CN100367809C - Action recognizing system - Google Patents
Action recognizing system Download PDFInfo
- Publication number
- CN100367809C CN100367809C CNB021024197A CN02102419A CN100367809C CN 100367809 C CN100367809 C CN 100367809C CN B021024197 A CNB021024197 A CN B021024197A CN 02102419 A CN02102419 A CN 02102419A CN 100367809 C CN100367809 C CN 100367809C
- Authority
- CN
- China
- Prior art keywords
- image
- contrast
- recognizing system
- data
- action
- 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 - Lifetime
Links
- 238000010295 mobile communication Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000013500 data storage Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 12
- 230000001343 mnemonic effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 210000001525 retina Anatomy 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Abstract
The present invention relates to an action recognizing system controlling a mobile communication device in an image recognizing mode by a dynamic image, particularly to a recognizing system with an automatic memory learning function. The present invention acquires the dynamic image. After the dynamic image is converted into digital image data, the digital image data is searched from an image database to generate a corresponding contrast result signal. The contrast result signal is converted into a control signal finally to control the mobile communication device. The recognizing system searches the database in a contrast mode according to an image recognition combined movement track method.
Description
Technical field
The present invention relates to a kind of identification system, particularly a kind of action recognizing system that can be applicable to device for mobile communication.
Background technology
By the identification system of sound and image, its development is quite rapid at present.Wherein, the speech recognition technology is commonly used in many individualized electronic installations, as phone, recorder, safety box switch and phonetic entry etc.Because its personalized demand must allow the computer learning voice relevant with memory just can move.The image identification technology then is commonly used in monitoring, tracking and the identification (as identification of fingerprint or retina identification) etc. of object.Therefore, the application of sound and image identification, different mostly.
In today that mobile phone is popularized gradually, (charge coupleddevice CCD) is applied to absorb image and is in fashion gradually with charge coupled device.Therefore, the image identification technology also becomes the research staff and wants one of direction of studying.But image identification technology in the past (as: fingerprint identification system or retina identification system) is all the identification technique of carrying out static scanning at certain individually defined thing, up to now, does not have the dynamic image identification system based on CCD to produce.On the contrary, mostly what be applied in mobile phone is the speech recognition technology, for example phonetic dialing, and the voice that it utilizes the user in advance telephone number to be recorded can externally dial by the calling of voice again.
Yet because the speech recognition technology has the problem of its existence, for example, the sound quality during recorded speech is if, just must record again when different with sound quality at ordinary times; Or the sound quality of the sound quality when sick when recording may be different.Therefore, how to use existing C CD technology to develop the image identification technology maturely, and then replace the speech recognition technology, the problem that has just like become the research staff and valued.
Summary of the invention
In view of this, the present invention provides a kind of action recognizing system of controlling device for mobile communication by presenting of hand motion for solving the speech recognition technology because of recording the different not high problems of discrimination power that cause with the sound quality of importing.After identification system was absorbed a dynamic image, system promptly can be converted to digital image data with this dynamic image.And then with this digital image data according to the way of contrast of a vivid identification in conjunction with motion track, many group images reference data of image database is deposited in search, and produce the corresponding results contrast signal, by this as a result contrast signal handle the device for mobile communication that control is equipped with this identification system.
Another object of the present invention is to provide a kind of function of automatic mnemonic learning, this identification system can be carried out the adjustment of System Discrimination attribute and the content that substitutes image database according to the kenel of dynamic image.So can promote identification correctness and can minimizing system for identification time of same action image.
Description of drawings
Fig. 1 is the whole calcspar of action recognizing system of the present invention; And
Fig. 2 is the overall operation flow chart of action recognizing system of the present invention.
Embodiment
The present invention is that a kind of user can be by the reception and registration of hand motion, controls that device for mobile communication dials or the action recognizing system of other input behavior.Below will utilize an embodiment that the concrete feasibility of this method is described, at first see also figure one.This action recognizing system is combined by image capturing device 110, data storage 120, contrast processor 130 and o controller 140.Have image database 121 in identification system, in order to deposit many group images reference data, this image reference data is the image corresponding to the hand motion of digital 0-9, with the identification benchmark as this system.
At first, the image capturing device 110 of this system receives by the dynamic image that hand motion presented, and this dynamic image is converted to a digital image data via image circuit 111, is stored at last in the data storage 120.Then, the digital image data that will be stored in the data storage 120 by contrast processor 130 takes out, and with this digital image data with the way of contrast of a vivid identification in conjunction with motion track, the image reference data of searching this image database 121.After search finishing, promptly can produce a contrast signal as a result.
Through searching the contrast signal as a result that is produced after the contrast, conversion via o controller 140, become a row control signal, in order to handle the device for mobile communication that control is equipped with this identification system, as mobile phone (mobile phone) or personal digital assistant (personal digital assistant, PDA).
At this moment, identification system can be according to the kenel of image, carry out the adjustment of identification attribute and the content that substitutes image database 121, so can increase identification correctness and can the minimizing system for identification time of same action image.
The actual operation flow process of relevant the inventive method sees also Fig. 2.After activating this action recognizing system, this system just can begin to absorb extraneous dynamic image and convert digital image data (step 210) to when operating device for mobile communication.Then, this digital image data is compared (step 220) with vivid identification in conjunction with the way of contrast and the database of motion track, the principle of contrast is to detect digital image data whether to meet image reference data (step 230) in the database.If the image data (might be unintelligible, the indeterminate or input error of image) that is consistent can't be searched by system from database, then can re-enter image, promptly get back to step 210.But if the result of contrast is consistent, system then can show the contrast signal (step 240) that meets the result, allows the user import the affirmation of content.
The user can be by the whether identification correct (step 250) of this system validation image.If identification is correct, then this system can be converted to control signal (step 260) with contrast signal as a result, handles control device for mobile communication (step 270) by control signal.Otherwise, the image data of being imported before then can deleting, and re-enter image, promptly get back to step 210.In any case as long as after confirming that image identification is correct, this system can carry out the adjustment of System Discrimination attribute immediately, thereby can comply with user's input habit.
Use action recognizing system of the present invention, can solve the speech recognition technology because of recording the different not high problems of discrimination power that cause with the sound quality of importing.The present invention is with the way of contrast of vivid identification in conjunction with motion track, searches in database.In identification process, the present invention has added the function of automatic mnemonic learning, this identification system can be carried out the adjustment of System Discrimination attribute automatically, and substitute the content of image database by the dynamic image in the external world, so can increase identification correctness and can the minimizing system for identification time of same action image.
The above only is the detailed description of the preferred embodiment of the present invention, still, is not in order to limit practical range of the present invention.Protection scope of the present invention should be as the criterion with the scope that accompanying claims define; all embodiments that meets the spirit variation similar of claims of the present invention with it; all should be included in the category of the present invention; equivalent variations and remodeling that all utilizations specification of the present invention and accompanying drawing content are done all should be contained within the appending claims restricted portion.
Claims (12)
1. an action recognizing system is used for device for mobile communication, and this system is characterized in that comprising:
One image capturing device, in order to absorb a dynamic image, this image capturing utensil has an image circuit, in order to convert this dynamic image to a digital image data;
One data storage is connected with this image capturing device, and in order to store this digital image data, this data storage has an image database, in order to deposit many group images reference data to this image database;
One contrast processor is connected with this data storage, and the digital image data that is stored in this data storage with the way of contrast of vivid identification in conjunction with motion track, is searched the image reference data of this image database, thereby born results contrast signal; And
One o controller is connected with this contrast processor, in order to receiving this contrast signal as a result, and with this as a result contrast signal convert a control signal to, handle this device for mobile communication of control by this control signal.
2. action recognizing system as claimed in claim 1 is characterized in that this device for mobile communication is a mobile phone.
3. action recognizing system as claimed in claim 1 is characterized in that this device for mobile communication is a personal digital assistant.
4. action recognizing system as claimed in claim 1 is characterized in that this image capturing device is a CCD camera.
5. action recognizing system as claimed in claim 1 is characterized in that this image reference data is presented by hand motion.
6. as claim 1 or 5 described action recognizing systems, it is characterized in that this image reference data is corresponding to digital 0-9.
7. action recognizing system as claimed in claim 1 is characterized in that this data storage is a flash memory.
8. action recognizing system as claimed in claim 1, but it is characterized in that this data storage is the erasing type read-only memory.
9. action recognizing system as claimed in claim 1 is characterized in that this contrast processor is a microcontroller.
10. action recognizing system as claimed in claim 1 is characterized in that this contrast processor is a digital signal processor.
11. an action identifying method is characterized in that comprising the following steps:
Absorb a dynamic image, simultaneously this dynamic image is converted to a digital image data, and be stored in the data storage;
This digital image data with the way of contrast of a vivid identification in conjunction with motion track, is searched many group images reference data of an image database, and produced a contrast signal as a result; And
With this as a result contrast signal be converted to a control signal, and by this control signal handle control one device for mobile communication.
12. action identifying method as claimed in claim 11 is characterized in that producing this as a result after the contrast signal, also comprises by the user and confirms this step of contrast signal correctness as a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021024197A CN100367809C (en) | 2002-01-18 | 2002-01-18 | Action recognizing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021024197A CN100367809C (en) | 2002-01-18 | 2002-01-18 | Action recognizing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1433236A CN1433236A (en) | 2003-07-30 |
| CN100367809C true CN100367809C (en) | 2008-02-06 |
Family
ID=27627558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB021024197A Expired - Lifetime CN100367809C (en) | 2002-01-18 | 2002-01-18 | Action recognizing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100367809C (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101581966B (en) * | 2008-05-16 | 2011-03-16 | 英业达股份有限公司 | Method and system for operating personal computer by utilizing action recognition |
| US8325978B2 (en) * | 2008-10-30 | 2012-12-04 | Nokia Corporation | Method, apparatus and computer program product for providing adaptive gesture analysis |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000036817A1 (en) * | 1998-12-17 | 2000-06-22 | Siemens Aktiengesellschaft | Communication-enabled image recording device |
-
2002
- 2002-01-18 CN CNB021024197A patent/CN100367809C/en not_active Expired - Lifetime
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000036817A1 (en) * | 1998-12-17 | 2000-06-22 | Siemens Aktiengesellschaft | Communication-enabled image recording device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1433236A (en) | 2003-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7831598B2 (en) | Data recording and reproducing apparatus and method of generating metadata | |
| CN101316324B (en) | Terminal and image processing method thereof | |
| EP2210214B1 (en) | Automatic identifying | |
| US20090112572A1 (en) | System and method for input of text to an application operating on a device | |
| JP5120777B2 (en) | Electronic data editing apparatus, electronic data editing method and program | |
| US7451090B2 (en) | Information processing device and information processing method | |
| CN106302933B (en) | Voice information processing method and terminal | |
| CN104168353A (en) | Bluetooth earphone and voice interaction control method thereof | |
| US20060036441A1 (en) | Data-managing apparatus and method | |
| US7623742B2 (en) | Method for processing document image captured by camera | |
| CN109871843A (en) | Character identifying method and device, the device for character recognition | |
| CN108182270A (en) | Search for content transmission and searching method, smart pen, search terminal and storage medium | |
| CN103076879A (en) | Multimedia interaction method and device based on face information, and terminal | |
| CN105608462A (en) | Character similarity judgment method and device | |
| KR20180109631A (en) | Electronic device and method for executing function of electronic device | |
| CN112130714A (en) | Keyword search method capable of learning and electronic equipment | |
| CN113806473A (en) | Intention recognition method and electronic equipment | |
| CN104239389A (en) | Methods and systems for media file management | |
| US20080244056A1 (en) | Method, device, and computer product for managing communication situation | |
| CN101825953A (en) | Chinese character input product with combined voice input and Chinese phonetic alphabet input functions | |
| CN109815311B (en) | Point reading method and system capable of identifying common books | |
| CN100367809C (en) | Action recognizing system | |
| US20150006173A1 (en) | System and Method for Processing a Keyword Identifier | |
| CN114691839A (en) | Intention slot position identification method | |
| CN113806469A (en) | Sentence intention identification method and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: I VALLEY HOLDINGS CO., LTD. Free format text: FORMER OWNER: YINGYEDA CO., LTD., TAIWAN Effective date: 20150713 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20150713 Address after: Cayman Islands, George Town Patentee after: IValley Holding Co., Ltd. Address before: Taipei City, Taiwan, China Patentee before: Inventec Corporation |
|
| CX01 | Expiry of patent term |
Granted publication date: 20080206 |
|
| CX01 | Expiry of patent term |