CN202584048U - Smart mouse based on DSP image location and voice recognition - Google Patents
Smart mouse based on DSP image location and voice recognition Download PDFInfo
- Publication number
- CN202584048U CN202584048U CN 201220223378 CN201220223378U CN202584048U CN 202584048 U CN202584048 U CN 202584048U CN 201220223378 CN201220223378 CN 201220223378 CN 201220223378 U CN201220223378 U CN 201220223378U CN 202584048 U CN202584048 U CN 202584048U
- Authority
- CN
- China
- Prior art keywords
- mouse
- dsp
- camera
- voice recognition
- module
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The utility model provides a smart mouse based on DSP (Digital Signal Processor) image location and voice recognition. The smart mouse comprises a camera, a voice recognition module and a DSP chip. The camera is used for acquiring human face images in real time; the voice recognition module is used for acquiring voice signals in real time; and the DSP chip is connected with the camera and the voice recognition module, and is used for processing the human face images from the camera, locating a human mouth part and controlling the cursor according to the movement locus of the human mouth part, and converting the codes from the voice recognition module into analogue mouse signals so as to control the mouse operation. The implementation of the smart mouse based on DSP image location and voice recognition provided by the utility model has the following benefits: controlling the movement of the cursor by tracking and locating the position of the human mouth via the camera, and substituting the functions of a normal mouse by controlling the behaviors of the mouse by languages via the voice recognition module; and enabling the people with disabled arms to operate the mouse, and bringing convenience for people in some places where the mouse is not convenient to be operated by hands, thereby being convenient and practical.
Description
Technical field
The utility model relates to a kind of intelligent mouse, more particularly, relates to a kind of intelligent mouse based on DSP framing, speech recognition.
Background technology
Along with the development of image processing techniques, voice technology, make and utilize voice, image manipulation computing machine to become possibility.In today of the increasingly extensive application of computing machine, the operating computer mouse exists very big difficulty for there are disabled people in those arms.The utility model is just as starting point; Design a kind of intelligent mouse based on DSP framing, speech recognition; This system can control the moving of cursor, location with the position of camera track and localization mouth, again with the behavior act of language mouse beacon be left click, right click, leftly double-click, move to left, move to right, on move, move down, on drag, drag down, drag on a left side, drag on the right side, middle key, on the function that order replaces common mouse such as roll, roll, stop down.The dream that so not only can let arm exist disabled people to realize operating mouse, and bring great convenience for those people in the occasion of being inconvenient to operate mouse.
Summary of the invention
The utility model is directed against the proposition of above problem, and develops a kind of intelligent mouse based on DSP framing, speech recognition.
The utility model provides a kind of intelligent mouse based on DSP framing, speech recognition, it is characterized in that, comprising:
Gather in real time facial image and the facial image that collects is sent to the camera of dsp chip;
After gathering in real time voice signal and searching the voice signal corresponding codes in the library, coding is sent to the sound identification module of dsp chip according to voice signal;
Be connected with sound identification module with camera; The facial image that will come from camera is handled; Moving of mouth position, location and the movement locus control cursor through the mouth position, and the code conversion that will come from sound identification module is the dsp chip of analog mouse signal controlling mouse action.
Preferably; Sound identification module comprises the pre-processing module of the voice signal that collects being carried out filtering, sampling, quantification, windowing, end-point detection, pre-emphasis operation; Extract the characteristic extracting module of key characterization parameter the signal after pre-processing module is handled, the module of searching of searching corresponding coding in the library according to key characterization parameter.
Preferably, intelligent mouse also comprises power supply and interface module.
Preferably, dsp chip is TMS320AC5402.
Implement the intelligent mouse based on DSP framing, speech recognition of the utility model; Have following beneficial effect: control the moving of cursor, location through the position of camera track and localization mouth, again the behavior act through sound identification module language mouse beacon be left click, right click, a left side double-click, move to left, move to right, on move, move down, on drag, drag down, drag on a left side, drag on the right side, middle key, on the function that order replaces common mouse such as roll, roll, stop down.This intelligent mouse can let the disabled people of those arms operate mouse, also is inconvenient to use the occasion of manual manipulation mouse to bring convenience to people at some, and is convenient and practical.
Description of drawings
Fig. 1 is the structural representation based on the intelligent mouse of DSP framing, speech recognition of the utility model;
Fig. 2 is the process flow diagram of the image recognition of the utility model;
Fig. 3 is the process flow diagram of the speech recognition of the utility model.
Embodiment
The utility model provides a kind of intelligent mouse based on DSP framing, speech recognition, helps disabled personage of arm and the inconvenient personage of operation mouse, the easy and convenient mouse action that carries out.
Fig. 1 is the structural representation based on the intelligent mouse of DSP framing, speech recognition of the utility model, and is as shown in the figure.This intelligent mouse comprises: camera, sound identification module and dsp chip.Camera is gathered facial image in real time and the facial image that collects is sent to dsp chip; Sound identification module is sent to dsp chip with coding after gathering voice signal in real time and searching the voice signal corresponding codes according to voice signal in the library; Dsp chip is connected with sound identification module with camera; The facial image that will come from camera is handled; Moving of mouth position, location and the movement locus control cursor through the mouth position, and the code conversion that will come from sound identification module is an analog mouse signal controlling mouse action.This intelligent mouse also comprises power supply and interface module, through interface module, the analog mouse signal is sent to computer, the mouse beacon operation.Dsp chip is selected the TMS320AC5402 of TI company for use in the present embodiment, and it is the chip that is exclusively used in the image speech processes.TMS320AC5402 handles the picture that camera transmits; Find out the position of mouth and follow the tracks of, control moving of cursor through the movement locus of face, and then by the people send left click, right click, a left side double-click, move to left, move to right, on move, move down, on drag, drag down, drag on a left side, drag on the right side, middle key, on order such as roll, roll, stop down; Voice acquisition module is gathered these voice messagings; Give controller TMS320AC5402 then and handle,, convert the analog mouse signal into the rectangular pulse signal that collects; Giving computer with these analog mouse signals is PC, comes the action of mouse beacon.
The collection of face-image is people's face that people know and detects, and is the position and big or small process of (existences) people face in the image of input, is one of people's technical task of being devoted to study in recent years.Common people's face detects has following several method: based on people's face detection algorithm of characteristic, based on people's face algorithm of people's face detection algorithm of knowledge, template matches, based on people's face algorithm of outward appearance etc.Whether wherein the people's face algorithm based on characteristic promptly carries out Treatment Analysis to input picture, and then obtains its eigenwert and compare in the characteristic with people's face, judges people's face; Whether for to be familiar with some experiences, the knowledge of summing up in the process of people's face, judge people's face based on people's face detection algorithm of knowledge at us; Template matches is then at first set up the template of some faces, judges whether it is people's face in that image and the template of input are mated; People's face algorithm based on outward appearance is through a large amount of people's face, non-face as training set; Train the sorter that detects people's face with SVMs (SVM), neuroid, detect with this sorter and carry out the detection of people's face, native system promptly adopts this mode to carry out people's face and detects; This method is different with additive method to be; It is not the direct labor input picture is handled the extraction masterplate, but directly compare, be exactly like this algorithm complex of image acquisition and processing reduces; Improve the efficient of handling greatly, made analog mouse be swift in motion, be quick on the draw.
Image process method is also a lot, spottiness analysis commonly used, template matches, geometric properties coupling and rim detection etc.Native system adopts the mouth tracking in the geometric properties coupling; Promptly come lip-syncing to follow the tracks of with mouth center, morphology location; This algorithm can only utilize half-tone information to carry out morphological operations, local twiddle operation; Therefore calculate very simply,, thereby do not receive the influence of factors such as background complexity, people's face exercise intensity and background color without information such as background, motion and colors.Tracking time is only relevant with people's face size to have nothing to do with the image size, so that the accuracy of the reaction sensitivity of analog mouse, action improves greatly.And mouth not only area is little, and it is simpler form to occur; Compare with other organs such as eyes that influenced by illumination, hair etc. less, mouth also has tangible gray difference with people's face.Therefore it is convenient to adopt this kind algorithm to make when handling image, makes algorithm simple, has reduced the time complexity and the space complexity of algorithm.
Fig. 2 is the process flow diagram of the image recognition of the utility model, and is as shown in the figure.After camera carries out IMAQ,, adopt the tracking in the geometric properties coupling, control cursor and move based on the method for detecting human face of outward appearance.
Fig. 3 is the process flow diagram of the speech recognition of the utility model, and is as shown in the figure.Sound identification module carries out pre-service such as filtering, sampling, quantification, windowing, end-point detection, pre-emphasis operation after gathering voice signal; After information carried out pre-service; Extract eigenwert the signal after handling; In library, search corresponding coding according to eigenwert, carry out the module coupling, obtain voice identification result according to code identification.The aforesaid operations that is operated in of setting up library carries out before, sets up library through extracting the eigenwert training.
Sound identification module is a kind of pattern-recognition in essence, mainly comprises the functional modules such as collection, pre-service, feature extraction, library foundation and pattern match of voice signal; Pre-processing module is that the voice signal that collects is carried out operations such as pre-filtering, sampling, quantification, windowing, end-point detection, pre-emphasis; Signal after then it being handled carries out feature extraction, i.e. the parameters,acoustic of computing voice signal extracts the key characterization parameter of reflected signal, to reduce dimension so that the computing in later stage and processing; Next be put into the voice signal after handling in the library and mate, find out this voice signal corresponding codes, give controller.
Present embodiment mainly adopts the isolated voice recognition system, is that unit carries out speech recognition with isolated word or speech promptly.At first the pronunciation of isolated word speech alive pauses clearly, and therefore feasible pre-service, end-point detection for voice becomes and be easy to, and can find end points very fast, makes accuracy improve greatly.Secondly sending out because of putting in place of isolated word or speech is just very simple when the pattern match of processes voice signals like this.Based on above can so that native system when analog mouse is ordered, obtain information more accurately, make the accuracy of action of analog mouse promote greatly.
The above; Be merely the preferable embodiment of the utility model; But the protection domain of the utility model is not limited thereto; Any technician who is familiar with the present technique field is equal to replacement or changes according to the technical scheme of the utility model and inventive concept thereof in the technical scope that the utility model discloses, and all should be encompassed within the protection domain of the utility model.
Claims (4)
1. the intelligent mouse based on DSP framing, speech recognition is characterized in that, comprising:
Gather in real time facial image and the facial image that collects is sent to the camera of dsp chip;
After gathering in real time voice signal and searching the voice signal corresponding codes in the library, coding is sent to the sound identification module of dsp chip according to voice signal;
Be connected with sound identification module with camera; The facial image that will come from camera is handled; Moving of mouth position, location and the movement locus control cursor through the mouth position, and the code conversion that will come from sound identification module is the dsp chip of analog mouse signal controlling mouse action.
2. the intelligent mouse based on DSP framing, speech recognition according to claim 1; It is characterized in that; Sound identification module comprises the pre-processing module of the voice signal that collects being carried out filtering, sampling, quantification, windowing, end-point detection, pre-emphasis operation; Extract the characteristic extracting module of key characterization parameter the signal after pre-processing module is handled, the module of searching of searching corresponding coding in the library according to key characterization parameter.
3. the intelligent mouse based on DSP framing, speech recognition according to claim 2 is characterized in that intelligent mouse also comprises power supply and interface module.
4. according to the described intelligent mouse of each claim of claim 1-3, it is characterized in that dsp chip is TMS320AC5402 based on DSP framing, speech recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220223378 CN202584048U (en) | 2012-05-17 | 2012-05-17 | Smart mouse based on DSP image location and voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201220223378 CN202584048U (en) | 2012-05-17 | 2012-05-17 | Smart mouse based on DSP image location and voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202584048U true CN202584048U (en) | 2012-12-05 |
Family
ID=47253439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201220223378 Expired - Fee Related CN202584048U (en) | 2012-05-17 | 2012-05-17 | Smart mouse based on DSP image location and voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202584048U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598138A (en) * | 2014-12-24 | 2015-05-06 | 三星电子（中国）研发中心 | Method and device for controlling electronic map |
| CN106356057A (en) * | 2016-08-24 | 2017-01-25 | 安徽咪鼠科技有限公司 | Speech recognition system based on semantic understanding of computer application scenario |
| CN107799124A (en) * | 2017-10-12 | 2018-03-13 | 安徽咪鼠科技有限公司 | A kind of VAD detection methods applied to intelligent sound mouse |
| CN109947268A (en) * | 2018-07-04 | 2019-06-28 | 湖北民族学院 | A kind of multi-functional expression mouse can be used for intelligent terminal |
| CN116774845A (en) * | 2023-08-21 | 2023-09-19 | 深圳市英菲克电子有限公司 | Intelligent disabled-aiding mouse control circuit and control method thereof |
-
2012
- 2012-05-17 CN CN 201220223378 patent/CN202584048U/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598138A (en) * | 2014-12-24 | 2015-05-06 | 三星电子（中国）研发中心 | Method and device for controlling electronic map |
| CN104598138B (en) * | 2014-12-24 | 2017-10-17 | 三星电子（中国）研发中心 | electronic map control method and device |
| CN106356057A (en) * | 2016-08-24 | 2017-01-25 | 安徽咪鼠科技有限公司 | Speech recognition system based on semantic understanding of computer application scenario |
| CN107799124A (en) * | 2017-10-12 | 2018-03-13 | 安徽咪鼠科技有限公司 | A kind of VAD detection methods applied to intelligent sound mouse |
| CN109947268A (en) * | 2018-07-04 | 2019-06-28 | 湖北民族学院 | A kind of multi-functional expression mouse can be used for intelligent terminal |
| CN116774845A (en) * | 2023-08-21 | 2023-09-19 | 深圳市英菲克电子有限公司 | Intelligent disabled-aiding mouse control circuit and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106985137B (en) | Multi-modal exchange method and system for intelligent robot | |
| CN202584048U (en) | Smart mouse based on DSP image location and voice recognition | |
| Gu et al. | Human gesture recognition through a kinect sensor | |
| Hasan et al. | Hand gesture modeling and recognition using geometric features: a review | |
| CN102103409A (en) | Man-machine interaction method and device based on motion trail identification | |
| Agrawal et al. | A survey on manual and non-manual sign language recognition for isolated and continuous sign | |
| CN107678550A (en) | A kind of sign language gesture recognition system based on data glove | |
| CN102930270A (en) | Method and system for identifying hands based on complexion detection and background elimination | |
| Kour et al. | Sign language recognition using image processing | |
| CN111126280B (en) | Gesture recognition fusion-based aphasia patient auxiliary rehabilitation training system and method | |
| CN108958620A (en) | A kind of dummy keyboard design method based on forearm surface myoelectric | |
| Zhang et al. | Robotic control of dynamic and static gesture recognition | |
| CN107452381B (en) | Multimedia voice recognition device and method | |
| Nath et al. | Embedded sign language interpreter system for deaf and dumb people | |
| CN107908289B (en) | Head-based robot face recognition interaction system | |
| CN108268818A (en) | Gesture identification method based on surface electromyogram signal and acceleration | |
| Basha et al. | Speaking system to mute people using hand gestures | |
| Dadiz et al. | Go-Mo (Go-Motion): An android mobile application detecting motion gestures for generating basic mobile phone commands utilizing KLT algorithm | |
| CN101446859B (en) | Machine vision based input method and system thereof | |
| CN113807280A (en) | Kinect-based virtual ship cabin system and method | |
| Jeong et al. | Hand gesture user interface for transforming objects in 3d virtual space | |
| CN110555391B (en) | Intelligent wireless operating system and method based on grating diffraction and gesture recognition | |
| Liu et al. | Gesture recognition based on Kinect | |
| CN104363494A (en) | Gesture recognition system for smart television | |
| CN109901700A (en) | A kind of new gesture identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121205 Termination date: 20130517 |