training the social relation model using a stored profile picture of the contacts and information about the contacts.

3. The method of claim 2, wherein training the social relation model using the stored profile picture of the contacts and the information about the contacts comprises:

extracting profile picture data of the contacts; and

annotating the profile picture data using the information about the contacts to obtain the social relation model, the information about the contacts comprising identity features of the contacts, and the identity features being used to represent a social relation between the contacts and the user of the terminal.

4. The method of claim 1, wherein acquiring the social relation categories for the contacts corresponding to the first-type pictures comprises:

acquiring, using the social relation model, information about the contacts corresponding to the first-type pictures, the information about the contacts corresponding to the first-type pictures comprising identity features of the contacts corresponding to the first-type pictures, and the identity features being used to represent a social relation between the contacts corresponding to the first-type pictures and the user of the terminal; and

determining the social relation categories for the contacts corresponding to the first-type pictures according to the identity features of the contacts corresponding to the first-type pictures.

5. The method of claim 1, further comprising,

detecting second-type pictures from the pictures stored in the terminal, wherein the second-type pictures do not include a human face;

and

ranking the second-type pictures according to a preset rule.

6. The method of claim 4, further comprising:

adding the first-type pictures to an unrecognized face group; and

performing clustering ranking on images in the unrecognized face group according to a preset rule when the information about the contacts corresponding to the first-type pictures is not acquired.

7. The method of claim 1, wherein before detecting the first-type pictures, the method further comprises:

extracting a feature value of a stored human face image;

learning the feature value of the human face image using a machine learning method; and

establishing a facial recognition model according to learning the feature value of the human face image.

8. The picture ranking method of claim 7, wherein detecting the first-type pictures comprises:

extracting feature values of the pictures stored in the terminal;

performing a matching between the feature values of the pictures stored in the terminal and the facial recognition model; and

detecting the first-type pictures based on a result of the matching for the first-type pictures being higher than a first preset value.

9. The picture ranking method of claim 5, wherein detecting whether the second-type pictures comprises:

extracting feature values of the pictures stored in the terminal;

performing a matching between the feature values of the pictures stored in the terminal and a facial recognition model; and

detecting the second-type pictures based on a result of the matching for the second-type pictures being less than a first preset value.

19. The method of claim 1, wherein before ranking the first-type pictures according to the social relations, the method further comprises:

acquiring interaction statistics between each of the contacts corresponding to the first-type pictures and the user;

selecting the social relation categories for the contacts corresponding to the first-type pictures based on the interaction statistics; and

training the social relation model using stored profile pictures of the contacts corresponding to the first-type pictures and the social relation categories for the contacts corresponding to the first-type pictures.

10. A terminal, comprising:

at least one processor; and

a non-transitory computer-readable storage medium coupled to the at least one processor and storing programming instructions, the programming instructions causing the at least one processor to be configured to;

acquire pictures stored in a terminal;

detect first-type pictures from the pictures stored in the terminal, the first-type pictures comprising one or more human faces;

determine contacts corresponding to the first-type pictures according to the one or more human faces in the first-type pictures;

acquire, according to a social relation model, social relation categories for the contacts corresponding to the first-type pictures, wherein the social relation categories identify different types of social relations between the contacts corresponding to the first-type pictures and a user of the terminal; and

rank the first-type pictures according to the social relations.

11. The terminal of claim 10, wherein the programming instructions further cause the at least one processor to be configured to train the social relation model using one or more stored profile pictures of the contacts and information about the contacts before acquiring the social relation categories for the contacts corresponding to the first-type pictures.

12. The terminal of claim 10, wherein the programming instructions further cause the at least one processor to be configured to:

extract profile picture data of the contacts; and

annotate the profile picture data using information about the contacts to obtain the social relation model, wherein the information about the contacts comprises identity features of the contacts, and the identity features represent a social relation between the contacts and the user of the terminal.

13. The terminal of claim 10, wherein the programming instructions further cause the at least one processor to be configured to:

acquire, using the social relation model, information about the contacts corresponding to the first-type pictures, the information about the contacts corresponding to the first-type pictures comprising identity features of the contacts corresponding to the first-type pictures, and the identity features being used to represent a social relation between the contacts corresponding to the first-type pictures and the user of the terminal; and

determine the social relation categories for the contacts corresponding to the first-type pictures according to the identity features of the contacts corresponding to the first-type pictures.

14. The terminal of claim 10, wherein the programming instructions further cause the at least one processor to be configured to:

detect second-type pictures from the pictures stored in the terminal, wherein the second-type pictures do not include a human face; and

rank the second-type pictures according to a preset rule.

15. The terminal of claim 13, wherein the programming instructions further cause the at least one processor to be configured to:

add the first-type pictures to an unrecognized face group; and

perform clustering ranking on images in the unrecognized face group according to a preset rule when the information about the contacts corresponding to the first-type pictures is not acquired.

16. The terminal of claim 10, wherein the programming instructions further cause the at least one processor to be configured to:

extract a feature value of a stored human face image;

learn the feature value of the human face image using a machine learning method; and

establish a facial recognition model according to learning the feature value of the human face image.

17. The terminal of claim 16, wherein the programming instructions further cause the at least one processor to be configured to:

extract feature values of the pictures stored in the terminal;

perform a matching between the feature values of the pictures stored in the terminal and the facial recognition model; and

detect the first-type pictures based on a result of the matching for the first-type pictures being higher than a first preset value.

18. The terminal of claim 14, wherein the programming instructions further cause the at least one processor to be configured to:

extract feature values of the pictures stored in the terminal;

perform a matching between the feature values of the pictures stored in the terminal and a facial recognition model; and

detect the second-type pictures based on a result of the matching for the second-type pictures being less than a first preset value.