CN102004548B - System and method of inputting information by using image collecting equipment - Google Patents
System and method of inputting information by using image collecting equipment Download PDFInfo
- Publication number
- CN102004548B CN102004548B CN 201010550092 CN201010550092A CN102004548B CN 102004548 B CN102004548 B CN 102004548B CN 201010550092 CN201010550092 CN 201010550092 CN 201010550092 A CN201010550092 A CN 201010550092A CN 102004548 B CN102004548 B CN 102004548B
- Authority
- CN
- China
- Prior art keywords
- motion vector
- motion
- vector
- input
- information
- 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
Abstract
The invention provides system and method of inputting information by using image collecting equipment, wherein the method comprises the following steps: obtaining a motion vector of each block by dividing an image into blocks; carrying out length filtering to the obtained motion vector; obtaining main motion vectors of image motion; carrying out time de-noising on the main motion vectors, thus obtaining effective motion vectors; combining the effective motion vectors; and decoding the information of the vector combination by retrieving the corresponding relationship between input information stored by an information presentation storage unit and the vector combination so as to obtain the input information of the specific presentation.
Description
[technical field]
The present invention relates to the input information field, particularly about utilizing image capture device to carry out system and the method thereof of input information.
[background technology]
Existing electronic equipment, take mobile phone as example, carrying out the mode of input information a kind of is keyboard entry method, another is the touch-screen input mode.Because the touch-screen input mode meets people's writing style, therefore become gradually the main flow of input mode.
But existing handwriting pad and touch-screen, because Cost Problems is difficult to popularize.And usually all comprise camera in the existing mobile phone, if can utilize camera to replace handwriting pad or touch-screen to carry out the input of information then can provide easily in a lot of places inputting.
[summary of the invention]
The object of the present invention is to provide a kind of method of utilizing image capture device to carry out input information.
Another object of the present invention is to provide a kind of system that utilizes image capture device to carry out input information.
For reaching aforementioned purpose, a kind of method of utilizing image capture device to carry out input information of the present invention; It comprises:
Image is carried out the motion vector that piecemeal obtains each piecemeal;
The motion vector that obtains is carried out length filtering;
Obtain the main movement vector of image motion;
The main movement vector is carried out the time denoising, obtain effective motion vector;
The input message of its embodiments is obtained in the decoding that described efficient motion-vector is carried out information.
Further, the step that before carrying out the input message detection, also comprises the initial sum termination time section that at first defines input message.
Further, describedly the motion vector that obtains is carried out length filtering comprise: set the motion vector threshold values, be judged as disturbance less than the motion vector of motion vector threshold values, filtering is judged as the motion vector of disturbance.
Further, the described main movement vector that obtains image motion comprises: the direction to the filtered motion vector of length is set up histogram, and transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Obtain histogrammic peak value, the direction of target travel in the direction indication present image of this peak value, the motion vector of this direction is the main movement vector.
Further, described the main movement vector is carried out the time denoising, obtaining effective motion vector comprises: the time threshold values of setting motion vector, the motion vector of continued presence time less than the time threshold values is judged as disturbance, and the direction of motion of continued presence time greater than the motion vector of described time threshold values is the effective exercise direction.
Further, the decoding of described efficient motion-vector being carried out information comprises: the corresponding relation that characterizes the input message of cell stores and motion vector by gathering information is determined the input message of motion vector embodiments.
Further, if a plurality of efficient motion-vectors are arranged in the section input time, a plurality of efficient motion-vectors are arranged the effective motion vector set of formation in chronological order close, what aforementioned information characterized cell stores is the corresponding relation of input message and motion vector combination.
For reaching aforementioned another purpose, a kind of system that utilizes image capture device to carry out input information of the present invention, it comprises:
Motion estimation unit, it is used for that the image piecemeal is carried out motion search and obtains motion vector;
The length filter unit is used for that the motion vector that motion estimation unit is obtained is carried out length filtering and gets rid of disturbance;
Main movement vector computing unit is for the main movement vector of the moving target that calculates present image;
The time filtering unit is used for described main movement vector is carried out temporal denoising, finally obtains effective motion vector;
The motion vector decoding unit is used for described efficient motion-vector is carried out the input message that decoding of information is obtained its embodiments.
Further, described system also comprises input segment determining unit, is used for defining the initial sum termination time section of input message.
Further, the length filter unit is set the motion vector threshold values, is judged as disturbance less than the motion vector of motion vector threshold values, and filtering is judged as the motion vector of disturbance.
Further, main movement vector computing unit is set up histogram to the direction of the filtered motion vector of length filter unit length, and transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Then obtain histogrammic peak value, the direction of target travel in the direction indication present image of this peak value, the motion vector of this direction is the main movement vector.
Further, the time threshold values of motion vector is set in described time filtering unit, and the motion vector of continued presence time less than the time threshold values is judged as disturbance, and the direction of motion of continued presence time greater than the motion vector of described time threshold values is the effective exercise direction.
Further, described motion vector decoding unit also comprises the storage unit that a storing moving vector and corresponding informance characterize, and the corresponding relation that characterizes the input message of cell stores and motion vector by gathering information is determined the input message of motion vector embodiments.
Described system further comprises an effective assembled unit, when have a plurality of efficient motion-vector in the section input time, described effective assembled unit is arranged in chronological order the effective motion vector set of formation to a plurality of efficient motion-vectors and is closed, and what aforementioned information characterized cell stores is the corresponding relation of input message and motion vector combination.
System and the method thereof of utilizing image capture device to carry out input information of the present invention, utilize image capture device to gather moving image, and image carried out piecemeal, obtain respectively the motion vector of each piecemeal, then motion vector is carried out length filtering, obtain the main motion vector and carry out time filtering and obtain efficient motion-vector, the corresponding relation that recycles pre-stored motion vector and input message obtains the input message that motion vector represents, thereby realize utilizing image capture device can realize the input of information, can replace handwriting pad or touch-screen to realize input information, can reduce cost of products.
[description of drawings]
Fig. 1 utilizes image capture device to carry out the schematic flow sheet of the method for input information.
Fig. 2 utilizes image capture device to carry out the structured flowchart of the system of input information.
[embodiment]
Alleged " embodiment " or " embodiment " refer to be contained in special characteristic, structure or the characteristic at least one implementation of the present invention herein.Different local in this manual " in one embodiment " that occur not are all to refer to same embodiment, neither be independent or the embodiment mutually exclusive with other embodiment optionally.In addition, represent the sequence of unit in method, process flow diagram or the functional block diagram of one or more embodiment and revocablely refer to any particular order, also be not construed as limiting the invention.
The invention relates to electronic equipment, such as mobile phone, PDA or panel computer etc. carried out the system and method for input information, wherein all is equipped with image capture device in these electronic equipments, for example camera.The below will take mobile phone as example, describe system of the present invention and Fang Fang take input Chinese character information in mobile phone as instantiation.
Because the Chinese character that has may only have a stroke, and the Chinese-character stroke that has is many, Chinese character can be disassembled into different strokes for the Chinese character of many strokes and carry out the input message detection, then each stroke combination is become a complete Chinese character.The Chinese character of single stroke is as a special case of many strokes Chinese character.The below describes information input system of the present invention and method as the Chinese character of a plurality of strokes as example take the information of input.
See also shown in Figure 1ly, it shows the process flow diagram that utilizes camera to carry out the method for input information of the present invention, and wherein the information of input is the Chinese character of many strokes.As shown in Figure 1, of the present inventionly utilize method that camera carries out input information it comprise:
Step S11: when input message in mobile phone, at first need to define and once carry out the input time that input message detects, also can be called definition input segment, in the input segment, carry out the detection of input message.Can be to set certain button to press the time of upspringing when definition input segment, also can be directly to define the once time of input.The input of finishing in input chip is concluded the time of justice is only an input message, if segment input time of definition also finishes, then can continue entering stroke, just carries out the final judgement of input message after input chip is concluded adopted time end.
Step S12: in the input segment, the image of camera collection input for example is to carry out writing of Chinese character by finger motion, and then the image of camera collection finger motion carries out piecemeal to image and carries out estimation, obtains the motion vector of each piecemeal.Can adopt the method for existing various motion detection about the technology of motion detection in the video image, for example frame differential method, background subtracting method, statistical average method, median filter method etc. are enumerated detailed description no longer one by one about concrete principle and this instructions of content of the method for motion detection.
Step S13: the motion vector that obtains is carried out length filtering.Because may sometimes be that the operator does not carry out input action in input process, but some disturbance factors be captured other little tricks such as the bending of pointing or shake by camera.For avoiding these disturbance factors to the interference of input message, the threshold values of a motion vector length can be set, when the length of motion vector thinks that just the operator is carrying out input information during greater than this length threshold values, if the length of motion vector is less than this length threshold values, think that then this motion vector is disturbance, this motion vector of filtering.
Step S14: the main movement vector that obtains image motion.To setting up histogram through the direction of the motion vector after the length filtering, transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Obtain histogrammic peak value, the direction of target travel in the direction indication present image of this peak value, the motion vector of this direction is the main movement vector.
Step S15: the main movement vector is carried out the time denoising, obtain effective motion vector.Although because some motion vector length satisfies the threshold values of length, might be operator's maloperation, such as finger accidental slip before the camera, possible motion vector be also very long.For determining it is that the operator is in input message really, can set the life period threshold values of motion vector, when the life period of motion vector less than this during threshold values predetermined time, judge that this motion vector is disturbance, it is carried out filtering removes, when continued presence time of motion vector surpasses this predetermined time and judges that the direction of motion of this motion vector is the effective exercise direction during threshold values, this motion vector is efficient motion-vector.
Step S16: each efficient motion-vector is made up.Because the corresponding motion vector of every unicursal for representing whole Chinese character, need to make up each efficient motion-vector, for example a plurality of efficient motion-vectors are arranged the effective motion vector set of formation in chronological order and close.
Step S17: the efficient motion-vector to input is combined into row decoding.Can preset in advance the corresponding relation of input message (for example stroke of Chinese character input) and motion vector combination, when combination is deciphered to motion vector, determine the input message of motion vector combination embodiments by the corresponding relation of transferring the combination of pre-stored input message and motion vector.
The step of motion vector combination can be regarded as the combination of single stroke oneself for the input of the Chinese character of single stroke, can be understood as does not need to carry out the motion vector combination yet, correspondingly, predefined input message is the corresponding relation with motion vector, when motion vector is deciphered, determine the input message of motion vector embodiments by the corresponding relation of transferring pre-stored input message and motion vector.
See also shown in Figure 2ly, it shows the structured flowchart that utilizes an embodiment of the system 1 that image capture device carries out input information of the present invention.As shown in Figure 2, of the present inventionly utilize system that image capture device carries out input information 1 it comprises motion estimation unit 11, length filter unit 12, main movement vector computing unit 13, time filtering unit 14, effectively assembled unit 15 and combination decoding unit 16.
Motion estimation unit 11, it is used for that the image piecemeal is carried out motion search and obtains motion vector.In one embodiment, for example be to carry out writing of Chinese character by finger motion, the image of camera collection finger motion then, 11 pairs of images of motion estimation unit carry out piecemeal and carry out estimation, obtain the motion vector of each piecemeal.Can adopt the method for existing various motion detection about the technology of motion detection in the video image, for example frame differential method, background subtracting method, statistical average method, median filter method etc. are enumerated detailed description no longer one by one about concrete principle and this instructions of content of the method for motion detection.
Length filter unit 12 is used for that the motion vector that motion estimation unit 11 is obtained is carried out length filtering and gets rid of disturbance.Because may sometimes be that the operator does not carry out input action in input process, but some disturbance factors be captured other little tricks such as the bending of pointing or shake by camera.For avoiding these disturbance factors to the interference of input message, the threshold values of a motion vector length can be set, when the length of motion vector thinks that just the operator is carrying out input information during greater than this length threshold values, if the length of motion vector is less than this length threshold values, think that then this motion vector is disturbance, this motion vector of filtering.
Main movement vector computing unit 13 is for the main movement vector of the moving target that calculates present image.13 pairs of directions through the motion vector after the 12 length filtering of length filter unit of main movement vector computing unit are set up histogram, and transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Then obtain histogrammic peak value, the direction of this peak value just represents the direction of target travel in the present image, and the motion vector of this direction is the main movement vector.
Time filtering unit 14, the main movement vector that is used for described main movement vector computing unit 13 is calculated carries out temporal denoising, finally obtains effective motion vector.Although because some motion vector length satisfies the threshold values of length, might be operator's maloperation, such as finger accidental slip before the camera, possible motion vector be also very long.For determining it is that the operator is in input message really, can set the life period threshold values of motion vector, when the life period of motion vector less than this during threshold values predetermined time, judge that this motion vector is disturbance, it is carried out filtering removes, when continued presence time of motion vector surpasses this predetermined time and judges that the direction of motion of this motion vector is the effective exercise direction during threshold values, this motion vector is efficient motion-vector.
Effective assembled unit 15, input message is the Chinese character input of many strokes in the present embodiment, the corresponding efficient motion-vector of each stroke, when had a plurality of efficient motion-vector in the section input time, 15 pairs of a plurality of efficient motion-vectors of described effective assembled unit were arranged in chronological order the effective motion vector set of formation and are closed.
Combination decoding unit 16 is used for the efficient motion-vector after aforementioned effective assembled unit 15 combinations is combined into row decoding, obtains the input message of its embodiments.In combination decoding unit 16, comprise the storage unit 161 that a storing moving vectorial combination and corresponding informance characterize, when decoding, combination decoding unit 16 is transferred the motion vector of storage unit 161 interior storages and the corresponding relation that corresponding informance characterizes, and then can obtain the input message of this motion vector combination embodiments.
Be to comprise effective assembled unit in the aforementioned embodiment, many stroke combination are become a Chinese character, if the single stroke Chinese character, can be regarded as the special case of effective assembled unit, only a stroke being made up or is interpreted as does not need this effective assembled unit.
In an embodiment of the present invention, it can also comprise that an input chip concludes adopted unit (not shown), is used for defining the time period that the initial sum of each input stops.The input of finishing in input chip is concluded the time of justice is only an input message, and the input that surpasses this time then can't be charged to this input, if be not totally lost, then needs to re-enter.
Above-mentioned explanation has fully disclosed the specific embodiment of the present invention.It is pointed out that and be familiar with the scope that any change that the person skilled in art does the specific embodiment of the present invention does not all break away from claims of the present invention.Correspondingly, the scope of claim of the present invention also is not limited only to previous embodiment.
Claims (8)
1. method of utilizing image capture device to carry out input information; It comprises:
Image is carried out the motion vector that piecemeal obtains each piecemeal;
The motion vector that obtains is carried out length filtering, set motion vector length threshold values, be judged as disturbance less than the motion vector of motion vector length threshold values, filtering is judged as the motion vector of disturbance;
Obtain the main movement vector of image motion;
The main movement vector is carried out the time denoising, obtain effective motion vector, set the time threshold values of motion vector, the motion vector of described main movement vector continued presence time less than the time threshold values is judged as disturbance, and the direction of motion of described main movement vector continued presence time greater than the motion vector of described time threshold values is the effective exercise direction;
The input message of its embodiments is obtained in the decoding that described efficient motion-vector is carried out information, preset the corresponding relation of each input message and motion vector, it is stored in the information representation storage unit, determines the input message of motion vector embodiments by the corresponding relation of transferring pre-stored input message and motion vector.
2. the method for utilizing image capture device to carry out input information as claimed in claim 1 is characterized in that: the step that also comprised the initial sum termination time section that at first defines input message before carrying out the input message detection.
3. the method for utilizing image capture device to carry out input information as claimed in claim 1, it is characterized in that: the described main movement vector that obtains image motion comprises: the direction to the filtered motion vector of length is set up histogram, transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Obtain histogrammic peak value, the direction of target travel in the direction indication present image of this peak value, the motion vector of this direction is the main movement vector.
4. the method for utilizing image capture device to carry out input information as claimed in claim 1, it is characterized in that: if a plurality of efficient motion-vectors are arranged in the section input time, a plurality of efficient motion-vectors are arranged the effective motion vector set of formation in chronological order close, what aforementioned information characterized cell stores is the corresponding relation of input message and motion vector combination.
5. system that utilizes image capture device to carry out input information, it comprises:
Motion estimation unit, it is used for that the image piecemeal is carried out motion search and obtains motion vector;
The length filter unit, be used for that the motion vector that motion estimation unit is obtained is carried out length filtering and get rid of disturbance, the length filter unit is set motion vector length threshold values, is judged as disturbance less than the motion vector of motion vector length threshold values, and filtering is judged as the motion vector of disturbance;
Main movement vector computing unit is for the main movement vector of the moving target that calculates present image;
The time filtering unit, be used for described main movement vector is carried out temporal denoising, finally obtain effective motion vector, the time threshold values of motion vector is set in described time filtering unit, the motion vector of main motion vector continued presence time less than the time threshold values is judged as disturbance, and the direction of motion of main motion vector continued presence time greater than the motion vector of described time threshold values is the effective exercise direction;
The motion vector decoding unit, be used for described efficient motion-vector is carried out the input message that decoding of information is obtained its embodiments, described motion vector decoding unit also comprises the storage unit of a storing moving vector and corresponding input message, and the corresponding relation that characterizes the input message of cell stores and motion vector by gathering information is determined the input message of motion vector embodiments.
6. the system that utilizes image capture device to carry out input information as claimed in claim 5 is characterized in that: it also comprises input segment determining unit, is used for defining the initial sum termination time section of input message.
7. the system that utilizes image capture device to carry out input information as claimed in claim 5, it is characterized in that: main movement vector computing unit is set up histogram to the direction of the filtered motion vector of length, transverse axis characterizes direction, and the longitudinal axis characterizes the number of this direction motion vector; Obtain histogrammic peak value, the direction of target travel in the direction indication present image of this peak value, the motion vector of this direction is the main movement vector.
8. the system that utilizes image capture device to carry out input information as claimed in claim 5, it is characterized in that: it further comprises an effective assembled unit, when have a plurality of efficient motion-vector in the section input time, described effective assembled unit is arranged in chronological order the effective motion vector set of formation to a plurality of efficient motion-vectors and is closed, and what aforementioned information characterized cell stores is the corresponding relation of input message and motion vector combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010550092 CN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010550092 CN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102004548A CN102004548A (en) | 2011-04-06 |
| CN102004548B true CN102004548B (en) | 2013-02-13 |
Family
ID=43811952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010550092 Active CN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102004548B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113452A (en) * | 1988-08-23 | 1992-05-12 | Sony Corporation | Hand-written character recognition apparatus and method |
| CN1881994A (en) * | 2006-05-18 | 2006-12-20 | 北京中星微电子有限公司 | Method and apparatus for hand-written input and gesture recognition of mobile apparatus |
| CN101539994A (en) * | 2009-04-16 | 2009-09-23 | 西安交通大学 | Mutually translating system and method of sign language and speech |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2985935B2 (en) * | 1995-10-04 | 1999-12-06 | 日本電気株式会社 | Handwritten character / graphic reader |
-
2010
- 2010-11-18 CN CN 201010550092 patent/CN102004548B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113452A (en) * | 1988-08-23 | 1992-05-12 | Sony Corporation | Hand-written character recognition apparatus and method |
| CN1881994A (en) * | 2006-05-18 | 2006-12-20 | 北京中星微电子有限公司 | Method and apparatus for hand-written input and gesture recognition of mobile apparatus |
| CN101539994A (en) * | 2009-04-16 | 2009-09-23 | 西安交通大学 | Mutually translating system and method of sign language and speech |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102004548A (en) | 2011-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111857356B (en) | Method, device, equipment and storage medium for recognizing interaction gesture | |
| EP3792869A1 (en) | Video deblurring method and apparatus, and storage medium and electronic apparatus | |
| CN106709932B (en) | Face position tracking method and device and electronic equipment | |
| EP3644219A1 (en) | Human face feature point tracking method, device, storage medium and apparatus | |
| CN108230232B (en) | Image processing method and related device | |
| CN105631427A (en) | Suspicious personnel detection method and system | |
| CN108479066B (en) | False touch prevention method, mobile terminal and computer readable storage medium | |
| CN109190532A (en) | It is a kind of based on cloud side fusion face identification method, apparatus and system | |
| US11158035B2 (en) | Method and apparatus for acquiring queuing information, and computer-readable storage medium thereof | |
| CN106060254A (en) | Incoming call answering method for mobile terminal and mobile terminal | |
| CN112153343B (en) | Elevator safety monitoring method and device, monitoring camera and storage medium | |
| CN110275794B (en) | Screen display method of terminal, and computer-readable storage medium | |
| CN106161916A (en) | A kind of image-pickup method and electronic equipment | |
| CN106055404B (en) | Method and device for cleaning background application program | |
| CN109584897B (en) | Video noise reduction method, mobile terminal and computer readable storage medium | |
| WO2023185037A1 (en) | Action detection method and apparatus, electronic device, and storage medium | |
| CN107145855B (en) | Reference quality blurred image prediction method, terminal and storage medium | |
| US20160085408A1 (en) | Information processing method and electronic device thereof | |
| CN110766131A (en) | Data processing device and method and electronic equipment | |
| CN102004548B (en) | System and method of inputting information by using image collecting equipment | |
| CN111382599A (en) | Image processing method and device and electronic equipment | |
| CN110223239B (en) | Image processing method, terminal and computer readable storage medium | |
| CN111093059A (en) | Monitoring method and related equipment | |
| CN108063894B (en) | Video processing method and mobile terminal | |
| CN108564059B (en) | Wearable device, data processing method and device thereof, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 214028 10-storey Building 530 Qingjia Road, Taihu International Science Park, Wuxi New District, Jiangsu Province Patentee after: WUXI ZHONGGAN MICROELECTRONIC CO., LTD. Address before: 214028 10-storey Building 530 Qingjia Road, Taihu International Science Park, Wuxi New District, Jiangsu Province Patentee before: Wuxi Vimicro Co., Ltd. |
|
| CP01 | Change in the name or title of a patent holder |