CN104767926A - Automatic focusing method and device - Google Patents
Automatic focusing method and device Download PDFInfo
- Publication number
- CN104767926A CN104767926A CN201410006852.1A CN201410006852A CN104767926A CN 104767926 A CN104767926 A CN 104767926A CN 201410006852 A CN201410006852 A CN 201410006852A CN 104767926 A CN104767926 A CN 104767926A
- Authority
- CN
- China
- Prior art keywords
- text
- region
- focusing
- lens focusing
- lens
- 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
Abstract
The embodiment of the invention provides an automatic focusing method, which comprises the following steps: a text in an image range is detected, and a region where the text is located is analyzed and determined; multiple text images of the text in the region are acquired, and a lens focusing position of the region is determined; and according to the lens focusing position of the region, a lens focusing position of the text in the image range is determined. The embodiment of the invention also provides an automatic focusing device, which comprises a detection module, a focusing module and a positioning module. According to the method and the device provided by the invention, the text image can be effectively focused, and accuracy and the rate of extracting the text content in the image can be improved. In addition, based on the text focusing mode, the speed and convenience of shooting the text can be improved, the automatic focusing problem of single-text shooting and multi-text shooting can be solved, man-machine interaction times can be effectively reduced, and use convenience of the user is improved.
Description
Technical field
The present invention relates to optical focus technical field, specifically, the present invention relates to method and the device of text image auto-focusing.
Background technology
Technology of auto is adopted based on mostly needing in the picture material acquisition methods of image.For obtaining the Autofocus Technology of picture material, refer to the distance according to subject, the position of the mirror group that automatically focuses in adjustment camera lens, makes object be imaged on imaging plane clearly, thus obtains the picture material on imaging plane further.Nowadays Autofocus Technology has been widely used on the image acquiring device such as camera, video camera, and relative to tradition focusing technology, Autofocus Technology has the advantages such as simple, quick and easy.
At present, for obtaining the Autofocus Technology of picture material, the region paid close attention to when focusing according to it can be divided into overall focusing technology and local focusing technology.
On the one hand, overall focusing technology is one focusing technology main at present, and it utilizes the Global Information of image to focus.At present, based on the Autofocus Technology of global information, the micromatic setting by regulating on automatic zoom camera lens mostly, automatic zoom camera lens is moved at different relative positions, and calculate AF assessed value according to the contrast of testee imaging on CCD, then by the AF assessed value of camera lens at each relative position and the relative position of camera lens, send into microcomputer to analyze simultaneously, microcomputer plots AF according to these values and assesses curve, relative position of lens when AF being assessed hump is defined as the corresponding relative position of lens of pinpointed focus, again its parameter is sent back to the micromatic setting on automatic zoom camera lens, to complete auto-focus process.
On the other hand, local region of interest focusing technology is then focus in the key area paid close attention to according to user in process of taking pictures.Present Application comparison is the Autofocus Technology based on face widely.Face focusing technology refer to, in auto-focus process, first find out the face in subject with human face detection tech, orient face block, then using face block as focusing object and find range.
Again on the one hand, prior art also teaches the method for text shooting, but be only adopt the mode of reprocessing to process the text image after shooting, improve its definition, instead of focus when taking.
Therefore for the existing picture material acquisition methods based on image at present, the Autofocus Technology adopted mainly carries out autozoom for global image and local facial to image.Along with popularizing of image acquiring device, picture shooting range of application is more and more extensive, extends many application newly, especially text shooting.Such as, the range of application of text shooting can comprise books shooting, photographing business card, car plate shooting or placard shooting etc.These picture materials obtained directly are preserved as pictorial information, or text message corresponding to pictorial information convert to, to carry out follow-up editor and preservation by text recognition software.But, for the existing picture material acquisition methods based on image, be no matter the overall situation focusing technology for image, or for the local focusing technology of recognition of face, existing Autofocus Technology not focus using text as Primary Reference object.Thus,, in process text shooting process, there are some common limitation, or be called common defects in the existing picture material acquisition methods based on image, even if the picture contrast of full figure reaches a reasonable effect, but text filed needed for user may but and unintelligible.
Therefore, be necessary the focusing scheme proposing effective text image, thus improve from image, obtain content of text accuracy rate and speed.
Summary of the invention
Object of the present invention is intended at least solve one of above-mentioned technological deficiency, particularly provides a kind of method and device of auto-focusing, for by obtaining several text images being in the text in region, determines the lens focusing position in region; According to the lens focusing position in region, determine the lens focusing position of the text in image range, to solve the focusing scheme that cannot realize effective text image in prior art, from image, obtain the problem that accuracy rate is low and speed is low of content of text.
For achieving the above object, the embodiment of the present invention provides a kind of method of auto-focusing on the one hand, comprises the steps:
Text in detected image scope, analyzes and determines the region at text place;
Obtain several text images being in the text in described region, determine the lens focusing position in described region;
According to the lens focusing position in described region, determine the lens focusing position of the text in described image range.
The embodiment of the present invention on the other hand provides a kind of method of taking text image, to focus and take according to the method for auto-focusing as above to text image.
The embodiment of the present invention provides a kind of device of auto-focusing on the other hand, comprises detection module, Focusing module and locating module,
Described detection module, for the text in detected image scope, analyzes and determines the region at text place;
Described Focusing module, for obtaining several text images of the text being in described region, determines the lens focusing position in described region;
Described locating module, for the lens focusing position according to described region, determines the lens focusing position of the text in described image range.
The embodiment of the present invention on the other hand provides a kind of capture apparatus, comprises the device of auto-focusing as above, to focus and take according to described device to text image.
The beneficial effect of embodiment provided by the invention comprises:
In embodiment provided by the invention, by the text in detected image scope, analyze and determine the region at text place; Obtain several text images being in the text in region, determine the lens focusing position in region; According to the lens focusing position in region, determine the lens focusing position of the text in image range; Thus the effective focusing achieved text image, and then improve from image, obtain content of text accuracy rate and speed.The such scheme that the present invention proposes, very little to the change of existing system, can not the compatibility of influential system, and realize simple, efficient.
The aspect that the present invention adds and advantage will part provide in the following description, and these will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the flow chart of a kind of embodiment of method of auto-focusing of the present invention;
Fig. 2 is the flow chart analyzed the region at text place in the another kind of embodiment of method of auto-focusing of the present invention;
Fig. 3 is the auto-focusing flow chart in the single region in the another kind of embodiment of method of auto-focusing of the present invention;
Fig. 4 is the multizone auto-focusing flow chart in the another kind of embodiment of method of auto-focusing of the present invention;
Fig. 5 is the structural representation of a kind of embodiment of device of auto-focusing of the present invention.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.
Those skilled in the art of the present technique are appreciated that unless expressly stated, and singulative used herein " ", " one ", " described " and " being somebody's turn to do " also can comprise plural form.Should be further understood that, the wording used in specification of the present invention " comprises " and refers to there is described feature, integer, step, operation, element and/or assembly, but does not get rid of and exist or add other features one or more, integer, step, operation, element, assembly and/or their group.Should be appreciated that, when we claim element to be " connected " or " coupling " to another element time, it can be directly connected or coupled to other elements, or also can there is intermediary element.In addition, " connection " used herein or " coupling " can comprise wireless connections or wirelessly to couple.Wording "and/or" used herein comprises one or more whole or arbitrary unit listing item be associated and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, and all terms used herein (comprising technical term and scientific terminology), have the meaning identical with the general understanding of the those of ordinary skill in field belonging to the present invention.It should also be understood that, those terms defined in such as general dictionary, should be understood to that there is the meaning consistent with the meaning in the context of prior art, unless and by specific definitions as here, otherwise can not explain by idealized or too formal implication.
Those skilled in the art of the present technique are appreciated that, here used " terminal ", " terminal equipment " had both comprised the equipment of wireless signal receiver, it only possesses the equipment of the wireless signal receiver without emissivities, comprise again the equipment receiving and launch hardware, it has and on bidirectional communication link, can carry out the reception of two-way communication and launch the equipment of hardware.This equipment can comprise: honeycomb or other communication equipments, its honeycomb or other communication equipment of having single line display or multi-line display or not having multi-line display; PCS(Personal Communications Service, PCS Personal Communications System), it can combine voice, data processing, fax and/or its communication ability; PDA(PersonalDigital Assistant, personal digital assistant), it can comprise radio frequency receiver, beep-pager, the Internet/intranet access, web browser, notepad, calendar and/or GPS(Global PositioningSystem, global positioning system) receiver; Conventional laptop and/or palmtop computer or other equipment, it has and/or comprises the conventional laptop of radio frequency receiver and/or palmtop computer or other equipment.Here used " terminal ", " terminal equipment " can be portable, can transport, be arranged in the vehicles (aviation, sea-freight and/or land), or be suitable for and/or be configured at local runtime, and/or with distribution form, any other position operating in the earth and/or space is run.Here used " terminal ", " terminal equipment " can also be communication terminal, access terminals, music/video playback terminal, can be such as PDA, MID(Mobile Internet Device, mobile internet device) and/or there is the mobile phone of music/video playing function, also can be the equipment such as intelligent television, Set Top Box.
In order to realize object of the present invention, the embodiment of the present invention proposes a kind of method of auto-focusing, comprises the steps:
Text in detected image scope, analyzes and determines the region at text place;
Obtain several text images being in the text in region, determine the lens focusing position in region;
According to the lens focusing position in region, determine the lens focusing position of the text in image range.
In the above embodiment of the present invention, by the text in detected image scope, analyze and determine the region at text place; Obtain several text images being in the text in region, determine the lens focusing position in region; According to the lens focusing position in region, determine the lens focusing position of the text in image range; Thus the effective focusing achieved text image, and then improve from image, obtain content of text accuracy rate and speed.
As shown in Figure 1, the flow chart of a kind of embodiment of the method for auto-focusing of the present invention, comprises step S110 to step S130, below in conjunction with specific embodiment, carries out expansion explanation to step S110 to step S130.
S110: the text in detected image scope, analyzes and determines the region at text place.
As embodiments of the invention, analyze and determine the region at text place, comprising the following steps:
Judge the size of character in image range, and the definition of the character on border, judging area and the character of regional center;
By the region of the same size of character in image range, and the region that the character of zone boundary is consistent with the definition of the character of regional center, be divided into a single region.
Specifically, as shown in Figure 2, be the flow chart that the region at text place is analyzed in the another kind of embodiment of method of auto-focusing of the present invention.
First carry out text detection, printed page analysis 201 is carried out to the area image of the text obtained, judges that whether the space of a whole page is regular, carry out different process according to different judged results.Here the space of a whole page said is regular refers to that character boundary is consistent, and has consistent character sharpness.Should be appreciated that the character boundary one in the present invention makes peace character sharpness unanimously, consistent implication refers to identical, namely not there are differences, or the difference existed is less, and the difference of existence is within predetermined threshold value.Such as, when the difference of the size between character is within predetermined threshold value, think that character boundary is consistent; When the difference of the definition between character is within predetermined threshold value, think that character sharpness is consistent.
Here judge that the regular method of the space of a whole page is, on the one hand, utilize judge the text obtained region in, whether the uniformity coefficient of character boundary consistent.On the other hand, judge in the region of the text obtained, whether character has consistent definition; Concrete determination methods for: judge that in the region of text that obtains, whether definition and the regional center partial character definition of the character of boundary member close.Particularly, analyze and determine the region at text place, comprising the following steps: the size judging character in image range, and the definition of the character on border, judging area and the character of regional center; By the region of the same size of character in image range, and the region that the character of zone boundary is consistent with the definition of the character of regional center, be divided into a single region.If above-mentioned analysis result display: in the region of obtained text, character boundary is consistent, and has consistent definition, both meets, is then focused as a whole in the region of the text, i.e. single text filed focusing.
In the process of text detection, printed page analysis, utilize binaryzation information or marginal information, the positional information and elevation information that obtain character can be analyzed, and then positional information and the elevation information of obtained character can be utilized, whether character boundary in region is unanimously judged.Particularly, utilize character location information, on original color image or gray level image, can calculating character definition.Here the method that Analysis of Contrast, histogram analysis or ambiguity are analyzed can be adopted, as definition evaluation method.
If above-mentioned analysis result display: in the region of obtained text, character boundary is inconsistent, and namely in region, character boundary difference is comparatively large, then text is carried out cutting text block 202, namely by zoning, make character boundary in each text block consistent; Then to the different text block marked off, the multifocal technology that employing is mentioned below is focused, i.e. how text filed focusing.
If above-mentioned analysis result display: in the region of obtained text, character does not have consistent definition, and namely in the region of obtained text, the character sharpness difference of borderline region and central area is larger, now, then the region of obtained text is divided.If the rule of text alignment, then adopt uniform grid to carry out grid cutting 203, if text arrange in region irregular, then according to the position of text block and density, adopt the region of non-uniform grid to obtained text to divide.To the different text block that Region dividing goes out, the multifocal technology that employing is mentioned below is focused, i.e. how text filed focusing.
After the process of step S110, by analysis, text will belong to one or more region to the text in image range.Wherein, the image information belonged in a region is character boundary is consistent with character sharpness.
S120: obtain several text images being in the text in region, determine the lens focusing position in region.
In the step s 120, obtain several text images being in the text in region, determine the lens focusing position in region, comprise the following steps:
Obtain several text images being in single region;
Calculate the quality of each width text image based on text detection information, use optimum first quality position of searching algorithm search;
Optimum first quality position is defined as the lens focusing position in single region.
Furthermore, also comprise:
Determine the adjacent area of optimum first quality position;
With the point on adjacent area for focus, calculate text quality based on identification and semantic information, utilize searching algorithm to search for optimum second quality position;
Optimum second quality position is defined as the lens focusing position in single region.
As shown in Figure 3, be the auto-focusing flow chart in the single region in the another kind of embodiment of method of auto-focusing of the present invention, below in conjunction with Fig. 3, the present invention will be described.
Specifically, if only have one text filed, then by regulating the micromatic setting on automatic zoom camera lens, automatic zoom camera lens is moved, to obtain the text image of different relative position at different relative positions; To the text image of the different relative position of several shooting imagings obtained, call text quality's assessment and carry out text quality's assessment, particularly, step 301 calculates text image quality, to obtain text quality's assessment result based on text detection information.To the area image of the text of input, carry out text quality's assessment, concrete quality evaluation process is: utilize the character quantity calculating the region detecting text, and calculates the contrast of character and background color in the region of this detection text; By information such as the contrasts of above-mentioned character quantity and character and background color, as the standard of assessment current text picture quality, and export text quality's quality of evaluation value.To obtain to obtain the text image of different relative position, adopt the text image quality method of above-mentioned diverse location to draw corresponding picture quality change curve.Step 302 uses searching algorithm to search for optimum first quality position, the i.e. lens location corresponding to peak of searching image mass-change curve.Detect and whether search optimum quality point, if testing result display searches optimum quality point, namely during optimum first quality position, then stop focal position search procedure, and further judge whether that choice for use high accuracy is focused; If testing result display does not search optimum quality point, when namely not finding optimum first quality position, then continue to enter step 303 and adjust lens location, enter thereafter the area image that step 304 obtains text; Return step 301 afterwards and carry out reprocessing.
Further, judge whether that choice for use high accuracy is focused.On the one hand, if judgment result displays not choice for use high accuracy focusing, then choice for use rapid focus, by the above-mentioned optimum quality point searched, i.e. optimum first quality position, as optimal focus position, and lens moving is completed auto-focusing to this position, export the information of optimum first quality position simultaneously.
On the other hand, if the focusing of judgment result displays choice for use high accuracy, then choice for use high accuracy focusing; Choice for use high accuracy is focused, and needs to enter step 305 and calculates binary search region.Here adopt at the above-mentioned optimum quality point searched, i.e. optimum first quality position place, a segment distance is respectively got in both sides forwards, backwards, thus forms high accuracy region of search.In this high accuracy region of search, use the assessment of high accuracy text quality by binary search, carry out text quality's assessment.The assessment of high accuracy text quality in above process, performs step 306 and calculates text quality, to obtain text quality's assessment result based on identification and semantic information.Particularly, the assessment of high accuracy text quality uses text identification and semantic technology, identifies, and according to semantic technology, analyze the reasonability of its recognition result to the text in text filed, finally exports text quality's score value to it.In binary search, again can obtain a text image mass-change curve figure, perform step 307 and utilize searching algorithm to search for optimum second quality position, the i.e. lens location corresponding to peak of picture quality change curve.If optimum quality position is not yet determined, then enter step 308 and adjust lens location, and perform the area image that step 309 obtains text, proceed thereafter the process of step 306.Detect and whether search optimum quality point, if testing result display searches optimum quality point, namely during optimum second quality position, then stop focal position search procedure, and export the optimum quality point searched, i.e. the information of optimum second quality position.
Obviously, optimum first quality position may be identical with optimum second quality position, also may be different.
S130: according to the lens focusing position in region, determines the lens focusing position of the text in image range.
As embodiments of the invention, determine the lens focusing position of the text in image range, comprising:
The lens focusing position of the text in image range is lens focusing position, one or more single region.
Specifically, when the text in image range is exactly an overall region, now, the lens focusing position of the text in image range is the lens focusing position in region.
When the text in image range is divided into multiple region, now, the lens focusing position of the text in image range is the lens focusing position in multiple region, namely export multiple focus, if need, to pictograph shooting, to take multiple focus exactly, obtain multiple text filed image, can preserve multiple images, also can to multiple imagery exploitation image fusion technology, permeated an optimum image.
Furthermore, when region is plural region, the lens focusing position in region can also be synthesized, obtain the lens focusing position of the text in image range.
As embodiments of the invention, when the lens focusing position of the text in image range is multiple single lens focusing position, region, optimum focal point plane is simulated to multiple focus, by the position of the camera lens of focus when optimum focal point plane, as the lens focusing position of the text in image range.
By obtained multiple optimal focus position, the mode that employing two kinds is different respectively processes:
1) difference technique is utilized, optimum focal point plane is obtained to multiple focus, use the distance of focal plane as auto-focusing result, namely fitting technique is used to simulate optimum focal point plane to multiple focus, by the position of the camera lens of focus when this optimum focal point plane, as final auto-focusing focus;
2) using multiple focus as focusing focus, take, to obtain multiple images, can preserve multiple images.
As shown in Figure 4, be the multizone auto-focusing flow chart in the another kind of embodiment of method of auto-focusing of the present invention.
Specifically, if how text filed, then multifocal text technique for taking is adopted to take.Multifocal text shooting process is as follows:
1) step 401:
Adopt single text filed focusing, obtain each text filed focus information.Detailed process is: separately that each is text filed as perpetual object, the previously described region by the text is adopted to focus as a whole, namely single text filed focusing is adopted, obtain each text filed focus information, wherein, text filed focus information comprises each text filed optimal focus position and text filed external boundary distribution thereof.
2) judge it is take for several text images, or take for single width text image.
3) step 402:
If select to take for single width text image, select single focus output mode exactly, the focus of minimum-depth then can be selected as final auto-focusing focus, also the method merging focal plane can be adopted, fitting technique is used to simulate optimum focal point plane to multiple focus, by the position of the camera lens of focus when this optimum focal point plane, as final auto-focusing focus, and export the corresponding information of this optimal focus position.
4) step 403:
If select to take for several text images, be exactly select multifocal output mode, then to each text filed respectively as area-of-interest, utilize the focus information that several text images of list text filed focusing technology export are above corresponding.
In the above embodiment of the present invention, by the text in detected image scope, analyze and determine the region at text place; Obtain several text images being in the text in region, determine the lens focusing position in region; According to the lens focusing position in region, determine the lens focusing position of the text in image range; Thus the effective focusing achieved text image, and then improve from image, obtain content of text accuracy rate and speed.
Further, text based focal modes, can make the text filed shooting effect obtaining optimum paid close attention to, thus effectively can strengthen the identification of text, or increase the accuracy of follow-up text identification in shooting process.In addition, text based focal modes, can improve speed and the convenience of shooting text, and can solve the auto-focusing problem of the shooting of single text and the shooting of many texts, can effectively reduce man-machine interaction number of times, improve the convenience that user uses.
The embodiment of the present invention provides a kind of method of taking text image on the other hand, and the method according to above-mentioned disclosed auto-focusing is focused to text image, and take text image thereafter, detail does not repeat them here.
Fig. 5 is the structural representation of a kind of embodiment of device of auto-focusing of the present invention.As shown in Figure 5, the device 500 of the present embodiment auto-focusing comprises detection module 510, Focusing module 520 and locating module 530.
Detection module 510, for the text in detected image scope, analyzes and determines the region at text place.
Specifically, detection module 510, for analyzing and determining the region at text place, comprises the following steps:
Judge the size of character in image range, and the definition of the character on border, judging area and the character of regional center;
By the region of the same size of character in image range, and the region that the character of zone boundary is consistent with the definition of the character of regional center, be divided into a single region.
Focusing module 520, for obtaining several text images of the text being in region, determines the lens focusing position in region;
Specifically, Focusing module 520, for obtaining several text images of the text being in region, is determined the lens focusing position in region, is comprised the following steps:
Obtain several text images being in single region;
Calculate the quality of each width text image based on text detection information, use optimum first quality position of searching algorithm search;
Optimum first quality position is defined as the lens focusing position in single region.
Further, Focusing module 520 also for determining the lens focusing position in single region, comprises the following steps:
Determine the adjacent area of optimum first quality position;
With the point on adjacent area for focus, calculate text quality based on identification and semantic information, utilize searching algorithm to search for optimum second quality position;
Optimum second quality position is defined as the lens focusing position in single region.
Locating module 530, for the lens focusing position according to region, determines the lens focusing position of the text in image range.Specifically, locating module 530, for determining the lens focusing position of the text in image range, comprising:
The lens focusing position of the text in image range is lens focusing position, one or more single region.
Further, when locating module 530 is multiple single lens focusing position, region for the lens focusing position of the text in the image range of focusing, optimum focal point plane is simulated to multiple focus, by the position of the camera lens of focus when optimum focal point plane, as the lens focusing position of the text in image range.
In the above embodiment of the present invention, by the text in detection module 510 detected image scope, analyze and determine the region at text place; Focusing module 520 obtains several text images being in the text in region, determines the lens focusing position in region; Locating module 530, according to the lens focusing position in region, determines the lens focusing position of the text in image range; Thus the effective focusing achieved text image, and then improve from image, obtain content of text accuracy rate and speed.
Further, text based focal modes, can make the text filed shooting effect obtaining optimum paid close attention to, thus effectively can strengthen the identification of text, or increase the accuracy of follow-up text identification in shooting process.In addition, text based focal modes, can improve speed and the convenience of shooting text, and can solve the auto-focusing problem of the shooting of single text and the shooting of many texts, can effectively reduce man-machine interaction number of times, improve the convenience that user uses.
The embodiment of the present invention provides a kind of capture apparatus on the other hand, comprises the device of auto-focusing as above, and focus to text image according to above-mentioned disclosed device, take text image thereafter, detail does not repeat them here.
Those skilled in the art of the present technique are appreciated that the one or more equipment that the present invention includes and relate to for performing in operation described in the application.These equipment for required object and specialized designs and manufacture, or also can comprise the known device in all-purpose computer.These equipment have storage computer program within it, and these computer programs optionally activate or reconstruct.Such computer program can be stored in equipment (such as, computer) in computer-readable recording medium or be stored in and be suitable for store electrons instruction and be coupled in the medium of any type of bus respectively, described computer-readable medium includes but not limited to that the dish of any type (comprises floppy disk, hard disk, CD, CD-ROM, and magneto optical disk), ROM(Read-Only Memory, read-only memory), RAM(Random Access Memory, memory immediately), EPROM(Erasable Programmable Read-Only Memory, Erarable Programmable Read only Memory), EEPROM(Electrically Erasable ProgrammableRead-Only Memory, EEPROM (Electrically Erasable Programmable Read Only Memo)), flash memory, magnetic card or light card.Namely, computer-readable recording medium comprises and being stored or any medium of transmission information with the form that can read by equipment (such as, computer).
Those skilled in the art of the present technique are appreciated that the combination that can realize the frame in each frame in these structure charts and/or block diagram and/or flow graph and these structure charts and/or block diagram and/or flow graph with computer program instructions.Those skilled in the art of the present technique are appreciated that, the processor that these computer program instructions can be supplied to all-purpose computer, special purpose computer or other programmable data processing methods realizes, thus is performed the scheme of specifying in the frame of structure chart disclosed by the invention and/or block diagram and/or flow graph or multiple frame by the processor of computer or other programmable data processing methods.
Those skilled in the art of the present technique are appreciated that various operations, method, the step in flow process, measure, the scheme discussed in the present invention can be replaced, changes, combines or delete.Further, there is various operations, method, other steps in flow process, measure, the scheme discussed in the present invention also can be replaced, change, reset, decompose, combine or delete.Further, of the prior art have also can be replaced with the step in operation various disclosed in the present invention, method, flow process, measure, scheme, changed, reset, decomposed, combined or deleted.
The above is only some embodiments of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (14)
1. a method for auto-focusing, is characterized in that, comprises the steps:
Text in detected image scope, analyzes and determines the region at text place;
Obtain several text images being in the text in described region, determine the lens focusing position in described region;
According to the lens focusing position in described region, determine the lens focusing position of the text in described image range.
2. the method for auto-focusing according to claim 1, is characterized in that, analyzes and determines the region at text place, comprising the following steps:
Judge the size of character in image range, and the definition of the character on border, judging area and the character of regional center;
By the region of the same size of character in image range, and the region that the character of zone boundary is consistent with the definition of the character of regional center, be divided into a single region.
3. the method for auto-focusing according to claim 2, is characterized in that, obtains several text images being in the text in described region, determines the lens focusing position in described region, comprise the following steps:
Obtain several text images being in described single region;
Calculate the quality of each width text image based on text detection information, use optimum first quality position of searching algorithm search;
Described optimum first quality position is defined as the lens focusing position in described single region.
4. the method for auto-focusing according to claim 3, is characterized in that, also comprises:
Determine the adjacent area of described optimum first quality position;
With the point on described adjacent area for focus, calculate text quality based on identification and semantic information, utilize searching algorithm to search for optimum second quality position;
Described optimum second quality position is defined as the lens focusing position in described single region.
5. the method for auto-focusing according to claim 4, is characterized in that, determines the lens focusing position of the text in described image range, comprising:
The lens focusing position of the text in described image range is lens focusing position, one or more described single region.
6. the method for auto-focusing according to claim 5, it is characterized in that, when the lens focusing position of the text in described image range is multiple described single lens focusing position, region, optimum focal point plane is simulated to multiple focus, by the position of the camera lens of focus when described optimum focal point plane, as the lens focusing position of the text in described image range.
7. to the method that text image is taken, it is characterized in that, according to the method as described in one of as any in claim 1 to 6 text image focused and take.
8. a device for auto-focusing, is characterized in that, comprises detection module, Focusing module and locating module,
Described detection module, for the text in detected image scope, analyzes and determines the region at text place;
Described Focusing module, for obtaining several text images of the text being in described region, determines the lens focusing position in described region;
Described locating module, for the lens focusing position according to described region, determines the lens focusing position of the text in described image range.
9. the device of auto-focusing according to claim 8, is characterized in that, described detection module, for analyzing and determining the region at text place, comprises the following steps:
Judge the size of character in image range, and the definition of the character on border, judging area and the character of regional center;
By the region of the same size of character in image range, and the region that the character of zone boundary is consistent with the definition of the character of regional center, be divided into a single region.
10. the device of auto-focusing according to claim 9, is characterized in that, described Focusing module, for obtaining several text images of the text being in described region, is determined the lens focusing position in described region, comprised the following steps:
Obtain several text images being in described single region;
Calculate the quality of each width text image based on text detection information, use optimum first quality position of searching algorithm search;
Described optimum first quality position is defined as the lens focusing position in described single region.
The device of 11. auto-focusing according to claim 10, is characterized in that, described Focusing module also for determining the lens focusing position in single region, comprises the following steps:
Determine the adjacent area of described optimum first quality position;
With the point on described adjacent area for focus, calculate text quality based on identification and semantic information, utilize searching algorithm to search for optimum second quality position;
Described optimum second quality position is defined as the lens focusing position in described single region.
The device of 12. auto-focusing according to claim 11, is characterized in that, described locating module, for determining the lens focusing position of the text in described image range, comprising:
The lens focusing position of the text in described image range is lens focusing position, one or more described single region.
The device of 13. auto-focusing according to claim 12, it is characterized in that, when described locating module is multiple described single lens focusing position, region for the lens focusing position of the text in the described image range of focusing, optimum focal point plane is simulated to multiple focus, by the position of the camera lens of focus when described optimum focal point plane, as the lens focusing position of the text in described image range.
14. 1 kinds of capture apparatus, is characterized in that, comprise one of as any in claim 8 to 13 as described in device, according to described device text image focused and take.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410006852.1A CN104767926A (en) | 2014-01-07 | 2014-01-07 | Automatic focusing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410006852.1A CN104767926A (en) | 2014-01-07 | 2014-01-07 | Automatic focusing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104767926A true CN104767926A (en) | 2015-07-08 |
Family
ID=53649504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410006852.1A Pending CN104767926A (en) | 2014-01-07 | 2014-01-07 | Automatic focusing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104767926A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678242A (en) * | 2015-12-30 | 2016-06-15 | 小米科技有限责任公司 | Focusing method and apparatus in the mode of holding certificate in hands |
| CN106979948A (en) * | 2017-02-21 | 2017-07-25 | 上海大学 | Handheld portable Density detecting system |
| WO2017167116A1 (en) * | 2016-03-28 | 2017-10-05 | 华为技术有限公司 | Automatic-focus method and automatic-focus device |
| CN109901355A (en) * | 2019-04-19 | 2019-06-18 | 深圳市当智科技有限公司 | Diversification projector Atomatic focusing method based on contrast plus histogram |
| CN116074617A (en) * | 2023-04-03 | 2023-05-05 | 常州微亿智造科技有限公司 | Integrated array camera and imaging control method thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408709A (en) * | 2007-10-10 | 2009-04-15 | 鸿富锦精密工业（深圳）有限公司 | Image viewfinding device and automatic focusing method thereof |
| CN101609505A (en) * | 2008-06-19 | 2009-12-23 | 三星电子株式会社 | The method and apparatus of identification character |
| CN101753846A (en) * | 2008-12-05 | 2010-06-23 | 三星电子株式会社 | Use camera to adjust the apparatus and method of character boundary automatically |
| CN102647449A (en) * | 2012-03-20 | 2012-08-22 | 西安联客信息技术有限公司 | Intelligent shooting method and intelligent shooting device based on cloud service and mobile terminal |
| CN102647450A (en) * | 2012-03-20 | 2012-08-22 | 西安联客信息技术有限公司 | Intelligent shooting method and system based on cloud service |
| US20130050668A1 (en) * | 2011-08-31 | 2013-02-28 | Asml Netherlands B.V. | Method of Determining Focus Corrections, Lithographic Processing Cell and Device Manufacturing Method |
-
2014
- 2014-01-07 CN CN201410006852.1A patent/CN104767926A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408709A (en) * | 2007-10-10 | 2009-04-15 | 鸿富锦精密工业（深圳）有限公司 | Image viewfinding device and automatic focusing method thereof |
| CN101609505A (en) * | 2008-06-19 | 2009-12-23 | 三星电子株式会社 | The method and apparatus of identification character |
| CN101753846A (en) * | 2008-12-05 | 2010-06-23 | 三星电子株式会社 | Use camera to adjust the apparatus and method of character boundary automatically |
| US20130050668A1 (en) * | 2011-08-31 | 2013-02-28 | Asml Netherlands B.V. | Method of Determining Focus Corrections, Lithographic Processing Cell and Device Manufacturing Method |
| CN102647449A (en) * | 2012-03-20 | 2012-08-22 | 西安联客信息技术有限公司 | Intelligent shooting method and intelligent shooting device based on cloud service and mobile terminal |
| CN102647450A (en) * | 2012-03-20 | 2012-08-22 | 西安联客信息技术有限公司 | Intelligent shooting method and system based on cloud service |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678242A (en) * | 2015-12-30 | 2016-06-15 | 小米科技有限责任公司 | Focusing method and apparatus in the mode of holding certificate in hands |
| CN105678242B (en) * | 2015-12-30 | 2019-05-07 | 小米科技有限责任公司 | Focusing method and device under hand-held certificate mode |
| WO2017167116A1 (en) * | 2016-03-28 | 2017-10-05 | 华为技术有限公司 | Automatic-focus method and automatic-focus device |
| CN106979948A (en) * | 2017-02-21 | 2017-07-25 | 上海大学 | Handheld portable Density detecting system |
| CN106979948B (en) * | 2017-02-21 | 2020-05-19 | 上海大学 | Handheld portable fabric density detection system |
| CN109901355A (en) * | 2019-04-19 | 2019-06-18 | 深圳市当智科技有限公司 | Diversification projector Atomatic focusing method based on contrast plus histogram |
| CN109901355B (en) * | 2019-04-19 | 2020-11-10 | 深圳市当智科技有限公司 | Automatic focusing method of diversified projector based on contrast and histogram |
| CN116074617A (en) * | 2023-04-03 | 2023-05-05 | 常州微亿智造科技有限公司 | Integrated array camera and imaging control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9225855B2 (en) | Imaging apparatus, imaging system, and control method for increasing accuracy when determining an imaging scene based on input image data and information stored in an external information processing apparatus | |
| RU2669063C2 (en) | Method and device for image acquisition | |
| CN108038837B (en) | Method and system for detecting target in video | |
| CN104767926A (en) | Automatic focusing method and device | |
| US20160148068A1 (en) | Image processing apparatus and method, and electronic device | |
| CN110569835B (en) | Image recognition method and device and electronic equipment | |
| CN105578027A (en) | Photographing method and device | |
| US11818428B2 (en) | Identifying viewing characteristics of an audience of a content channel | |
| CN105809174A (en) | Method and device for identifying image | |
| KR101397873B1 (en) | Apparatus and method for providing contents matching related information | |
| CN105590113A (en) | Information-acquiring method based on law enforcement recorder | |
| CN111563398A (en) | Method and device for determining information of target object | |
| US11348254B2 (en) | Visual search method, computer device, and storage medium | |
| CN101908057A (en) | Information processing apparatus and information processing method | |
| KR101954717B1 (en) | Apparatus for Processing Image by High Speed Analysis and Driving Method Thereof | |
| GB2537886A (en) | An image acquisition technique | |
| CN102737383A (en) | Camera movement analyzing method and device in video | |
| CN111797266B (en) | Image processing method and apparatus, storage medium, and electronic device | |
| KR101831663B1 (en) | Display mehtod of ecotourism contents in smart device | |
| CN105451175A (en) | Method of recording photograph positioning information and apparatus thereof | |
| US10489460B2 (en) | Method and apparatus for providing local search suggestion | |
| CN113014876A (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| US20150149458A1 (en) | Method for generating blocks for video searching and method for processing queries based on blocks generated thereby | |
| CN113516145B (en) | Image processing and vehicle information providing method, apparatus and storage medium | |
| CN114625900A (en) | Content management apparatus, content management system, and control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20220429 |
|
| AD01 | Patent right deemed abandoned |