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

Image processing methods and devices

An image and filter processing technology, applied in the field of face recognition, to achieve the effect of improving performance, fast processing speed, and improving illumination robustness

Inactive Publication Date: 2016-03-16
SHENZHEN YIHUA COMP +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present invention is to propose a method and device for image processing, aiming to solve the problem of how to effectively eliminate the illumination changes of human face images

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
  • Image processing methods and devices
  • Image processing methods and devices
  • Image processing methods and devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] refer to figure 1 , figure 1 It is a schematic flowchart of the first embodiment of the method for processing an image according to the embodiment of the present invention.

[0048] In Embodiment 1, the method for processing an image includes:

[0049] Step 101, obtaining the high-frequency sub-band coefficients of the image to be processed;

[0050] Preferably, the acquisition of the high-frequency sub-band coefficients of the image to be processed includes:

[0051] The image to be processed is decomposed by non-sampled Shearlet transform to obtain high-frequency sub-band coefficients.

[0052] Specifically, the non-sampled Shearlet transform is introduced into the field of face recognition illumination preprocessing. Compared with the non-subsampled contourlet transform (NSCT), the non-sampled Shearlet transform is faster.

[0053] Step 102, performing illumination filtering processing on the high-frequency sub-band coefficients to obtain a filtered high-frequenc...

Embodiment 2

[0063] refer to figure 2 , figure 2It is a schematic flowchart of the second embodiment of the image processing method according to the embodiment of the present invention.

[0064] On the basis of Embodiment 1, the method also includes:

[0065] Step 104, obtaining the low-frequency sub-band coefficients of the image to be processed;

[0066] Specifically, the image is decomposed by non-sampling Shearlet transform to obtain low-frequency sub-band coefficients.

[0067] Step 105, performing illumination filtering on the low-frequency subband coefficients through the logarithmic total variation quotient image model LTVQI to obtain a filtered low-frequency coefficient subband set;

[0068] Specifically, the logarithmic total variation quotient image model LTVQI is used to de-illuminate the low-frequency sub-band coefficients to obtain face detail information in the low-frequency sub-band. The LTVQI model has good edge-preserving properties for low-frequency illumination re...

Embodiment 3

[0073] refer to image 3 , image 3 It is a schematic flowchart of the third embodiment of the method for processing an image according to the embodiment of the present invention.

[0074] On the basis of the second embodiment, before obtaining the high-frequency sub-band coefficients of the image to be processed, it also includes:

[0075] Step 107, performing logarithmic threshold transformation on the image to be processed.

[0076] Specifically, the logarithmic domain transformation is performed on the face image to obtain the image. The logarithmic transformation converts the product operation into an addition and subtraction operation, which is beneficial to the addition and subtraction operation processing of the threshold function in the subsequent step.

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

Embodiments of the invention disclose image processing methods and devices. A high-frequency sub band coefficient of a to-be-processed image is obtained, illumination filtering processing is performed on the high-frequency sub band coefficient, and then a high-frequency coefficient sub band set after filtering is obtained. A first to-be-processed image after illumination filtering processing is obtained according to the high-frequency coefficient sub band set after the filtering. The processing speed is rapid, so the utilization rate of human face information is improved; and an illumination change of the image can be effectively eliminated, human face identification performance is improved, and illumination robustness of a human face identification system is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face recognition, and in particular to a method and device for processing images. Background technique [0002] Face recognition is one of the most successful applications in the field of image analysis and understanding. It has developed rapidly in recent years, but its performance is still affected by many factors such as illumination, viewing angle, occlusion, and age. Among the many influencing factors, illumination change is one of the key factors affecting the recognition performance of the system. Due to the 3D structure of the face, the shadow cast by the light will strengthen or weaken the original face features. Especially at night, the facial shadows caused by insufficient light will lead to a sharp drop in the recognition rate, making it difficult for the system to meet practical requirements. At the same time, theory and experiment also prove that the difference caused ...

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): G06K9/00
CPCG06V40/16
Inventor 翟云龙
Owner SHENZHEN YIHUA COMP