CN111242086A - Image exposure adjusting method based on face recognition - Google Patents
Image exposure adjusting method based on face recognition Download PDFInfo
- Publication number
- CN111242086A CN111242086A CN202010071833.2A CN202010071833A CN111242086A CN 111242086 A CN111242086 A CN 111242086A CN 202010071833 A CN202010071833 A CN 202010071833A CN 111242086 A CN111242086 A CN 111242086A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- exposure
- face recognition
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the neighborhood of face recognition technology, in particular to an image exposure adjusting method based on face recognition, wherein a camera shoots and acquires a frame of RAW image in real time; adjusting the whole image to reach the required exposure value and transmitting the exposure value to the main controller; executing, by the master controller, a face recognition algorithm; when the camera detects a face, carrying out brightness statistics on a face area and a non-face area of the image; acquiring the brightness of a statistical area, and adjusting exposure according to the brightness of the human face to obtain a frame of image frame 1; meanwhile, according to the brightness of the non-face area, adjusting exposure to obtain a frame image frame 2; synthesizing the two frames of images to obtain a required image and executing a face recognition algorithm again; the method and the device solve the problems that the human face is dark under normal exposure due to factors such as illumination and the like, and the overexposure of the non-human face area of the video is caused based on the human face exposure condition, obtain the image with better background and human face exposure after synthesis, ensure better snapshot human face illumination and video acquisition effect, and prevent the video background from being over-exploded.
Description
Technical Field
The invention relates to a face recognition technology neighborhood, in particular to an image exposure adjusting method applied to face recognition.
Background
With the continuous progress of science and technology, a face recognition technology for performing identity recognition based on face feature information of a person, namely, a biotechnology, is widely applied to various neighborhood scenes such as security, finance, traffic, education, medical treatment and the like.
At present, the quality of pictures grabbed by a camera in a good and stable environment of an indoor illumination environment is good, and the face recognition effect is stable and accurate. However, in the outdoor environment or in the scene where the illumination is easy to change, the quality of the captured picture is poor due to various physical factors, so that the difference between the actual face recognition effect and the expected face recognition effect is large. There is a problem that the exposure based on a large scene of a general camera usually results in a dark image, and the exposure based on a human face and a background image are usually overexposed, so that the required recognition effect cannot be achieved.
Disclosure of Invention
The invention aims to solve the technical problems that the human face is dark under normal exposure due to factors such as illumination and the like, and the non-human face area of the video is overexposed based on the human face exposure condition.
The technical scheme adopted by the invention is as follows: the image exposure adjusting method based on face recognition comprises the following steps:
step S1, shooting and acquiring a frame of RAW image in real time by a camera;
step S2, adjusting the whole image to reach the required exposure value and transmitting to the main controller; executing, by the master controller, a face recognition algorithm;
step S3, when the camera detects a face, the brightness statistics is carried out on the face area and the non-face area of the image;
step S4, obtaining the brightness of the statistical region, adjusting exposure according to the brightness of the human face to obtain a frame image frame 1; meanwhile, according to the brightness of the non-face area, adjusting exposure to obtain a frame image frame 2;
in step S5, the two frames of images are combined to obtain a desired image, and the face recognition algorithm is executed again.
Further, in step S2, the face recognition algorithm uses the MTCN algorithm to obtain the face region position.
Further, in step S3, the luminance of the region is obtained by calculating the expectation of the gray histogram of the region.
Further, in step S3, if no human face is detected, the method returns to step S2.
Further, in step S5, the synthesized two frames of images are obtained by using a laplacian pyramid method, specifically, gradient mean calculation of 8 neighborhoods is performed on the same point p (x, y) of the two frames of images in the same layer of the laplacian pyramid, and a point with a large gradient mean is used as a corresponding value of a new image in the layer of the laplacian pyramid.
Further, a laplacian pyramid of the synthesized image is obtained, and an image is reconstructed from the laplacian pyramid.
The invention has the beneficial effects that:
1) the method and the device solve the problems that the human face is dark under normal exposure due to factors such as illumination and the like, and overexposure of a non-human face area of the video is caused based on human face exposure conditions, and obtain the image with better background and human face exposure after synthesis.
2) Compared with a common camera exposure method, the design scheme has the advantages that the face shot by the design scheme is better in illumination and not dark, and meanwhile, compared with a common face-based exposure method, the video acquisition effect is better, and the video background is not over-exploded.
Drawings
Fig. 1 is a schematic flow chart of an image exposure adjustment method based on face recognition according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
According to the scheme, luminance statistics is carried out on a face region and a non-face region respectively by combining the face position region given by a face recognition algorithm after a camera acquires a frame of RAW image, exposure is adjusted according to the face luminance to obtain a frame of image frame1, exposure is adjusted according to the luminance of the non-face region to obtain a frame of image frame2, two frames of images are synthesized, and finally an image with good background and face exposure after one frame of synthesis is obtained.
The image exposure adjustment method based on face recognition comprises the following specific working procedures:
after a camera acquires a frame of RAW image, combining a face position area given by a face recognition algorithm, the face recognition algorithm obtaining the face area position by adopting an MTCN algorithm, then respectively carrying out brightness statistics on the face area and a non-face area, wherein the face brightness is obtained by calculating the expectation of a face area gray histogram, and similarly, the non-face area brightness is obtained by calculating the expectation of a non-face area gray histogram, adjusting exposure according to the face brightness to obtain a frame of image frame1, then adjusting exposure according to the brightness of the non-face area to obtain a frame of image frame2, synthesizing the two frames of images, respectively carrying out 8-layer Laplace pyramid transformation on the two frames of images by a Laplace pyramid method, fusing each layer of the pyramid (respectively carrying out 8-neighborhood gradient mean values on the same point p (x, y) of the same layer of the two image pyramids, the larger the gradient mean value is, the clearer the image is, and the point with the large gradient mean value is used as the corresponding value of the Laplacian pyramid of the new image on the layer), so that the Laplacian pyramid of the fused image is obtained, an image is reconstructed by the pyramid, and finally a frame of image with better background and face exposure after synthesis is obtained.
Claims (6)
1. The image exposure adjusting method based on the face recognition is characterized by comprising the following steps of:
step S1, shooting and acquiring a frame of RAW image in real time by a camera;
step S2, adjusting the whole image to reach the required exposure value and transmitting to the main controller; executing, by the master controller, a face recognition algorithm;
step S3, when the camera detects a face, the brightness statistics is carried out on the face area and the non-face area of the image;
step S4, obtaining the brightness of the statistical region, adjusting exposure according to the brightness of the human face to obtain a frame image frame 1; meanwhile, according to the brightness of the non-face area, adjusting exposure to obtain a frame image frame 2;
in step S5, the two frames of images are combined to obtain a desired image, and the face recognition algorithm is executed again.
2. The image exposure adjustment method based on face recognition according to claim 1, characterized in that: in step S2, the face recognition algorithm uses the MTCN algorithm to obtain the face region position.
3. The image exposure adjustment method based on face recognition according to claim 1, characterized in that: in step S3, the luminance of the region is obtained by calculating the expectation of the gray histogram of the region.
4. The image exposure adjustment method based on face recognition according to claim 1, characterized in that: in step S3, if no face is detected, the process returns to step S2.
5. The image exposure adjustment method based on face recognition according to claim 1, characterized in that: in step S5, the two synthesized frames of images are obtained by using a laplacian pyramid method, specifically, gradient mean values of 8 neighborhoods are respectively calculated at the same point p (x, y) of the two frames of images in the same layer of the laplacian pyramid, and the point with the large gradient mean value is used as a corresponding value of a new image in the layer of the laplacian pyramid.
6. The image exposure adjustment method based on face recognition according to claim 1 or 5, characterized in that: and obtaining the Laplacian pyramid of the synthesized image, and reconstructing an image by the Laplacian pyramid.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010071833.2A CN111242086A (en) | 2020-01-21 | 2020-01-21 | Image exposure adjusting method based on face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010071833.2A CN111242086A (en) | 2020-01-21 | 2020-01-21 | Image exposure adjusting method based on face recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111242086A true CN111242086A (en) | 2020-06-05 |
Family
ID=70876480
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010071833.2A Withdrawn CN111242086A (en) | 2020-01-21 | 2020-01-21 | Image exposure adjusting method based on face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111242086A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114007020A (en) * | 2021-10-12 | 2022-02-01 | 深圳创维-Rgb电子有限公司 | Image processing method and device, intelligent terminal and computer readable storage medium |
-
2020
- 2020-01-21 CN CN202010071833.2A patent/CN111242086A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114007020A (en) * | 2021-10-12 | 2022-02-01 | 深圳创维-Rgb电子有限公司 | Image processing method and device, intelligent terminal and computer readable storage medium |
CN114007020B (en) * | 2021-10-12 | 2022-11-29 | 深圳创维-Rgb电子有限公司 | Image processing method and device, intelligent terminal and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9692964B2 (en) | Modification of post-viewing parameters for digital images using image region or feature information | |
CN110619593B (en) | Double-exposure video imaging system based on dynamic scene | |
KR101699919B1 (en) | High dynamic range image creation apparatus of removaling ghost blur by using multi exposure fusion and method of the same | |
US10764496B2 (en) | Fast scan-type panoramic image synthesis method and device | |
CN110599433B (en) | Double-exposure image fusion method based on dynamic scene | |
CN110378859B (en) | Novel high dynamic range image generation method | |
US9129381B2 (en) | Modification of post-viewing parameters for digital images using image region or feature information | |
CN111986129B (en) | HDR image generation method, equipment and storage medium based on multi-shot image fusion | |
CN108111749B (en) | Image processing method and device | |
CN105827935B (en) | A kind of method and terminal of terminal sectional drawing | |
WO2016019770A1 (en) | Method, device and storage medium for picture synthesis | |
US20120249841A1 (en) | Scene enhancements in off-center peripheral regions for nonlinear lens geometries | |
CN108156369B (en) | Image processing method and device | |
JP2015180062A (en) | Method for processing video sequence and device for processing video sequence | |
KR20090078583A (en) | Method and system for processing for low light level image | |
CN112396562A (en) | Disparity map enhancement method based on RGB and DVS image fusion in high-dynamic-range scene | |
CN112419181B (en) | Method for enhancing detail of wide dynamic infrared image | |
WO2016141810A1 (en) | Image processing method for shooting terminal and apparatus therefor | |
CN107734271B (en) | 1,000,000,000 pixel video generation method of high dynamic range | |
CN110636227B (en) | High dynamic range HDR image synthesis method and high-speed camera integrating same | |
JP2015082768A (en) | Image processing device, image processing method, program, and storage medium | |
CN108429887A (en) | A kind of image processing method and device | |
CN114862698A (en) | Method and device for correcting real overexposure image based on channel guidance | |
Yang et al. | Learning event guided high dynamic range video reconstruction | |
CN112153240B (en) | Method and device for adjusting image quality and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200605 |