Methods and devices for classifying pictures

• US 9,779,294 B2
• Filed: 11/04/2015
• Issued: 10/03/2017
• Est. Priority Date: 12/31/2014
• Status: Active Grant

• Current Assignee: METHODS AND DEVICES FOR CLASSIFYING PICTURES, Xiaomi Inc. (Xiaomi Corp.)
• Original Assignee: Xiaomi Inc. (Xiaomi Corp.)
• Inventors: Zhang, Tao, Long, Fei, Chen, Zhijun
• Primary Examiner(s): Bayat, Ali
• Application Number:
  US14/932,561
• Publication Number:
  US 20160189008A1
• Time in Patent Office: 699 Days
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

Methods and devices are provided for classifying pictures. In the method, the device obtains a picture to be classified. The device determines a class of the picture according to feature information of the picture, in which the class includes a text picture class and a non-text picture class. The device classifies the picture according to the class of each picture.

Claims

1. A method for classifying pictures, comprising:

obtaining, by a device comprising a processor, a picture to be classified;

determining, by the device, a class of the picture according to feature information of the picture, wherein the class comprises a text picture class and a non-text picture class; and

classifying, by the device, the picture according to the class of the picture;

after classifying the picture according to the class of the picture, the method further comprising at least one of;

adding the classified picture to a folder corresponding to the class of the picture and displaying the folder; and

adding the classified picture to a folding picture set corresponding to the class of the picture and displaying the folding picture set.

2. The method according to claim 1, further comprising:

if the picture belongs to the text picture class, obtaining valid time information and current time information of text information in the picture;

detecting whether an expiration time of the picture exceeds a first predetermined period according to the valid time information and the current time information; and

if yes, deleting the picture.

3. The method according to claim 2, wherein obtaining valid time information and current time information of text information in the picture comprises:

reading the valid time information from a text recorded in the picture or receiving inputted valid time information when storing the picture; and

obtaining the current time information.

4. The method according to claim 2, wherein deleting the picture comprises one of the following:

generating and displaying a prompt message, receiving a deleting instruction triggered by a user according to the prompt message, and deleting the picture according to the deleting instruction, wherein the prompt message is configured to prompt that the picture has expired;

transferring the picture to a recycle buffer, obtaining a storage duration of the picture in the recycle buffer, and deleting the picture if the storage duration is greater than a second predetermined period; and

transferring the picture to the recycle buffer, receiving an emptying instruction for emptying the recycle buffer, and deleting the picture according to the emptying instruction.

5. The method according to claim 1, wherein displaying the folding picture set comprises:

extracting a representation picture with a best quality from the folding picture set or extracting a representation picture with a latest storage time from the folding picture set; and

displaying the representation picture of the folding picture set without displaying other pictures in the folding picture set, or displaying the representation picture of the folding picture set and edge portions of the other pictures.

6. The method according to claim 1, wherein determining the class of the picture according to feature information of the picture comprises:

extracting feature information of each pixel in the picture;

determining the feature information according to a Support Vector Machine model, wherein the Support Vector Machine model is obtained by training sample pictures, and the sample pictures comprise text pictures and non-text pictures; and

determining the class of the picture according to a determining result.

7. The method according to claim 6, further comprising:

normalizing resolutions of the sample pictures to a predetermined resolution;

extracting feature information of each pixel in each normalized sample picture;

calculating a histogram of each sample picture block, wherein the sample picture block is obtained by dividing an area of the sample picture; and

obtaining the Support Vector Machine model according to types of the sample pictures and the histograms.

8. The method according to claim 1, wherein the feature information comprises a Gabor feature value or a gradient direction value.

9. A device for classifying pictures, comprising:

a processor;

a memory configured to store instructions executable by the processor;

wherein the processor is configured to;

obtain a picture to be classified;

determine a class of the picture according to feature information of the picture, wherein the class comprises a text picture class and a non-text picture class; and

classify the picture according to the class of the picture;

wherein the processor is further configured to;

add the classified picture to a folder corresponding to the class of the picture and display the folder;

or

add the classified picture to a folding picture set corresponding to the class of the picture and display the folding picture set.

10. The device according to claim 9, wherein the processor is further configured to:

if the picture belongs to the text picture class, obtain valid time information and current time information of text information in the picture;

detect whether an expiration time of the picture exceeds a first predetermined period according to the valid time information and the current time information; and

if yes, delete the picture.

11. The device according to claim 10, wherein the processor is further configured to obtain valid time information and current time information of text information in the picture by:

reading the valid time information from a text recorded in the picture or receiving inputted valid time information when storing the picture; and

obtaining the current time information.

12. The device according to claim 10, wherein the processor is further configured to delete the picture by using one of the following acts:

generating and displaying a prompt message, receiving a deleting instruction triggered by a user according to the prompt message, and deleting the picture according to the deleting instruction, wherein the prompt message is configured to prompt that the picture has expired;

transferring the picture to a recycle buffer, obtaining a storage duration of the picture in the recycle buffer, and deleting the picture if the storage duration is greater than a second predetermined period; and

transferring the picture to the recycle buffer, receiving an emptying instruction for emptying the recycle buffer, and deleting the picture according to the emptying instruction.

13. The device according to claim 9, wherein displaying the folding picture set comprises:

extracting a representation picture with a best quality from the folding picture set or extracting a representation picture with a latest storage time from the folding picture set; and

displaying the representation picture of the folding picture set without displaying other pictures in the folding picture set, or displaying the representation picture of the folding picture set and edge portions of the other pictures.

14. The device according to claim 9, wherein the processor is configured to determine the class of the picture according to feature information of the picture by:

extracting feature information of each pixel in the picture;

determining the feature information according to a Support Vector Machine model, wherein the Support Vector Machine model is obtained by training sample pictures, and the sample pictures comprise text pictures and non-text pictures; and

determining the class of the picture according to a determining result.

15. The device according to claim 14, wherein the processor is further configured to:

normalize resolutions of the sample pictures to a predetermined resolution;

extract feature information of each pixel in each normalized sample picture;

calculate a histogram of each sample picture block, wherein the sample picture block is obtained by dividing an area of the sample picture; and

obtain the Support Vector Machine model according to types of the sample pictures and the histograms.

16. The device according to claim 9, wherein the feature information comprises a Gabor feature value or a gradient direction value.

17. A non-transitory computer-readable storage medium having stored therein instructions that, when executed by a processor of a terminal device, causes the terminal device to perform acts comprising:

obtaining a picture to be classified;

determining a class of the picture according to feature information of the picture, wherein the class comprises a text picture class and a non-text picture class; and

classifying the picture according to the class of the picture;

wherein the terminal device is further caused to perform at least one of;

adding the classified picture to a folder corresponding to the class of the picture and displaying the folder; and

adding the classified picture to a folding picture set corresponding to the class of the picture and displaying the folding picture set.

18. The non-transitory computer-readable storage medium according to claim 17, wherein the instructions further causes the terminal to:

extract feature information comprising a Gabor feature value or a gradient direction value from sample pictures of different classes; and

obtain a Support Vector Machine model by training the sample pictures using the extracted feature information that comprises the Gabor feature value or the gradient direction value.