Unlock instant, AI-driven research and patent intelligence for your innovation.

Photo classification method

A classification method, photo technology, applied in still image data clustering/classification, still image data retrieval, instruments, etc., can solve problems such as no way to classify

Pending Publication Date: 2021-04-27
北京华安信联通信技术有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above problems can be solved, there is no way to classify when the photos contain some old photos and the old photos have no relevant electronic information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Photo classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1, there are 100 old photos, and 900 digital photos, first remake the old photos, obtain 100 remade photos, modify the shooting time in the 100 remade photos to the old photo shooting time, get 100 A remake photo with information, and then put 100 remake photos with shooting time information and the remaining 900 digital photos into the photo library, and compare the similarity of the avatar pictures in the high-quality library through the first method, that is First establish a face database, compare the features of the avatar pictures in the high-quality library with the feature combinations of the avatar pictures in the face database to determine whether they are the same person, and set the features of the avatar pictures in the high-quality library to be compared with the feature combinations of the face database. If the similarity of the feature combination of the avatar picture in the high-quality database is ≥80%, it is considered to be the same person...

Embodiment 2

[0061] Embodiment 2, there are 100 old photos, and 900 digital photos, first remake the old photos, obtain 100 remade photos, modify the shooting time in the 100 remade photos to the shooting time of the old photos, get 100 remake photos with shooting time information, then put 100 remake photos with shooting time information and the remaining 900 digital photos into the photo library, and use the first method to compare the similarity of the avatar pictures in the high-quality library Comparison, that is to compare the avatar pictures in the high-quality library with each other in turn to determine whether they are the same person, and set the similarity ≥ 80%, then it is considered the same person, set the similarity < 80%, and ≥ 50, then It is considered that they may be the same person, and if the similarity is set to <50%, then it is determined that they are not the same person; when the face database is compared with the corresponding similar database, if the number of av...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a photo classification method, which comprises the following steps of: 1, duplicating old photos; 2, modifying the shooting time of the copied old photo; 3, putting the copied old photo and photos except the old photo into a photo library; 4, cutting the face in the photo into a head portrait picture; step 5, identifying the quality of the head portrait picture to form a high-quality library and a low-quality library; 6, dividing the high-quality library into similar libraries according to the similarity of the head portrait pictures; 7, comparing the head portrait pictures in the face library with the head portrait pictures in the similar library; 8, comparing the photos in the low-quality library, and determining that the photos of the same person are moved into a corresponding face library; and 9, classifying the photos according to the face library. According to the invention, the old photos are copied and the information is manually edited, and the photos in different shooting periods are accurately identified, so that an accurate and reliable photo classification method is provided, and a large amount of photo screening and viewing time is saved.

Description

technical field [0001] The present invention generally relates to the technical field of artificial intelligence, and more specifically, relates to a photo classification method. Background technique [0002] With the development of smart terminal technology, the camera function of smart terminals is becoming more and more powerful. Most users are accustomed to using smart terminals such as mobile phones to take pictures, so that they can be viewed and shared with friends at any time. Photos taken by smart terminals such as mobile phones are saved in a system album folder by default, and photos downloaded or transferred by other smart terminals are saved in other folders. For the photos in the system album folder, some existing smart terminals can manage according to the distance of the shooting date; when a large number of photos are taken when traveling, etc., if you need to view the photos of a certain person, you need to spend a lot of time. The search process, or when ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06F16/55
CPCG06F16/55G06V40/172G06F18/22
Inventor 刘识田继忠白呢李欣林志贾庆丰
Owner 北京华安信联通信技术有限公司