CN109901701A - A kind of mouse action system based on computer vision - Google Patents
A kind of mouse action system based on computer vision Download PDFInfo
- Publication number
- CN109901701A CN109901701A CN201711300728.6A CN201711300728A CN109901701A CN 109901701 A CN109901701 A CN 109901701A CN 201711300728 A CN201711300728 A CN 201711300728A CN 109901701 A CN109901701 A CN 109901701A
- Authority
- CN
- China
- Prior art keywords
- image
- mouse action
- nose
- computer vision
- mouse
- 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
Landscapes
- Position Input By Displaying (AREA)
Abstract
The invention discloses a kind of mouse action system based on computer vision, the system comprises: image capture module uses camera to acquire facial image；Image processing module handles the image of acquisition；Face recognition module identifies nose and mouth in facial image；Mouse action module carries out mouse action according to nose and mouth position.
Description
Technical field
The present invention relates to mouse action technologies, and in particular to mouse action system based on computer vision.
Background technique
With the development of information technology and the continuous improvement of the level of IT application, information technology is in the work of people,
It practises and is used widely in living.However, almost all of info class product and information service at present, especially man-machine friendship
What mutual mode was designed both for ordinary people, the application demand of disabled person is not accounted for, this makes disabled person common without the image of Buddha
It is convenient that people enjoys information technology bring like that, thus faces the danger by marginalisation in social life.Only using science and technology
Means adapt to the use habit of disabled person, eliminate disabled person because obtaining information obstacle caused by physical disabilities, are only solution
The effective way of this problem.
With becoming stronger day by day for desktop operating system, mouse has become most common interpersonal interactive mode.Traditional
Mouse goes to control with hand, but for the patient of arm incomplete for arm or inconvenient to use, is become very using mouse
It is difficult.
Summary of the invention
The purpose of the present invention is to overcome the deficiency in the prior art, and arm missing can not be suitable for by especially solving existing mouse
Disabled person or the problem of the patient of arm inconvenient to use.
In order to solve the above technical problems, the present invention provides a kind of mouse action system based on computer vision, wherein institute
The system of stating includes: image capture module, acquires facial image using camera；Image processing module carries out the image of acquisition
Processing；Face recognition module identifies nose and mouth in facial image；Mouse action module, according to nose and mouth position
To carry out mouse action.
The beneficial effect of the scheme of the invention is, facial image is acquired using monocular cam, by correcting face device
Official realizes the movement of mouse, as long as the mobile face of patient moves mouse, has good expansibility and stability.
Detailed description of the invention
Fig. 1 is the mouse action system schematic based on computer vision of the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing and specific embodiment to the present invention carry out in further detail with complete explanation.It is understood that
It is that described herein the specific embodiments are only for explaining the present invention, rather than limitation of the invention.
Referring to Fig.1, the mouse action system based on computer vision includes: image capture module 10, uses camera shooting
Head acquisition facial image；Image processing module 20 handles the image of acquisition；Face recognition module 30 identifies face figure
Nose and mouth as in；Mouse action module 40 carries out mouse action according to nose and mouth position.
Specifically, the embodiment of the present invention is described as follows:
Image capture module 10: facial image is acquired using camera.Face direct picture is acquired using USB camera,
And saved facial image by network, carry out next step operation.
Image processing module 20: the image of acquisition is handled, following steps are specifically divided into:
(1) image binaryzation: after the completion of calibration, image binaryzation is carried out with maximum variance between clusters, by the prospect of image
It is split with background.
(2) image denoising sound: image filtering denoising is carried out using agglomerate area threshold method, removes target part in image
The noise of surrounding.
(3) Image Edge-Detection: edge detection is carried out with Mathematical Morphology Method to bianry image, detects mesh in image
Mark the edge of pipeline.
Face recognition module 30: nose and mouth in identification facial image.It is carried out in face using Adaboost algorithm
The identification of nose and mouth, principle are that some weaker classification methods are combined, and are combined into new very strong classification
Method.Detailed process is described as follows:
(1) Haar feature is extracted in the picture of a 20*20, calculation method is by the pixel in white area and to subtract black
Color region.
(2) Weak Classifier is chosen, is selected in multiple Haar features, the minimum feature of error rate, for judging nose and mouth
Bar, here it is a Weak Classifiers, while being classified with this classifier to sample, and the weight of more new samples.
(3) strong classifier is formed using multiple Weak Classifiers.
Mouse action module 40: mouse action, concrete operations are carried out according to nose and mouth position are as follows:
(1) simulation mouse is clicked, and the parameter used is mouth variation, calculates the mouth change frequency of front and back two field pictures,
If mouth change frequency is 1 time in setting time, determine that left mouse button is activated to click；If change frequency is 2 times, sentence
Surely activation left mouse button is double-clicked；If change frequency is 3 times, determine that right mouse button is activated to click.
(2) simulation mouse is mobile, and with the position that parameter is nose is obtained, the nose for calculating front and back two field pictures changes position
It sets, mobile speed is then calculated by the time of predefined, then judge mobile vector when being more than the speed,
It is assigned to the coordinate of current mouse.
Claims (1)
1. a kind of mouse action system based on computer vision, which is characterized in that the system comprises:
Image capture module acquires facial image using camera；
Image processing module handles the image of acquisition；
Face recognition module identifies nose and mouth in facial image；
Mouse action module carries out mouse action according to nose and mouth position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711300728.6A CN109901701A (en) | 2017-12-10 | 2017-12-10 | A kind of mouse action system based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711300728.6A CN109901701A (en) | 2017-12-10 | 2017-12-10 | A kind of mouse action system based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109901701A true CN109901701A (en) | 2019-06-18 |
Family
ID=66941167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711300728.6A Pending CN109901701A (en) | 2017-12-10 | 2017-12-10 | A kind of mouse action system based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109901701A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673721A (en) * | 2019-08-29 | 2020-01-10 | 江苏大学 | Robot nursing system based on vision and idea signal cooperative control |
| CN114816090A (en) * | 2022-04-29 | 2022-07-29 | 广东迅扬科技股份有限公司 | Method and system for manually awakening mouse without need of manual awakening |
-
2017
- 2017-12-10 CN CN201711300728.6A patent/CN109901701A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110673721A (en) * | 2019-08-29 | 2020-01-10 | 江苏大学 | Robot nursing system based on vision and idea signal cooperative control |
| CN110673721B (en) * | 2019-08-29 | 2023-07-21 | 江苏大学 | Robot nursing system based on vision and idea signal cooperative control |
| CN114816090A (en) * | 2022-04-29 | 2022-07-29 | 广东迅扬科技股份有限公司 | Method and system for manually awakening mouse without need of manual awakening |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104915649B (en) | A kind of biopsy method applied to recognition of face | |
| CN106846403B (en) | Method and device for positioning hand in three-dimensional space and intelligent equipment | |
| Ahmed et al. | Vision based hand gesture recognition using dynamic time warping for Indian sign language | |
| Jain et al. | Real-time upper-body human pose estimation using a depth camera | |
| US20150131855A1 (en) | Gesture recognition device and control method for the same | |
| CN106600640B (en) | Face recognition auxiliary glasses based on RGB-D camera | |
| CN106503651B (en) | A kind of extracting method and system of images of gestures | |
| CN104361326A (en) | Method for distinguishing living human face | |
| CN104504856A (en) | Fatigue driving detection method based on Kinect and face recognition | |
| EP3179408A3 (en) | Picture processing method and apparatus, computer program and recording medium | |
| EP1477924A3 (en) | Gesture recognition apparatus, method and program | |
| CN103593598A (en) | User online authentication method and system based on living body detection and face recognition | |
| CN110991315A (en) | Method for detecting wearing state of safety helmet in real time based on deep learning | |
| WO2016070688A1 (en) | Remote control method and system for virtual operation interface | |
| CN109697430A (en) | The detection method that working region safety cap based on image recognition is worn | |
| CN102184016B (en) | Noncontact type mouse control method based on video sequence recognition | |
| CN109190522A (en) | A kind of biopsy method based on infrared camera | |
| JP2016162075A (en) | Object track method, device and program | |
| CN111367415B (en) | Equipment control method and device, computer equipment and medium | |
| CN102831408A (en) | Human face recognition method | |
| US20210209342A1 (en) | Human face detcetion method | |
| CN110148092A (en) | The analysis method of teenager's sitting posture based on machine vision and emotional state | |
| CN109901701A (en) | A kind of mouse action system based on computer vision | |
| CN106599873A (en) | Figure identity identification method based on three-dimensional attitude information | |
| CN109359581A (en) | A kind of face registration method based on intelligent glasses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190618 |
|
| WD01 | Invention patent application deemed withdrawn after publication |