CN106447627A - Image processing method and apparatus - Google Patents
Image processing method and apparatus Download PDFInfo
- Publication number
- CN106447627A CN106447627A CN201610809372.8A CN201610809372A CN106447627A CN 106447627 A CN106447627 A CN 106447627A CN 201610809372 A CN201610809372 A CN 201610809372A CN 106447627 A CN106447627 A CN 106447627A
- Authority
- CN
- China
- Prior art keywords
- region
- image information
- image processing
- information
- fisrt feature
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 23
- 230000037303 wrinkles Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000212384 Bifora Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- VEMKTZHHVJILDY-UHFFFAOYSA-N resmethrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=COC(CC=2C=CC=CC=2)=C1 VEMKTZHHVJILDY-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G06T5/73—
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides an image processing method and apparatus. The method comprises the steps of performing feature identification processing on obtained target object image information to obtain a first feature region; and processing key feature information in the first feature region by adopting a corresponding processing policy. The apparatus comprises an acquisition unit, an identification unit and an operation unit, wherein the acquisition unit is connected with the operation unit through the identification unit. According to the method and the apparatus, an acquired human face part in an image is automatically processed, so that human face image fuzziness or distortion caused by reasons of light rays, bandwidth limitation or the like is overcome; the processing process is simple and the processing effect is good; and the whole processing process is automated.
Description
Technical field
The invention belongs to computer realm, more particularly, to a kind of image processing method and device.
Background technology
In daily teaching activity, because the light in classroom, bandwidth limit and lead to the excessively low reason of code check, often lead to adopt
The image of collection is fuzzyyer, loses and really feels.
After collection, often only overall to collection image color or brightness is adjusted existing teacher's image, and
The face image particular for teacher does not carry out special landscaping treatment, and the face image being therefore usually present teacher is unintelligible, shadow
Ring teaching efficiency.
Content of the invention
The present invention provides a kind of image processing method and device, to solve the above problems.
The present invention provides a kind of image processing method, comprises the following steps：The destination object image information obtaining is carried out
Feature identification is processed, and then obtains fisrt feature region；To the key feature information in described fisrt feature region, using correspondence
Process strategy processed.
The present invention provides a kind of image processing apparatus, including：Acquiring unit, recognition unit and operating unit；Wherein, described
Acquiring unit is connected with described operating unit by described recognition unit；Described acquiring unit, for obtaining destination object image
Information, and described destination object image information is sent to described recognition unit；Described recognition unit, for receiving described target
Object images information, and feature identification process is carried out to the destination object image information obtaining, and then obtain fisrt feature region；
Recognition unit is additionally operable to send described fisrt feature region to described operating unit；Described operating unit, described for receiving
The described fisrt feature region that recognition unit sends, and to the key feature information in described fisrt feature region, using correspondence
Process strategy processed.
Compared to prior art, a kind of image processing method being provided according to the present invention and device, by collecting
Destination object image information is processed, thus identifying fisrt feature region, and for crucial special in fisrt feature region
Reference breath is processed using corresponding process strategy.The present invention be directed to the face part in the image collecting is carried out automatically
Process, overcome the face fuzzy pictures because the reason such as light or bandwidth restriction leads to or distortion, its processing procedure is simple, process
Effect is good, and whole-course automation is processed, and need not additionally manually operate.
Brief description
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this
Bright schematic description and description is used for explaining the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
The flow chart that Fig. 1 show the image processing method providing according to presently preferred embodiments of the present invention；
Fig. 2 show the internal structure schematic diagram of the image processing apparatus providing according to presently preferred embodiments of the present invention.
Specific embodiment
To describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the embodiment in the application and the feature in embodiment can be mutually combined.
The flow chart that Fig. 1 show the image processing method providing according to a preferred embodiment of the present invention.
As shown in figure 1, following two steps are mainly included according to the image processing method of the present invention：
Step 101, carries out feature identification process to the destination object image information obtaining, and then obtains fisrt feature area
Domain；
Before feature identification process is carried out to the destination object image information obtaining, also include：To the destination object obtaining
Image information is filtered, and obtains face skin area.
Using the binaryzation based on fixed threshold, the described destination object image information obtaining is filtered, and then obtain
Face skin area.
Specifically it is assumed that destination object image information is the current bishop classroom instruction picture A of camera acquisition, by people
The brightness fixed threshold of face skin is set to 35, and each pixel in detection picture A, when the brightness of pixel is more than or equal to
When 35, the gray value of pixel is set to 1, when the brightness of pixel is less than 35, the gray value of this pixel is set to
0, wherein, the gray value of pixel is 1 for people's face skin, the gray value of pixel is 0 filters out, obtains people's face skin
The gray-scale maps in region.
Using Niblack Binarization methods, described face skin area is carried out with feature identification to separate, and then obtain first
Characteristic area.
After described face skin area being carried out with feature identification separation using Niblack Binarization methods, also include：
By corroding expansion algorithm, demarcation process is carried out to the result isolated by Niblack Binarization methods, and then obtain
Take fisrt feature region.
Wherein, described fisrt feature region includes：Eye areas, nasal area, face region.
Step 102, to the key feature information in described fisrt feature region, at corresponding process strategy
Reason.
Wherein, key feature information includes wrinkle image information and spot image information.
If described key feature information is wrinkle image information, pass through iterative nonlinear Multilevel Median Filtering Algorithm, right
Fisrt feature region is smoothed.
If described key feature information is spot image information, judge spot image information was carried out by connected domain
Filter, obtains target blob region；
By inpaint algorithm, described target blob region is filled with.
Judge described spot image information is filtered by connected domain, before obtaining target blob region, also include：
By Sobel algorithm, rim detection is carried out to the gray-scale maps in the fisrt feature region after smoothing processing, obtains speckle
Image information.
To the key feature information in described fisrt feature region, after being processed using corresponding process strategy, warp
Overcompression coding and network crossfire are sent to far-end classroom, can be watched by student.
Fig. 2 show the internal structure schematic diagram of the image processing apparatus providing according to presently preferred embodiments of the present invention, root
Image processing apparatus according to embodiments of the invention can include：Acquiring unit 201, recognition unit 202 and operating unit 203；
Wherein, described acquiring unit 201 is connected with described operating unit 203 by described recognition unit 202；
Described acquiring unit 201, for obtaining destination object image information, and described destination object image information is sent
To described recognition unit 202；
Described recognition unit 202, for receiving described destination object image information, and to the destination object image letter obtaining
Breath carries out feature identification process, and then obtains fisrt feature region；Recognition unit 202 is additionally operable to send out described fisrt feature region
Deliver to described operating unit 203；
Described operating unit 203, for receiving the described fisrt feature region that described recognition unit 202 sends, and to institute
State the key feature information in fisrt feature region, processed using corresponding process strategy.
Furthermore, described recognition unit 202, is additionally operable to carrying out feature knowledge to the destination object image information obtaining
Before the reason of other places, using the binaryzation based on fixed threshold, described destination object image information is filtered, obtain people's face
Skin region；It is additionally operable to, using Niblack Binarization methods, described face skin area is carried out with feature identification separation, and then pass through
Corrosion expansion algorithm obtains fisrt feature region.
Furthermore, if described key feature information is wrinkle image information, described operating unit 203 is additionally operable to pass through
Iterative nonlinear Multilevel Median Filtering Algorithm, is smoothed to fisrt feature region；
Furthermore, if described key feature information is spot image information, described operating unit 203 is additionally operable to pass through
Connected domain judges spot image information is filtered, and obtains target blob region, and passes through inpaint algorithm, to described mesh
Marking spot region is filled with.
Compared to prior art, a kind of image processing method being provided according to the present invention and device, by collecting
Destination object image information is processed, thus identifying fisrt feature region, and for crucial special in fisrt feature region
Reference breath is processed using corresponding process strategy.The present invention be directed to the face part in the image collecting is carried out automatically
Process, overcome the face fuzzy pictures because the reason such as light or bandwidth restriction leads to or distortion, its processing procedure is simple, process
Effect is good, and whole-course automation is processed, and need not additionally manually operate.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.All within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (12)
1. a kind of image processing method is it is characterised in that comprise the following steps：
Feature identification process is carried out to the destination object image information obtaining, and then obtains fisrt feature region；
To the key feature information in described fisrt feature region, processed using corresponding process strategy.
2. image processing method according to claim 1 is it is characterised in that carry out to the destination object image information obtaining
Before feature identification is processed, also include：
The destination object image information obtaining is filtered, obtains face skin area.
3. image processing method according to claim 2 is it is characterised in that using the binaryzation based on fixed threshold to obtaining
The described destination object image information taking is filtered, and then obtains face skin area.
4. image processing method according to claim 2 is it is characterised in that adopt Niblack Binarization methods to described
Face skin area carries out feature identification and separates, and then obtains fisrt feature region.
5. image processing method according to claim 4 is it is characterised in that adopt Niblack Binarization methods to described
After face skin area carries out feature identification separation, also include：
By corroding expansion algorithm, demarcation process is carried out to the result isolated by Niblack Binarization methods, and then obtain the
One characteristic area.
If the image processing method 6. according to claim 4 or 5 is it is characterised in that described key feature information is wrinkle
Image information, then pass through iterative nonlinear Multilevel Median Filtering Algorithm, fisrt feature region be smoothed.
If the image processing method 7. according to claim 4 or 5 is it is characterised in that described key feature information is speckle
Image information, then judge spot image information is filtered by connected domain, obtains target blob region；
By inpaint algorithm, described target blob region is filled with.
8. image processing method according to claim 7 is it is characterised in that judged to described spot image by connected domain
Information is filtered, and before obtaining target blob region, also includes：
By Sobel algorithm, rim detection is carried out to the gray-scale maps in the fisrt feature region after smoothing processing, obtains spot image
Information.
9. image processing method according to claim 1 is it is characterised in that described fisrt feature region includes：Eyes area
Domain, nasal area, face region.
10. a kind of image processing apparatus are it is characterised in that include：Acquiring unit, recognition unit and operating unit；Wherein, described
Acquiring unit is connected with described operating unit by described recognition unit；
Described acquiring unit, for obtaining destination object image information, and described destination object image information is sent to described
Recognition unit；
Described recognition unit, for receiving described destination object image information, and is carried out to the destination object image information obtaining
Feature identification is processed, and then obtains fisrt feature region；Recognition unit is additionally operable to send described fisrt feature region to described
Operating unit；
Described operating unit, for receiving the described fisrt feature region that described recognition unit sends, and to described fisrt feature
Key feature information in region, is processed using corresponding process strategy.
11. image processing apparatus according to claim 10 it is characterised in that described recognition unit, are additionally operable to obtaining
Before the destination object image information taking carries out feature identification process, using the binaryzation based on fixed threshold to described target pair
As image information is filtered, obtain face skin area；It is additionally operable to using Niblack Binarization methods to described people's face skin
Region carries out feature identification and separates, and then obtains fisrt feature region by corroding expansion algorithm.
12. image processing apparatus according to claim 11 it is characterised in that
If described key feature information is wrinkle image information, described operating unit is additionally operable to by the multistage intermediate value of iterative nonlinear
Filtering algorithm, is smoothed to fisrt feature region；
If described key feature information is spot image information, described operating unit is additionally operable to judge to spot figure by connected domain
As information is filtered, obtain target blob region, and pass through inpaint algorithm, described target blob region is filled with.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610809372.8A CN106447627A (en) | 2016-09-08 | 2016-09-08 | Image processing method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610809372.8A CN106447627A (en) | 2016-09-08 | 2016-09-08 | Image processing method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447627A true CN106447627A (en) | 2017-02-22 |
Family
ID=58164407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610809372.8A Pending CN106447627A (en) | 2016-09-08 | 2016-09-08 | Image processing method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447627A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563977A (en) * | 2017-08-28 | 2018-01-09 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| CN112533024A (en) * | 2020-11-26 | 2021-03-19 | 北京达佳互联信息技术有限公司 | Face video processing method and device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100026833A1 (en) * | 2008-07-30 | 2010-02-04 | Fotonation Ireland Limited | Automatic face and skin beautification using face detection |
| CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
-
2016
- 2016-09-08 CN CN201610809372.8A patent/CN106447627A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100026833A1 (en) * | 2008-07-30 | 2010-02-04 | Fotonation Ireland Limited | Automatic face and skin beautification using face detection |
| CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
Non-Patent Citations (2)
| Title |
|---|
| TRENT1985: "图像美妆算法——自动祛斑算法研究", 《CSDN博客-HTTPS://BLOG.CSDN.NET/TRENT1985/ARTICLE/DETAILS/48311199》 * |
| 韩静亮 等: "基于迭代多级中值滤波的人脸美化算法", 《计算机应用与软件》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563977A (en) * | 2017-08-28 | 2018-01-09 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| CN112533024A (en) * | 2020-11-26 | 2021-03-19 | 北京达佳互联信息技术有限公司 | Face video processing method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN105930800B (en) | A kind of method for detecting lane lines and device | |
| CN106897698B (en) | Classroom people number detection method and system based on machine vision and binocular collaborative technology | |
| WO2017028587A1 (en) | Vehicle monitoring method and apparatus, processor, and image acquisition device | |
| CN106980852B (en) | Based on Corner Detection and the medicine identifying system matched and its recognition methods | |
| CN105022999B (en) | A kind of adjoint real-time acquisition system of people's code | |
| CN107705288A (en) | Hazardous gas spillage infrared video detection method under pseudo- target fast-moving strong interferers | |
| CN109635758A (en) | Wisdom building site detection method is dressed based on the high altitude operation personnel safety band of video | |
| CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
| CN102542246A (en) | Abnormal face detection method for ATM (Automatic Teller Machine) | |
| CN106709518A (en) | Android platform-based blind way recognition system | |
| CN109117752A (en) | A kind of face recognition method based on gray scale and RGB | |
| CN111259763B (en) | Target detection method, target detection device, electronic equipment and readable storage medium | |
| CN112434545A (en) | Intelligent place management method and system | |
| CN110111272A (en) | A kind of artificial intelligence infrared image processing instrument, control system and control method | |
| CN106447627A (en) | Image processing method and apparatus | |
| CN113887519A (en) | Artificial intelligence-based garbage throwing identification method, device, medium and server | |
| CN112232205B (en) | Mobile terminal CPU real-time multifunctional face detection method | |
| CN103226690B (en) | Detect blood-shot eye illness method and device, removal blood-shot eye illness method and device | |
| CN115830719B (en) | Building site dangerous behavior identification method based on image processing | |
| CN104615985B (en) | A kind of recognition methods of human face similarity degree | |
| CN104794445A (en) | ARM platform based dynamic facial iris acquisition method | |
| CN115690130A (en) | Image processing method and device | |
| JP3578321B2 (en) | Image normalizer | |
| CN112101107A (en) | Intelligent identification method for intelligent network combined model type vehicle-in-loop simulation traffic signal lamp |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |
|
| WD01 | Invention patent application deemed withdrawn after publication |