CN109089158B - Human face image quality parameter processing system for smart television and implementation method thereof - Google Patents
Human face image quality parameter processing system for smart television and implementation method thereof Download PDFInfo
- Publication number
- CN109089158B CN109089158B CN201810819373.XA CN201810819373A CN109089158B CN 109089158 B CN109089158 B CN 109089158B CN 201810819373 A CN201810819373 A CN 201810819373A CN 109089158 B CN109089158 B CN 109089158B
- Authority
- CN
- China
- Prior art keywords
- face
- image
- image quality
- standard
- video
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000000694 effects Effects 0.000 claims abstract description 34
- 230000008859 change Effects 0.000 claims description 57
- 239000000284 extract Substances 0.000 claims description 10
- 230000001629 suppression Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 2
- 230000001052 transient effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 9
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
-
- 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
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a human face image quality parameter processing system for an intelligent television and an implementation method thereof, wherein the system comprises a video storage module, an object recognition module and an image quality functional module, wherein the video storage module is respectively connected with the object recognition module and the image quality functional module; the video storage module is used for storing the video to be processed or the processed video; the object recognition module is used for extracting video pixel information which accords with the human face contour characteristic and the skin color characteristic in the video to be processed to form human face area information in the video; the image quality function module is internally pre-stored with the image optimal image quality effect standard and is used for receiving the face area information and processing the face image in the face area information according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard. The human face image quality parameter processing system for the intelligent television and the implementation method thereof can enable the intelligent television to carry out special processing on the human face image quality parameters when displaying common television signals, thereby realizing the optimal display effect.
Description
Technical Field
The invention relates to the technical field of intelligent television systems, in particular to a human face image quality parameter processing system for an intelligent television and an implementation method thereof.
Background
The face recognition technology has been developed rapidly in recent years, and the face image of a person can be recognized based on face recognition to acquire related information, so that the face recognition technology can be widely applied to various fields.
With the rapid development of the intelligent television SOC and the software system, the bottom interface of the intelligent algorithm is provided, and technologies such as face recognition provide possibility for the function expansion and technical breakthrough of the intelligent television. The image quality adjusting technology of the television and the face recognition technology are combined, so that a better portrait display effect can be realized.
Disclosure of Invention
The invention aims to provide a human face image quality parameter processing system for an intelligent television and an implementation method thereof based on the background technology, so that the intelligent television can perform special processing on human face image quality parameters when displaying common television signals, and the optimal display effect is realized.
In order to achieve the technical effects, the invention adopts the following technical scheme:
a human face image quality parameter processing system for an intelligent television comprises a video storage module, an object recognition module and an image quality functional module, wherein the video storage module is respectively connected with the object recognition module and the image quality functional module; the video storage module is used for storing the video to be processed or the processed video; the object recognition module is used for extracting video pixel information which accords with face contour characteristics and skin color characteristics in a video to be processed and forming face region information in the video; the image quality function module is internally pre-stored with an image optimal image quality effect standard and is used for receiving the face region information and processing the face image in the face region information according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard;
the face image quality parameter processing system for the intelligent television can pre-store videos to be played in the television in the video storage module, the object recognition module extracts video pixel information in the videos according with face contour characteristics and skin color characteristics to form face area information in the videos, the image quality function module performs face image quality parameter processing on face objects contained in the face area information according to the best image quality effect standard of the images stored in the image quality function module, and the processed images are played in the television finally, so that better viewing experience is brought to users.
Furthermore, a face contour feature standard is prestored in the object recognition module, the object recognition module extracts the video pixel information of the face contour feature and the skin color feature of the face object only when the face object in the recognized video meets the face contour feature standard, the face contour feature standard is prestored in the object recognition module, and only the image meeting the face contour feature standard is subjected to subsequent processing, so that the processing efficiency of the system and the processing effectiveness can be effectively improved.
Further, the face contour feature criteria include a criterion of a proportion of the face object in the video picture and a picture proportion change criterion of the face object in the continuous multi-frame images, and the image is subjected to subsequent processing only when the criterion of the proportion of the face object in the video picture and the picture proportion change criterion of the face object in the continuous multi-frame images are simultaneously satisfied.
Furthermore, the standard of the proportion of the face object in the video image is a face object image proportion threshold value prestored in the object recognition module, when the proportion of the face object in the video image is not less than the face object image proportion threshold value, the face object meets the standard of the proportion of the face object in the video image, and the face object image proportion threshold value is set so as to screen out a more main face image in the image and perform image quality parameter processing on the face image, so that the processing efficiency of the system can be effectively improved.
Further, the picture ratio change criterion at least includes a size change criterion of the face object in the continuous multi-frame images and a relative position change criterion of the face object in the continuous multi-frame images.
Furthermore, the size change standard of the face object in the continuous multi-frame images is a face object size change threshold pre-stored in the object recognition module, when the size change value of the face object in the continuous multi-frame images does not exceed the face object size change threshold, the face object meets the size change standard of the face object in the continuous multi-frame images, the change of the picture proportion of the generally important face image in the video picture is not large, the face object size change threshold is set to filter the unimportant face image, the face images which possibly meet the standard of the proportion of the face object in the video picture only in one frame picture are avoided, and the subsequent pictures do not meet the standard or even do not process the face images, so that the processing efficiency is reduced;
and/or the relative position change standard of the face object in the continuous multi-frame images is a face object relative position change threshold value prestored in the object identification module, and when the relative position change value of the face object in the continuous multi-frame images does not exceed the face object relative position change threshold value, the face object meets the relative position change standard of the face object in the continuous multi-frame images; generally, the change of the picture position of the more important face image in the video picture is not too large, so that the unimportant face image can be filtered through the face object relative position change threshold.
Further, the image best quality effect standard at least comprises a skin color phase standard, a color saturation standard, a color brightness standard, a noise suppression standard, a picture definition standard and/or a local contrast standard.
Furthermore, the image quality function module at least comprises a skin color phase adjusting unit, a color saturation adjusting unit, a color brightness adjusting unit, a noise suppression adjusting unit, a picture definition adjusting unit and/or a local contrast adjusting unit.
Meanwhile, the invention also discloses an implementation method of the human face image quality parameter processing system for the smart television, which comprises the following steps:
A. the object identification module reads a frame of image in a video to be processed in the video storage module;
B. the object recognition module reads the read image to perform face recognition to judge whether the image contains a face object to be processed, and the step C is performed when the image contains the face object;
C. the object recognition module detects whether the proportion of the face object in the picture reaches a preset proportion standard or not, and the step D is entered when the proportion of the face object in the picture meets the preset proportion standard;
D. the object identification module reads the proportion change condition of a face object in a picture in continuous multi-frame images subsequent to a current frame image;
E. judging whether human face image quality parameter processing needs to be carried out on the image according to the proportion change condition; if the judgment result is that the processing is needed, the step F is carried out, otherwise, the step I is directly carried out;
F. the object recognition module extracts video pixel information of contour features and skin color features of the face object in the image as an object recognition result;
G. the image quality function module judges whether the object recognition result meets the image optimal image quality effect standard or not;
H. the image quality function module processes the face image in the object recognition result according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard;
I. and displaying the image in the intelligent television.
If the human face image quality parameter processing is judged not to be required to be carried out on the image in the step E, the transitional parameters in the image are adjusted through the image quality function module, and then the step I is carried out; after the image without the human face image quality parameter processing is adjusted by the partial transitional parameters, the image with higher image quality can be further provided for the user, for example, the exposure of the overexposed image is properly adjusted, and the overall texture of the image is favorably improved.
Compared with the prior art, the invention has the following beneficial effects:
according to the face image quality parameter processing system for the smart television and the implementation method thereof, the image quality adjusting technology of the television can be combined with the face recognition technology, so that the smart television has a better image display effect, the image quality processing is performed on the face object region mainly based on the face recognition and the image pixel information, the image display effect is improved, and finally the processed image is played in the television, so that better viewing experience is brought to a user.
Drawings
Fig. 1 is a schematic flow chart of an implementation method of a human face image quality parameter processing system for a smart television according to the present invention.
Detailed Description
The invention will be further elucidated and described with reference to the embodiments of the invention described hereinafter.
Example (b):
the first embodiment is as follows:
a human face image quality parameter processing system for an intelligent television comprises a video storage module, an object recognition module and an image quality function module, wherein the video storage module is respectively connected with the object recognition module and the image quality function module, and the video storage module is used for storing videos to be processed or processed videos.
The object recognition module is used for extracting video pixel information which accords with the face contour characteristic and the skin color characteristic in the video to be processed and forming face region information in the video.
Specifically, a face contour feature standard is prestored in the object recognition module, the object recognition module extracts the video pixel information of the face contour feature and the skin color feature of the face object only when the face object in the recognized video meets the face contour feature standard, the face contour feature standard is prestored in the object recognition module, and only the image meeting the face contour feature standard is subjected to subsequent processing, so that the processing efficiency and the processing effectiveness of the system can be effectively improved.
In this embodiment, the face contour feature criteria include a criterion of a proportion of the face object in the video picture and a picture proportion change criterion of the face object in the continuous multi-frame images, and the image is subjected to subsequent processing only when the criterion of the proportion of the face object in the video picture and the picture proportion change criterion of the face object in the continuous multi-frame images are simultaneously satisfied.
Specifically, the standard of the proportion of the face object in the video image is a face object image proportion threshold value prestored in the object identification module, when the proportion of the face object in the video image is not less than the face object image proportion threshold value, the face object meets the standard of the proportion of the face object in the video image, the face object image proportion threshold value is set so as to screen out a more main face image in the image and carry out image quality parameter processing on the face image, and the processing efficiency of the system can be effectively improved.
The frame ratio change criterion at least includes a size change criterion of the face object in the continuous multi-frame images and a relative position change criterion of the face object in the continuous multi-frame images.
The size change standard of the face object in the continuous multi-frame images is a face object size change threshold value prestored in the object recognition module, when the size change value of the face object in the continuous multi-frame images does not exceed the face object size change threshold value, the face object meets the size change standard of the face object in the continuous multi-frame images, the change of the picture proportion of the face image which is generally more important in the video picture is not larger, the face image which is not important can be filtered by setting the face object size change threshold value, the face images which possibly meet the standard of the proportion of the face object in the video picture in one frame picture are avoided, and the processing efficiency is reduced because the face images which do not meet the standard or even do not appear in the subsequent pictures.
The relative position change standard of the face object in the continuous multi-frame images is a face object relative position change threshold value prestored in the object identification module, and when the relative position change value of the face object in the continuous multi-frame images does not exceed the face object relative position change threshold value, the face object meets the relative position change standard of the face object in the continuous multi-frame images; generally, the change of the picture position of the more important face image in the video picture is not too large, so that the unimportant face image can be filtered through the face object relative position change threshold.
The image quality function module is internally pre-stored with an image optimal image quality effect standard and is used for receiving the face area information and processing the face image in the face area information according to the image optimal image quality effect standard so as to meet the image optimal image quality effect standard; specifically, the image quality optimization effect criteria at least include a skin color phase criterion, a color saturation criterion, a color brightness criterion, a noise suppression criterion, a picture definition criterion, and a local contrast criterion.
In this embodiment, the image quality function module at least includes a skin color phase adjustment unit, a color saturation adjustment unit, a color brightness adjustment unit, a noise suppression adjustment unit, a picture definition adjustment unit, and a local contrast adjustment unit, that is, the image quality function module adjusts the skin color phase of the human face object to a standard parameter range through the skin color phase adjustment unit, adjusts the color saturation of the human face object to a standard parameter range through the color saturation adjustment unit, adjusts the color brightness of the human face object to the standard parameter range through the color brightness adjustment unit, and the like, and the specific standard parameter ranges of the skin color phase standard, the color saturation standard, the color brightness standard, the noise suppression standard, the picture definition standard, and the local contrast standard may also be set according to the display standard desired by the user.
When the human face image quality parameter processing system for the intelligent television is used specifically, the specific working principle is as follows: the object recognition module extracts video pixel information which accords with face contour characteristics and skin color characteristics in a video to be processed and forms face region information in the video; the image quality function module calls related functions to process the complexion phase, the color saturation, the color brightness, the noise suppression, the image definition and the local contrast in the face area according to the face area information.
Specifically, the object recognition module analyzes each frame of image in the video, and determines whether an object to be processed exists based on a face recognition technology, if a face object exists in the video, the proportion of a face region in a picture is detected, when the proportion is higher than a set threshold value, the change condition of the proportion of the corresponding object picture in the subsequent 2-3 frames of images is continuously read (the change condition of the proportion of the picture in the embodiment at least comprises a size change condition, a relative position change condition and the like), the object to be processed is determined to be in a suitable processing state, and at the moment, video pixel information such as the contour feature, the skin color feature and the like of the face object is extracted to be used as an object recognition result.
The image quality function module extracts an object recognition result, judges whether a preset optimal image quality effect (the optimal image quality effect standard of the image can be a database containing parameters such as skin color phase, color saturation, color brightness, noise suppression, image definition, local contrast and the like) is met or not according to the parameters such as the overall brightness, the contrast and the like of the image, and if the deviation is large, related functions are called to process the image in the face area. The image quality processing method can also be used for fine adjustment or effect display by designing a single parameter control switch.
The face image quality parameter processing system for the intelligent television can pre-store videos to be played in the television in the video storage module, the object recognition module extracts video pixel information in the videos according with face contour characteristics and skin color characteristics to form face area information in the videos, the image quality function module performs face image quality parameter processing on face objects contained in the face area information according to the best image quality effect standard of the images stored in the image quality function module, and the processed images are played in the television finally, so that better viewing experience is brought to users.
Example two
As shown in fig. 1, the implementation method of the human face image quality parameter processing system for the smart television includes the following steps:
A. the object identification module reads a frame of image in a video to be processed in the video storage module;
B. the object recognition module reads the read image to perform face recognition to judge whether the image contains a face object to be processed, and the step C is performed when the image contains the face object;
C. the object recognition module detects whether the proportion of the face object in the picture reaches a preset proportion standard or not, and the step D is entered when the proportion of the face object in the picture meets the preset proportion standard;
D. the object identification module reads the proportion change condition of a face object in a picture in continuous multi-frame images subsequent to a current frame image;
E. judging whether human face image quality parameter processing needs to be carried out on the image according to the proportion change condition; if the judgment result is that the processing is needed, the step F is carried out, otherwise, the step I is directly carried out;
F. the object recognition module extracts video pixel information of contour features and skin color features of the face object in the image as an object recognition result;
G. the image quality function module judges whether the object recognition result meets the image optimal image quality effect standard or not;
H. the image quality function module processes the face image in the object recognition result according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard;
I. and displaying the image in the intelligent television.
Preferably, in step E, if it is determined that the face image quality parameter processing is not required for the image, the image quality function module adjusts the transient parameter in the image and then the process proceeds to step I; after the image without the human face image quality parameter processing is adjusted by the partial transitional parameters, the image with higher image quality can be further provided for the user, for example, the exposure of the overexposed image is properly adjusted, and the overall texture of the image is favorably improved.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (6)
1. A human face image quality parameter processing system for an intelligent television is characterized by comprising a video storage module, an object recognition module and an image quality function module, wherein the video storage module is respectively connected with the object recognition module and the image quality function module;
the video storage module is used for storing the video to be processed or the processed video; the object recognition module is used for extracting video pixel information which accords with face contour characteristics and skin color characteristics in a video to be processed and forming face region information in the video; the image quality function module is internally pre-stored with an image optimal image quality effect standard and is used for receiving the face region information and processing the face image in the face region information according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard;
the object recognition module is internally pre-stored with a face contour feature standard, and only when a face object in the recognized video meets the face contour feature standard, the object recognition module extracts the video pixel information of the face contour feature and the skin color feature of the face object;
the human face contour characteristic standard comprises a standard of the proportion of a human face object in a video picture and a picture proportion change standard of the human face object in continuous multi-frame images;
the standard of the proportion of the human face object in the video picture is a human face object picture proportion threshold value prestored in the object identification module, and when the proportion of the human face object in the video picture is not less than the human face object picture proportion threshold value, the human face object meets the standard of the proportion of the human face object in the video picture;
the picture ratio change standard at least comprises a size change standard of the face object in the continuous multi-frame images and a relative position change standard of the face object in the continuous multi-frame images.
2. The system according to claim 1, wherein the size variation criterion of the face object in the consecutive multi-frame images is a size variation threshold of the face object pre-stored in the object recognition module, and when the size variation value of the face object in the consecutive multi-frame images does not exceed the size variation threshold of the face object, the face object satisfies the size variation criterion of the face object in the consecutive multi-frame images;
and/or the relative position change standard of the face object in the continuous multi-frame images is a face object relative position change threshold value prestored in the object recognition module, and when the relative position change value of the face object in the continuous multi-frame images does not exceed the face object relative position change threshold value, the face object meets the relative position change standard of the face object in the continuous multi-frame images.
3. The system of claim 1, wherein the image quality optimization criteria comprises at least one of a skin color phase criteria, a color saturation criteria, a color brightness criteria, a noise suppression criteria, a picture sharpness criteria, and/or a local contrast criteria.
4. The system of claim 3, wherein the image quality function module at least comprises a skin color phase adjustment unit, a color saturation adjustment unit, a color brightness adjustment unit, a noise suppression adjustment unit, a picture sharpness adjustment unit, and/or a local contrast adjustment unit.
5. The implementation method of the human face image quality parameter processing system for the smart television set as claimed in claim 1, comprising the following steps:
A. the object identification module reads a frame of image in a video to be processed in the video storage module;
B. the object recognition module reads the read image to perform face recognition to judge whether the image contains a face object to be processed, and the step C is performed when the image contains the face object;
C. the object recognition module detects whether the proportion of the face object in the picture reaches a preset proportion standard or not, and the step D is entered when the proportion of the face object in the picture meets the preset proportion standard;
D. the object identification module reads the proportion change condition of a face object in a picture in continuous multi-frame images subsequent to a current frame image;
E. judging whether human face image quality parameter processing needs to be carried out on the image according to the proportion change condition; if the judgment result is that the processing is needed, the step F is carried out, otherwise, the step I is directly carried out;
F. the object recognition module extracts video pixel information of contour features and skin color features of the face object in the image as an object recognition result;
G. the image quality function module judges whether the object recognition result meets the image optimal image quality effect standard or not;
H. the image quality function module processes the face image in the object recognition result according to the image optimal image quality effect standard so as to enable the face image to meet the image optimal image quality effect standard;
I. and displaying the image in the intelligent television.
6. The method as claimed in claim 5, wherein in step E, if it is determined that the face image quality parameter processing is not required, the image quality function module adjusts transient parameters in the image and then proceeds to step I.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819373.XA CN109089158B (en) | 2018-07-24 | 2018-07-24 | Human face image quality parameter processing system for smart television and implementation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819373.XA CN109089158B (en) | 2018-07-24 | 2018-07-24 | Human face image quality parameter processing system for smart television and implementation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109089158A CN109089158A (en) | 2018-12-25 |
| CN109089158B true CN109089158B (en) | 2020-04-28 |
Family
ID=64838389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810819373.XA Active CN109089158B (en) | 2018-07-24 | 2018-07-24 | Human face image quality parameter processing system for smart television and implementation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109089158B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334629B (en) * | 2019-06-26 | 2022-12-23 | 如隆智能科技(嘉兴)有限公司 | Method and device capable of detecting distance in multiple directions and readable storage medium |
| CN113014992A (en) * | 2021-03-09 | 2021-06-22 | 四川长虹电器股份有限公司 | Image quality switching method and device for smart television |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013152643A (en) * | 2012-01-25 | 2013-08-08 | Canon Inc | Image processing apparatus, image processing method, and program |
| CN105323634A (en) * | 2014-06-27 | 2016-02-10 | Tcl集团股份有限公司 | Method and system for generating thumbnail of video |
| CN105631417A (en) * | 2015-12-24 | 2016-06-01 | 武汉鸿瑞达信息技术有限公司 | Video beautification system and method applied to Internet video live broadcast |
| CN105872447A (en) * | 2016-05-26 | 2016-08-17 | 努比亚技术有限公司 | Video image processing device and method |
| CN106447638A (en) * | 2016-09-30 | 2017-02-22 | 北京奇虎科技有限公司 | Beauty treatment method and device thereof |
| CN106570472A (en) * | 2016-11-02 | 2017-04-19 | 华为技术有限公司 | Skin color detecting method and device and terminal |
| CN108230331A (en) * | 2017-09-30 | 2018-06-29 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment, computer storage media |
| CN108235117A (en) * | 2018-01-29 | 2018-06-29 | 北京奇虎科技有限公司 | A kind of video shading process and device |
-
2018
- 2018-07-24 CN CN201810819373.XA patent/CN109089158B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013152643A (en) * | 2012-01-25 | 2013-08-08 | Canon Inc | Image processing apparatus, image processing method, and program |
| CN105323634A (en) * | 2014-06-27 | 2016-02-10 | Tcl集团股份有限公司 | Method and system for generating thumbnail of video |
| CN105631417A (en) * | 2015-12-24 | 2016-06-01 | 武汉鸿瑞达信息技术有限公司 | Video beautification system and method applied to Internet video live broadcast |
| CN105872447A (en) * | 2016-05-26 | 2016-08-17 | 努比亚技术有限公司 | Video image processing device and method |
| CN106447638A (en) * | 2016-09-30 | 2017-02-22 | 北京奇虎科技有限公司 | Beauty treatment method and device thereof |
| CN106570472A (en) * | 2016-11-02 | 2017-04-19 | 华为技术有限公司 | Skin color detecting method and device and terminal |
| CN108230331A (en) * | 2017-09-30 | 2018-06-29 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment, computer storage media |
| CN108235117A (en) * | 2018-01-29 | 2018-06-29 | 北京奇虎科技有限公司 | A kind of video shading process and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109089158A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3087730B1 (en) | Method for inverse tone mapping of an image | |
| US8520089B2 (en) | Eye beautification | |
| CN109961453B (en) | Image processing method, device and equipment | |
| US9007480B2 (en) | Automatic face and skin beautification using face detection | |
| EP2854389B1 (en) | Scene recognition method and apparatus | |
| CN109302628B (en) | Live broadcast-based face processing method, device, equipment and storage medium | |
| CN109639982A (en) | A kind of image denoising method, device, storage medium and terminal | |
| CN107871303B (en) | Image processing method and device | |
| JP2002158893A (en) | Device and method for correcting picture and recording medium | |
| US8457196B2 (en) | Method for image visual effect improvement of video encoding and decoding | |
| US8421900B2 (en) | Image capturing apparatus, an image capturing method and a machine readable medium storing thereon a computer program for capturing an image of a range wider than an image capture designation range | |
| CN106570838A (en) | Image brightness optimization method and device | |
| EP3136736A1 (en) | Method for inverse tone mapping of a sequence of images | |
| CN109089158B (en) | Human face image quality parameter processing system for smart television and implementation method thereof | |
| US20230063309A1 (en) | Method for processing human body image and electronic device | |
| CN106204743B (en) | Control method and device for augmented reality function and mobile terminal | |
| CN105791925A (en) | Method and device for processing recorded video | |
| CN113253890B (en) | Video image matting method, system and medium | |
| CN105933613A (en) | Image processing method and apparatus and mobile terminal | |
| JP2009100270A (en) | Video-editing method and television broadcast receiver | |
| JP4496005B2 (en) | Image processing method and image processing apparatus | |
| CN108769825B (en) | Method and device for realizing live broadcast | |
| CN112435173A (en) | Image processing and live broadcasting method, device, equipment and storage medium | |
| CN115578273A (en) | Image multi-frame fusion method and device, electronic equipment and storage medium | |
| CN111292677B (en) | Image display processing method and device, computer equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |