A photo cropping method and system based on face recognition

A face recognition and photo technology, applied in character and pattern recognition, TV system parts, color TV parts and other directions, can solve the problem of high cost of use, complicated cutting operations, and no better optimization and help on the mobile terminal. and other problems to achieve the effect of improving the accuracy

Active Publication Date: 2018-08-24
CHENDU PINGUO TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, such a design will bring the following problems: 1. The cropping result is completely operated manually by the user, and it is very likely that the cropping result does not meet the size
2. The cutting operation is complicated, the learning threshold for users is high, and the use cost is high
Therefore, these traditional cropping methods are not well optimized and helpful for the operation interaction on the mobile terminal. The above problems need a new intelligent way to optimize and solve these problems

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
  • A photo cropping method and system based on face recognition
  • A photo cropping method and system based on face recognition
  • A photo cropping method and system based on face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 , the first photo cropping method based on face recognition provided by the present invention, comprising:

[0043] Step 1: Perform face detection on the captured image to obtain the face detection frame 1; in this embodiment, the face detection frame is obtained by using an existing third-party face detection application.

[0044] Step 2: Take the center point of the face detection frame 1 as the origin, and generate a rectangular cropping frame 2 with an aspect ratio of 4:3 according to the ratio of the area to the area of ​​the face detection frame 10:7, such as figure 1 shown.

[0045] Step 3: Cut out the part of the image other than the rectangular cropping frame 2.

Embodiment 2

[0047] When the aspect ratio of the image required by the user is greater than 4:3, the cropping process is as follows figure 1 and figure 2 :

[0048] Step 1: Perform face detection on the captured image to obtain face detection frame 1;

[0049] Step 2: Take the center point of the face detection frame 1 as the origin, and generate a rectangular cropping frame 2 with an aspect ratio of 4:3 according to the ratio of the area to the area of ​​the face detection frame 10:7;

[0050] Step 3: take the center point of the face detection frame as the origin of the rectangular cropping frame with an aspect ratio greater than 4:3, and take the length of the rectangular cropping frame with the aspect ratio as 4:3 as the origin of the rectangular cropping frame with an aspect ratio greater than 4:3 The length of the rectangular cropping frame is calculated according to the image aspect ratio required by the user to calculate the wide length of the rectangular cropping frame with an ...

Embodiment 3

[0055] When the aspect ratio of the image required by the user is less than 4:3, the cropping process is, continue to refer to figure 1 and figure 2 :

[0056] Step 1: Perform face detection on the captured image to obtain face detection frame 1;

[0057] Step 2: Take the center point of the face detection frame as the origin, and generate a rectangular cropping frame 2 with an aspect ratio of 4:3 according to the ratio of the area to the area of ​​the face detection frame: 10:7;

[0058] Step 3: Take the center point of the face detection frame as the origin of the rectangular cropping frame with an aspect ratio of less than 4:3, and take the width of the rectangular cropping frame with an aspect ratio of 4:3 as the aspect ratio of less than 4:3 The width of the rectangular cropping frame is calculated according to the image aspect ratio required by the user to calculate the long length of the rectangular cropping frame with an aspect ratio less than 4:3, thereby obtaining...

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 discloses a photo cropping method and system based on face recognition, relates to the photographing technology of mobile terminals, and aims to provide a simple and easy-to-operate fixed aspect ratio for the defects that existing mobile devices are difficult to take standard photos. How to get photos. The technical points of the present invention include: step 1: perform face detection on the captured image to obtain a face detection frame; step 2: take the center point of the face detection frame as the origin, and generate according to the ratio of the area to the area of ​​the face detection frame 10:7 A rectangular cropping frame with a length-to-width ratio of 4:3; step 3: crop the part of the image outside the rectangular cropping frame.

Description

technical field [0001] The invention relates to a photographing technology of a mobile terminal, in particular to a simple and easy-to-operate method for obtaining photographs with fixed aspect ratios. Background technique [0002] With the development of mobile terminals, the camera functions of both mobile phones and tablet computers are becoming more and more powerful, and taking pictures through mobile devices has become an indispensable part of people's lives. Users also tend to use camera software more frequently in their daily life, and the application scenarios are more extensive. [0003] However, portrait photos that need to be used on specific occasions have strict requirements on the proportion of faces in the photos (for example: ID photos, etc.). At present, when users need standard photos such as ID photos, they still need to go to a photo studio to take pictures, and the production cost is very high. [0004] In fact, the current camera functions of mobile ...

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 Patents(China)
IPC IPC(8): G06K9/00H04N5/232
CPCG06V40/161H04N23/611
Inventor 李灵溪
Owner CHENDU PINGUO TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap