CN103763453A - Image and text collection and recognition device - Google Patents
Image and text collection and recognition device Download PDFInfo
- Publication number
- CN103763453A CN103763453A CN201410027696.7A CN201410027696A CN103763453A CN 103763453 A CN103763453 A CN 103763453A CN 201410027696 A CN201410027696 A CN 201410027696A CN 103763453 A CN103763453 A CN 103763453A
- Authority
- CN
- China
- Prior art keywords
- information
- image information
- camera
- multipoint
- image
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/04—Scanning arrangements, i.e. arrangements for the displacement of active reading or reproducing elements relative to the original or reproducing medium, or vice versa
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10821—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum further details of bar or optical code scanning devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an image and text collection and recognition device which comprises a multipoint image information collection unit and an image information recognition unit. The multipoint image information collection unit transmits collected image information to the image information recognition unit, the image information recognition unit recognizes image and text content information according to the image information, and the multipoint image information collection unit collects the image information by using a photograph mode. The multipoint image information collection unit at least comprises a movable type camera, or the multipoint image information collection unit comprises multiple cameras, or the multipoint image information collection unit comprises one fixed type camera, and the fixed type camera comprises multiple lenses. By means of the implementation of the image and text collection and recognition device, in an image information collection process, image information in different angles or different positions in areas where image information needs to be collected can be obtained flexibly, and therefore corresponding image and text content information can be recognized accurately in subsequent image and text recognition processing processes.
Description
Technical field
The present invention relates to IMAQ identifying processing technical field, relate in particular to a kind of graphics context collection recognition device.
Background technology
Development along with image processing techniques, the application of corresponding IMAQ recognition technology is also increasingly extensive, yet, in current IMAQ recognition technology, be generally and adopt single common camera to be fixedly installed in the acquisition operations of carrying out image in image-region to be collected, the processing mode of this collection image makes the image information collecting often cannot react truely and accurately the actual conditions in collected region, cannot obtain the image really and accurately in defendant's pickup area, and then cause cannot accurately identifying corresponding graph-text content information in follow-up identification processing procedure.
Particularly, if carry out IMAQ with common camera, in order to obtain the covering to required acquisition target, need to arrange more at a distance corresponding camera.If attempt, with wide-angle lens or flake mirror, in short distance, the covering of required acquisition target will be produced to larger distortion.And its single focal length of single fixing camera causes captured object only the clearest in that suitable sub-fraction of focal length, other parts are due to not at best focus position place, clear not.And curved surface (such as the macrobending at the book middle part to opening) is difficult to realize distortionless shooting.And, the shooting angle of common camera also can only directly over could effectively take whole subjects, if from the side or inclined-plane take; easily make part not at pinpointed focus and unintelligible, and due to projection principle, object imaging apart from camera far-end is little, and resolution can decline a lot.Therefore, if it is very high to adopt common single fixing camera (being common camera) resolution ratio of camera head to be required comprehensive covering of required acquisition target, and cannot reach desirable shooting effect.
Moreover current Book Publishing amount is very large.But also have at present a part of crowd, as children, blind person, the elderly etc., its inconvenience is directly read books, needs aid reading audible device to read for this part crowd, and there is no at present the aid reading audible device for general book.
Summary of the invention
The object of this invention is to provide a kind of graphics context collection recognition device, thereby can collect accurately and easily the image information of expectation, to improve the accuracy of identification processing procedure.
The object of the invention is to be achieved through the following technical solutions:
A graphics context collection recognition device, comprising:
Multipoint images information acquisition unit and image information recognition unit, described multipoint images information acquisition unit passes to described image information recognition unit by the image information of collection, described image information recognition unit identifies graph-text content information according to described image information, and described multipoint images information acquisition unit adopts shooting style to obtain described image information, wherein, institute's multipoint images information acquisition unit comprises at least one movable camera, the photo angle of described movable camera and/or position are adjustable, and the control information of the control mode of described movable camera based on predetermined or reception is controlled its activity and taken subject is carried out to multi-angle and/or multipoint multipoint images, or, described multipoint images information acquisition unit comprises a plurality of cameras, i.e. two or three or four or more camera, described a plurality of camera has been used for multi-angle and/or multipoint multipoint images is taken, and each camera is fixed camera or movable camera, the photo angle of described movable camera and/or position are adjustable, described movable camera is for the control mode based on predetermined or the control information based on receiving or manually control its activity subject is carried out to multi-angle and/or the shooting of multipoint multipoint images, or, described multipoint images information acquisition unit comprises a fixed camera, described fixed camera comprises a plurality of camera lenses, and each camera lens that the described a plurality of camera lenses of the control information of the control mode based on predetermined or reception control comprise gathers described graph-text content information.
Described movable camera comprises rotatable camera head and/or packaged type camera, and described movable camera is rotatable removable or removable rotatable; Or described movable camera comprises one or more movable camera lenses, the photo angle of described movable camera lens and/or position are adjustable; If it is a plurality of that described movable camera comprises, each camera that a plurality of movable cameras comprise is for gathering the graph-text content information of all or part of scene; The position that described movable camera is arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
Described fixed camera comprises one or more camera lenses, if and described fixed camera comprises a plurality of camera lenses, the control information of the control mode based on predetermined or reception is controlled each camera lens and is gathered described graph-text content information, and each camera that described a plurality of cameras comprise is for gathering the graph-text content information of all or part of scene; The position that described camera is arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
Described graph-text content information comprises: the picture of printed matter or word content information, and/or, printed matter is read to the indication information of operation.
The described indication information that printed matter is read to operation comprises: the reading carried out on printed matter by hand or hand-held object indication operation information.
Described multipoint images information acquisition unit also comprises reading position information acquisition module, for the character image information of reading operating position by camera collection user, and described image information recognition unit is identified the word content that character image packets of information that described user reads operating position contains.
The picture of described printed matter or word content packets of information are containing the Bibliographical Information of books, the collection of described multipoint images information acquisition unit include books Bibliographical Information image information and pass to described image information recognition unit, the described image information that includes the Bibliographical Information of books comprises the image information of figure book envelope, and described image information recognition unit is determined Bibliographical Information by the word of identifying in the image information of described figure book envelope, or, by identifying the image information of described figure book envelope, determine Bibliographical Information, or, by the sign of identifying in the image information of described figure book envelope, determine Bibliographical Information, described sign is books self or additional,
And/or
The picture of described printed matter or word content packets of information are containing the page number information of books, the collection of described multipoint images information acquisition unit include books page number information image information and pass to described image information recognition unit, the image information that described page number information acquisition module gathers page in books by described camera module is as the information that comprises described page number information, by identifying the image information of page in described books, determine the page number of current reading, or, the page number of determining current reading by identifying in described books word in the image information of page or the digital page number.
This device also comprises:
Audio unit, described multipoint images information acquisition unit passes to described image information recognition unit by current read page in the books of collection or the current reading position of printed matter or reading operation image information indicating positions or that comprise Bibliographical Information or that comprise page number information, described image information recognition unit identifies this current read page or the current reading position of printed matter or reads audio-frequency information corresponding to operation word content information indication or Bibliographical Information or page number information and notify described audio unit according to described current read page or the current reading position of printed matter or reading operation image information indicating positions or that comprise Bibliographical Information or that comprise page number information, described audio unit is exported the audio-frequency information of described correspondence with audio form,
And/or,
Audio frequency input unit, for obtaining audio-frequency information;
And/or,
Memory cell, comprises audio information and/or preserves gathering image and/or the Word message obtaining in identifying and/or preserving the outside content information obtaining;
And/or,
Display unit, shows and comprises the content information of setting and/or gather image and Word message and/or the outside content information obtaining obtaining in identifying;
And/or,
Communication unit, for and compunication.
This device comprises interactive processing module, for the interactive operation control information of obtaining user, and carry out predetermined interactive operation according to described interactive operation control information, and described interactive operation control information comprises at least one in limb action, the action that operates object, voice messaging, screen input or operation push-button.
As seen from the above technical solution provided by the invention, a kind of graphics context collection recognition device that the embodiment of the present invention provides is owing to having adopted unique camera arrangement, make can obtain neatly the image information (being the image information of different angles and/or diverse location) that need to gather (being subject) multiple spot in image information region in image information collecting process, with respect to common camera, can complete the required image collection of taking pictures practicality is closely distortionless, from books, do not affect the angle of reading or position such as oblique upper also can IMAQ identification, do not affect user's reading, corresponding movable camera or a plurality of camera have a plurality of focal lengths, so just can make institute's acquisition target each several part all in pinpointed focus, all clear to guarantee the image of each several part, for curved surface (such as the macrobending face at books middle part), can there be suitable shooting angle and position, therefore can effectively to it, take identification, and, corresponding multipoint images information acquisition unit can be so that require lower to resolution ratio of camera head, with the camera of same resolution, captured thing is taken to the resolution (being more conducive to identification) that can reach higher in other words, thereby can be so that the image information collecting can be reacted the actual conditions in collected region truely and accurately, and then make can accurately identify corresponding graph-text content information in follow-up picture and text identification processing procedure.Thereby make this device also can be, but not limited to as a kind of picture and text input device etc., picture and text typing is such as full text typing, or divides picture and text to carry out typing etc. along with printed matter being read to the selection portion of the indication of operation.On the other hand, in this graphics context collection recognition device, owing to can accurately carrying out the identification of graph-text content information, thereby can carry out picture and text identifying processing for general book, and realize for the aid reading sounding of general book and processing in conjunction with corresponding vocal function, thereby for providing a kind of, people can assist to general book the aid reading audible device of sounding.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing of required use during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain other accompanying drawings according to these accompanying drawings.
The structural representation one of the graphics context collection recognition device that Fig. 1 provides for the embodiment of the present invention;
The structural representation two of the graphics context collection recognition device that Fig. 2 provides for the embodiment of the present invention;
The structural representation one of the graphics context collection recognition device that comprises a plurality of cameras that Fig. 3 provides for the embodiment of the present invention;
The structural representation two of the graphics context collection recognition device that comprises a plurality of cameras that Fig. 4 provides for the embodiment of the present invention;
The structural representation three of the graphics context collection recognition device that comprises a plurality of cameras that Fig. 5 provides for the embodiment of the present invention;
The structural representation of the camera that is arranged at edge top that Fig. 6 provides for the embodiment of the present invention;
The structural representation one of the camera that is arranged at oblique upper that Fig. 7 provides for the embodiment of the present invention;
The structural representation two of the camera that is arranged at oblique upper that Fig. 8 provides for the embodiment of the present invention;
Fig. 9 for the embodiment of the present invention provide be arranged at directly over the structural representation of camera;
A plurality of cameras that Figure 10 provides for the embodiment of the present invention are taken the schematic diagram one of books top-surface camber;
A plurality of cameras that Figure 11 provides for the embodiment of the present invention are taken the schematic diagram two of books top-surface camber;
A plurality of cameras that Figure 12 provides for the embodiment of the present invention are taken the schematic diagram three of books top-surface camber;
The front schematic diagram of taking books top-surface camber of rotatable camera head rotation that Figure 13 provides for the embodiment of the present invention;
The rear schematic diagram of taking books top-surface camber of rotatable camera head rotation that Figure 14 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Based on embodiments of the invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to protection scope of the present invention.
Below in conjunction with accompanying drawing, the embodiment of the present invention is described in further detail.
The embodiment of the present invention provides a kind of graphics context collection recognition device, its specific implementation structure as shown in Figure 1, can comprise: multipoint images information acquisition unit and image information recognition unit, described multipoint images information acquisition unit passes to described image information recognition unit by the image information of collection, described image information recognition unit identifies graph-text content information according to described image information, and described multipoint images information acquisition unit adopts shooting style to obtain described image information, be that the camera that described multipoint images information acquisition unit comprises by it is taken the described image information of acquisition.
Further, for realizing for multi-angle and/or multipoint multipoint images of subject, take, corresponding multipoint images information acquisition unit can adopt following arbitrary structure to realize:
(1) described multipoint images information acquisition unit can comprise at least one movable camera, and the control information of the control mode of described movable camera based on predetermined or reception is controlled its activity and taken subject is carried out to multi-angle and/or multipoint multipoint images.For example, according to feedback, automatically control (as done automatic adjustment according to the feedback after photographic images identification), such as when pointing, the place of showing has gone beyond the scope or segment word has gone beyond the scope or the page number has gone beyond the scope, automatically adjust angle and/or the position of movable camera, like this product in the course of the work without or need less manual intervention, or, as described in controlling according to the control information of user input (predetermined control information that the specific limb action of carrying out as user or user input by operation push-button etc.), camera rotates or mobile, or, also can automatically control described camera rotation or mobile according to the predefined time interval, to carry out multi-angle and/or the shooting of multipoint multiple spot for subject.
Particularly, described movable camera comprises rotatable camera head and/or packaged type camera, and described movable camera is rotatable removable or removable rotatable; Or described movable camera comprises one or more movable camera lenses; If it is a plurality of that described movable camera comprises, each camera that a plurality of movable cameras comprise is for gathering the graph-text content information of all or part of scene; The position that described movable camera can be arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
(2) described multipoint images information acquisition unit comprises a plurality of cameras, i.e. two or three or four or more camera, described a plurality of camera has been used for multi-angle and/or multipoint multipoint images is taken, and each camera is fixed camera or movable camera, described movable camera is for the control mode based on predetermined or the control information based on receiving or manually control its activity subject is carried out to multi-angle and/or the shooting of multipoint multipoint images.For example, according to feedback, automatically control (as done automatic adjustment according to the feedback after photographic images identification), such as when pointing, the place of showing has gone beyond the scope or segment word has gone beyond the scope or the page number has gone beyond the scope, automatically adjust angle and/or the position of movable camera, like this product in the course of the work without or need less manual intervention, or, as described in controlling according to the control information of user input (predetermined control information that special limbs move surely or user inputs by operation push-button of carrying out as user etc.), camera rotates or mobile, or, also can automatically control described camera rotation or mobile according to the predefined time interval, to carry out multi-angle and/or the shooting of multipoint multiple spot for subject.
Particularly, described fixed camera comprises one or more camera lenses, if and described fixed camera comprises a plurality of camera lenses, the control information of the control mode based on predetermined or reception is controlled each camera lens and is gathered described graph-text content information, and described predetermined control mode comprises whole cameras of controlling in a plurality of cameras or part camera carries out multi-angle and/or multipoint multipoint images is taken;
Each camera that described a plurality of camera comprises is for gathering the graph-text content information of all or part of scene;
In this scheme (2), the position that described camera can be arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
That is to say, in this graphics context collection recognition device, corresponding multipoint images information acquisition unit can comprise a plurality of cameras, as shown in Fig. 3, Fig. 4 and Fig. 5, corresponding a plurality of camera can be fix or mobilizable mode be arranged at the edge top of subject region and/or oblique upper and/or directly over, for example, can be arranged at the edge top of books and/or oblique upper and/or directly over, the position arranging when reading as reader need to not affect reader's read books, specifically can be with reference to shown in Fig. 6, Fig. 7, Fig. 8 and Fig. 9.Simultaneously, owing to having adopted a plurality of cameras, greatly having reduced the needed shooting to each camera covers, increased whole covering, thereby guarantee to cover identifying needed shooting, a plurality of cameras can be taken the identification work of carrying out separately separately, also can shooting results is comprehensive after for identification.
(3) described multipoint images information acquisition unit comprises a fixed camera, described fixed camera comprises a plurality of camera lenses, and each camera lens that the control mode based on predetermined or the described a plurality of camera lenses of the control information of reception control comprise gathers described graph-text content information, thereby can realize subject is carried out to multi-angle and/or multipoint multipoint images is taken by described a plurality of camera lenses, and described predetermined control mode comprises whole camera lenses of controlling in a plurality of camera lenses or partial lens carries out multi-angle and/or multipoint multipoint images is taken.For example, according to feedback, automatically control (as done automatic adjustment according to the feedback after photographic images identification), such as when pointing, the place of showing has gone beyond the scope or segment word has gone beyond the scope or the page number has gone beyond the scope, automatically adjust angle and/or the position of movable camera, like this product in the course of the work without or need less manual intervention, or, as described in controlling according to the control information of user input (predetermined control information that limbs move surely or user inputs by operation push-button of carrying out as user etc.), each camera lens is taken the multi-angle of subject and/or multiposition, or, also can take according to predefined each camera lens collection multi-angle of subject and/or described each camera lens of the automatic control of the mode of multipoint image information (such as, can set each camera lens and obtain corresponding image information for taking successively subject, also can set each camera lens takes subject simultaneously and obtains corresponding image information, or, also can obtain corresponding image information by setting section lens shooting subject, etc.).
Particularly, in this scheme (3), the position that described fixed camera can be arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over, specifically can be with reference to shown in Fig. 6, Fig. 7, Fig. 8 and Fig. 9.
Fixing camera has the fixing visual field conventionally, but a plurality of cameras can form comprehensive covering, and movable camera has the fixing visual field when a certain angle position, but it changes the visual field by activity, therefore also can form comprehensive covering, in concrete enforcement, if fixing camera has become flexible, can not be considered as movable camera, equally, even if camera can be movable, if but in its course of work, be not to obtain required special result by activity, such as comprehensively covering etc., in fact still belong to fixing camera scheme.Such as, if can adjust in advance suitable angle position etc. by movable camera, but do not need to carry out activity in actual use, or movablely to special effect, such as comprehensively covering to wait, act on very littlely, in fact still belong to fixing camera scheme.
In the graphics context collection recognition device that the embodiment of the present invention provides, described graph-text content information specifically can be, but not limited to comprise: the picture of printed matter or word content information, and/or, the pictorial information of space still life, and/or, limb action information, and/or, printed matter is read to the indication information of operation, and/or, the action message of operation object; Be described graph-text content information can be for pictorial information, the limb action information of the picture of printed matter or word content information, space still life, printed matter is read at least one in the indication information of operation and the action message of operation object.
That is to say, corresponding image information recognition unit can identify picture or the Word message in printed matter according to the image information collecting, or, also can identify the picture (as determined the content informations such as the corresponding picture of corresponding space still life or explanatory note according to the image information of the space still life that collects) of space still life, or, also can identify the limb action information such as gesture motion (as identified the corresponding execution instruction of predetermined limb action implication etc.) that user carries out, or, also can identify the action message that user operates object, or, also the reading operation indication in the time of can identifying user printed matter is read, etc..Further, printed matter is read to the indication information of operation and can be realized by the action message of limb action information or operation object, the action of specific limb action or operation object can be read to the indication information of operation as certain; That is to say, the described indication information that printed matter is read to operation can comprise: the reading carried out on printed matter by hand or hand-held object indication operation information, the indication that somewhere reads as determine given directions or determine the indication etc. that needs the indication of reading content or determine whether needs reading, such as hand is given directions, clicks, is double-clicked on printed matter, slip, page turning etc.
A kind of graphics context collection recognition device that the embodiment of the present invention provides is owing to having adopted unique camera arrangement, make can obtain neatly the multipoint images information that need to gather subject in image information collecting process, gather be taken corresponding different angles and/or the image information of diverse location, thereby can be so that the image information collecting can be reacted the actual conditions of subject truely and accurately, and then make can accurately identify corresponding graph-text content information in follow-up picture and text identification processing procedure, as identified exactly word or the pictorial information in printed matter, or, identify the implication of user's limb action, or, identify the implication that user operates the action of object execution, or, identify the implication that user operates the reading of the printed matters such as books by limb action or operation object, or, identify the word of user indication or picture etc.
In the graphics context collection recognition device providing in the embodiment of the present invention, for ease of user, based on this device, realize the sound reading for printed matter, as shown in Figure 2, in this device, can also comprise audio unit, described multipoint images information acquisition unit passes to described image information recognition unit by the current reading position of current read page or printed matter in the books of collection or reading operation indicating positions or the image information that comprises Bibliographical Information or comprise page number information, described image information recognition unit identifies according to described current read page or the current reading position of printed matter or reading operation indicating positions or the image information that comprises Bibliographical Information or comprise page number information and identifies audio-frequency information corresponding to the word content information of this current read page or the current reading position of printed matter or reading operation indicating positions or Bibliographical Information or page number information and notify described audio unit, described audio unit is exported the audio-frequency information of described correspondence with audio form, thereby can realize sound the reading aloud for printed matter Chinese word content, be convenient to the inconvenient crowd who intuitively books is read and obtain the content information in general book.
By described audio unit, printed matter is being carried out in sound reading operating process, described multipoint images information acquisition unit also comprises reading position information acquisition module, for read the character image information of operating position (being the current reading position of printed matter of user's appointment) by camera collection user, and described image information recognition unit is identified the word content that character image packets of information that described user reads operating position contains, and the audio-frequency information that audio-frequency information corresponding to the described word content that identification is determined or the conversion of described word content obtain is notified described audio unit.Wherein, the audio-frequency information that described word content is corresponding can be the audio-frequency information of reading aloud of this segment word content, can be also other audio-frequency informations corresponding to this article word content, as to audio-frequency informations such as explaining of this word content.
Corresponding word identification has progressed into the practical stage at present, corresponding identification processing procedure can comprise: first to the image preliminary treatment of taking pictures, this preliminary treatment mainly comprises the processing such as binaryzation, noise remove, inclination calibration, then carry out character features extraction, comprise after word image graph thinning, obtain the stroke end points of word, quantity and the position in crosspoint, or take stroke section as feature, coordinate comparison method to compare, thus identification word.Because character recognition technology has been prior art, therefore be no longer described in detail at this.
In this graphics context collection recognition device, owing to can accurately carrying out the identification of graph-text content information, thereby can carry out picture and text identifying processing for general book, and realize for the aid reading sounding of general book and processing in conjunction with corresponding vocal function, thereby for providing a kind of, people can assist to general book the aid reading audible device of sounding, this just makes children, blind person, the crowd that the inconveniences such as the elderly are directly read books can carry out aid reading by this graphics context collection recognition device, be very easy to the reading operation of this part crowd to general book.And the accuracy of identifying can also guarantee that books reading process can carry out swimmingly, has further guaranteed that reading user has preferably reading experience.
In the graphics context collection recognition device providing in the embodiment of the present invention, for ease of preserving the graph-text content information identifying, in this device, can also comprise memory cell, for preserving the described graph-text content information that described image information recognition unit identifies, to facilitate follow-up calling described graph-text content information.
In the graphics context collection recognition device providing in the embodiment of the present invention, the image information of the Bibliographical Information that includes books that described multipoint images information acquisition unit can also gather also passes to described image information recognition unit, described image information recognition unit according to described in include the Bibliographical Information of books image information identify book name.Further, can also export described book name by the mode of audio frequency or demonstration, for example, can read aloud out book name by described audio unit, or demonstrate book name by display screen.
Further, described multipoint images information acquisition unit can be by described camera collection figure book envelope image information as the image information of the Bibliographical Information that comprises described books, described image information recognition unit can (comprise front cover by the described figure book envelope of identification, back cover etc.) book name determined in the word in image information, or, also can determine book name by identifying the image information of described figure book envelope, or, can also determine book name by the label of identifying in the image information of described figure book envelope, corresponding label comprises special label or coding, or also can comprise ISBN bar code (International Standard Book Number, International Standard Book Number) etc. the label or the coding that have existed at present.
Because front cover and the back cover image of every book are all different, thus can contrast by the image information photographing identification, thereby or extract Characteristic Contrast and identify and be specially which books, thereby determine corresponding book name.And, for ease of identification, the label of being convenient to accordingly identification can also be set in books, make can determine according to this label the concrete book name of current books, corresponding label can be for being printed on the label on books, also can be for being pasted on the label on books, and can be the content informations such as picture or coding or word on corresponding label.Because concrete image recognition technology has been prior art, therefore be no longer described in detail at this.
In the graphics context collection recognition device providing in the embodiment of the present invention, the image information that includes page number information that described multipoint images information acquisition unit can also gather also passes to described image information recognition unit, described image information recognition unit according to described in include page number information image information identify the page number.Further, can also export described book name by the mode of audio frequency or demonstration, for example, can be by the bright page number of reading of described audio unit, or demonstrate the page number by display screen.
Described page number information acquisition module is determined the page number of current reading by identifying in described books the image information of page, or, the page number of determining current reading by identifying word in the image information of page in described books or the digital page number.
This graphics context collection recognition device can also comprise display unit, be used for the content information of display setting and/or gather image and Word message and/or the outside content information obtaining that identifying obtains, for example, can show the information such as the page number of current books reading or book name, or, show needle is to the information of explaining of books (as introduction of authors etc.), or, the operational order that shows the user that described image information recognition unit identifies, or, play the video information for books are made an explanation, etc.
Particularly, this graphics context collection recognition device can also comprise following any one or multinomial unit:
Audio frequency input unit, for obtaining audio-frequency information.Audio-frequency information after obtaining accordingly can be preserved by memory cell.
Memory cell, comprise audio information and/or preserve and gather image and/or the Word message obtaining in identifying and/or preserve the outside content information obtaining, the voice messaging of preserving can be play by audio unit when needed, for example, by the cooperation of audio frequency input unit and this memory cell and audio unit, can proofread and correct the pronunciation of user in Course of Language Learning whether accurate etc.
Communication unit, for and computer between communicate.
Moreover, for strengthening the interactive processing between user and this graphics context collection recognition device, promote the experience that user uses this graphics context collection recognition device, in this device, can also comprise interactive processing module, for the interactive operation control information of obtaining user, and carry out predetermined interactive operation according to described interactive operation control information, and described interactive operation control information comprises at least one in limb action, the action that operates object, voice messaging, screen input or operation push-button; In interactive processing process, graphics context collection recognition device can also be play particular hint acoustic information to user by described audio unit, or also can to user, show specific content information by described display unit, and user can be according to the specific content information of corresponding voice prompt information or demonstration to the corresponding interactive operation control information of graphics context collection recognition device transmission, so that carry out interaction with graphics context collection recognition device.Particularly, corresponding interactive operation control information can be included in the reading of carrying out on printed matter and operate indication information etc., take and carry out interactive operation as example by limb action, interactive so that reading method or reading content are carried out to interaction control etc. between the hand-held object of action can be by hand or to(for) the user who reads general book and graphics context collection recognition device, as controlled the content etc. of a current location of re-reading by prearranged gesture.By this interactive processing module, can identify limb action or the operating article body action of reading user, so that this device can and read between user and carry out interaction, thereby promote the reading experience of reading user, make books vocalize media and interactive medium.
In embodiments of the present invention, closely just can be to the covering of required acquisition target and undistorted by corresponding multipoint images collection.Particularly, corresponding movable camera or a plurality of camera have a plurality of focal lengths, so just can make institute's all parts of acquisition target all in pinpointed focus, all clear to guarantee the image of each several part.
For example, shown in Figure 10, Figure 11, Figure 12, Figure 13 and Figure 14, owing to having adopted multi-cam or the movable camera structure of (as can rotary head type camera), for curved surface (such as the macrobending face at books middle part), can there be suitable shooting angle and position, therefore can effectively to it, take identification, corresponding shooting angle no matter directly over or inclined-plane, side can effectively take reference object, each several part is all in good focal length and get a distinct image and good resolution.And corresponding multipoint images collection makes resolution ratio of camera head requirement lower, with the camera of same resolution, captured thing is taken to the resolution (being more conducive to identification) that can reach higher in other words.
The above; be only the present invention's embodiment preferably, but protection scope of the present invention is not limited to this, is anyly familiar with in technical scope that those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claims.
Claims (10)
1. a graphics context collection recognition device, is characterized in that, comprising:
Multipoint images information acquisition unit and image information recognition unit, described multipoint images information acquisition unit passes to described image information recognition unit by the image information of collection, described image information recognition unit identifies graph-text content information according to described image information, and described multipoint images information acquisition unit adopts shooting style to obtain described image information, wherein, institute's multipoint images information acquisition unit comprises at least one movable camera, the photo angle of described movable camera and/or position are adjustable, and the control information of the control mode of described movable camera based on predetermined or reception is controlled its activity and taken subject is carried out to multi-angle and/or multipoint multipoint images, or, described multipoint images information acquisition unit comprises a plurality of cameras, i.e. two or three or four or more camera, described a plurality of camera has been used for multi-angle and/or multipoint multipoint images is taken, and each camera is fixed camera or movable camera, the photo angle of described movable camera and/or position are adjustable, described movable camera is for the control mode based on predetermined or the control information based on receiving or manually control its activity subject is carried out to multi-angle and/or the shooting of multipoint multipoint images, or, described multipoint images information acquisition unit comprises a fixed camera, described fixed camera comprises a plurality of camera lenses, and each camera lens that the described a plurality of camera lenses of the control information of the control mode based on predetermined or reception control comprise gathers described graph-text content information.
2. graphics context collection recognition device according to claim 1, is characterized in that, described movable camera comprises rotatable camera head and/or packaged type camera; Or described movable camera comprises one or more movable camera lenses, the photo angle of described movable camera lens and/or position are adjustable; If it is a plurality of that described movable camera comprises, each camera that a plurality of movable cameras comprise is for gathering the graph-text content information of all or part of scene; The position that described movable camera is arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
3. graphics context collection recognition device according to claim 1, it is characterized in that, described fixed camera comprises one or more camera lenses, if and described fixed camera comprises a plurality of camera lenses, the control information of the control mode based on predetermined or reception is controlled each camera lens and is gathered described graph-text content information, and each camera that described a plurality of cameras comprise is for gathering the graph-text content information of all or part of scene; The position that described camera is arranged at the region that need to gather described image information comprises: top, the edge in described region and/or oblique upper and/or directly over.
4. graphics context collection recognition device according to claim 1, is characterized in that, described graph-text content information comprises: the picture of printed matter or word content information, and/or, printed matter is read to the indication information of operation.
5. graphics context collection recognition device according to claim 4, is characterized in that, the described indication information that printed matter is read to operation comprises: the reading carried out on printed matter by hand or hand-held object indication operation information.
6. graphics context collection recognition device according to claim 4, it is characterized in that, described multipoint images information acquisition unit also comprises reading position information acquisition module, for the character image information of reading operating position by camera collection user, and described image information recognition unit is identified the word content that character image packets of information that described user reads operating position contains.
7. graphics context collection recognition device according to claim 4, it is characterized in that, the picture of described printed matter or word content packets of information are containing the Bibliographical Information of books, the collection of described multipoint images information acquisition unit include books Bibliographical Information image information and pass to described image information recognition unit, the described image information that includes the Bibliographical Information of books comprises the image information of figure book envelope, and described image information recognition unit is determined Bibliographical Information by the word of identifying in the image information of described figure book envelope, or, by identifying the image information of described figure book envelope, determine Bibliographical Information, or, by the sign of identifying in the image information of described figure book envelope, determine Bibliographical Information, described sign is books self or additional,
And/or,
The picture of described printed matter or word content packets of information are containing the page number information of books, the collection of described multipoint images information acquisition unit include books page number information image information and pass to described image information recognition unit, the image information that described page number information acquisition module gathers page in books by described camera module is as the information that comprises described page number information, by identifying the image information of page in described books, determine the page number of current reading, or, the page number of determining current reading by identifying in described books word in the image information of page or the digital page number.
8. according to the graphics context collection recognition device described in claim 1 to 7 any one, it is characterized in that, this device also comprises:
Audio unit, described multipoint images information acquisition unit passes to described image information recognition unit by current read page in the books of collection or the current reading position of printed matter or reading operation image information indicating positions or that comprise Bibliographical Information or comprise page number information, described image information recognition unit identifies this current read page or the current reading position of printed matter or reads audio-frequency information corresponding to operation word content information indication or Bibliographical Information or page number information and notify described audio unit according to described current read page or the current reading position of printed matter or reading operation image information indicating positions or that comprise Bibliographical Information, described audio unit is exported the audio-frequency information of described correspondence with audio form,
And/or,
Audio frequency input unit, for obtaining audio-frequency information;
And/or,
Memory cell, comprises audio information and/or preserves gathering image and/or the Word message obtaining in identifying and/or preserving the outside content information obtaining;
And/or,
Display unit, shows and comprises the content information of setting and/or gather image and Word message and/or the outside content information obtaining obtaining in identifying;
And/or,
Communication unit, for and compunication.
9. according to the graphics context collection recognition device described in claim 1 to 7 any one, it is characterized in that, this device comprises interactive processing module, for the interactive operation control information of obtaining user, and carry out predetermined interactive operation according to described interactive operation control information, and described interactive operation control information comprises at least one in limb action, the action that operates object, voice messaging, screen input or operation push-button.
10. graphics context collection recognition device according to claim 8, it is characterized in that, this device comprises interactive processing module, for the interactive operation control information of obtaining user, and carry out predetermined interactive operation according to described interactive operation control information, and described interactive operation control information comprises at least one in limb action, the action that operates object, voice messaging, screen input or operation push-button.
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910811258.2A CN111429767A (en) | 2013-01-25 | 2014-01-21 | Image-text photographing and identifying device |
| CN201410027696.7A CN103763453B (en) | 2013-01-25 | 2014-01-21 | A kind of graphics context collection identification device |
| CN201710012058.1A CN106791262A (en) | 2013-01-25 | 2014-01-21 | Graphics context collection identifying device |
| CN201710012060.9A CN106791263A (en) | 2013-01-25 | 2014-01-21 | One class graphics context collection identifying device |
| CN201710012059.6A CN106803864A (en) | 2013-01-25 | 2014-01-21 | Certain graphics context collection identifying device |
| CN201910811259.7A CN111050017A (en) | 2013-01-25 | 2014-01-21 | Picture and text photographing equipment |
Applications Claiming Priority (7)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201320040638.9 | 2013-01-25 | ||
| CN201310028174 | 2013-01-25 | ||
| CN2013200406389 | 2013-01-25 | ||
| CN201310028174.4 | 2013-01-25 | ||
| CN201320040638 | 2013-01-25 | ||
| CN2013100281744 | 2013-01-25 | ||
| CN201410027696.7A CN103763453B (en) | 2013-01-25 | 2014-01-21 | A kind of graphics context collection identification device |
Related Child Applications (5)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910811258.2A Division CN111429767A (en) | 2013-01-25 | 2014-01-21 | Image-text photographing and identifying device |
| CN201710012060.9A Division CN106791263A (en) | 2013-01-25 | 2014-01-21 | One class graphics context collection identifying device |
| CN201710012059.6A Division CN106803864A (en) | 2013-01-25 | 2014-01-21 | Certain graphics context collection identifying device |
| CN201910811259.7A Division CN111050017A (en) | 2013-01-25 | 2014-01-21 | Picture and text photographing equipment |
| CN201710012058.1A Division CN106791262A (en) | 2013-01-25 | 2014-01-21 | Graphics context collection identifying device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103763453A true CN103763453A (en) | 2014-04-30 |
| CN103763453B CN103763453B (en) | 2019-09-10 |
Family
ID=50529124
Family Applications (7)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420038757.5U Expired - Fee Related CN204046697U (en) | 2013-01-25 | 2014-01-21 | A kind of graphics context collection recognition device |
| CN201420037927.8U Expired - Fee Related CN203773763U (en) | 2013-01-25 | 2014-01-21 | Book reader |
| CN201710012059.6A Withdrawn CN106803864A (en) | 2013-01-25 | 2014-01-21 | Certain graphics context collection identifying device |
| CN201710012058.1A Withdrawn CN106791262A (en) | 2013-01-25 | 2014-01-21 | Graphics context collection identifying device |
| CN201410027696.7A Expired - Fee Related CN103763453B (en) | 2013-01-25 | 2014-01-21 | A kind of graphics context collection identification device |
| CN201410028668.7A Expired - Fee Related CN103761893B (en) | 2013-01-25 | 2014-01-21 | A kind of book reader |
| CN201710012060.9A Withdrawn CN106791263A (en) | 2013-01-25 | 2014-01-21 | One class graphics context collection identifying device |
Family Applications Before (4)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420038757.5U Expired - Fee Related CN204046697U (en) | 2013-01-25 | 2014-01-21 | A kind of graphics context collection recognition device |
| CN201420037927.8U Expired - Fee Related CN203773763U (en) | 2013-01-25 | 2014-01-21 | Book reader |
| CN201710012059.6A Withdrawn CN106803864A (en) | 2013-01-25 | 2014-01-21 | Certain graphics context collection identifying device |
| CN201710012058.1A Withdrawn CN106791262A (en) | 2013-01-25 | 2014-01-21 | Graphics context collection identifying device |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410028668.7A Expired - Fee Related CN103761893B (en) | 2013-01-25 | 2014-01-21 | A kind of book reader |
| CN201710012060.9A Withdrawn CN106791263A (en) | 2013-01-25 | 2014-01-21 | One class graphics context collection identifying device |
Country Status (1)
| Country | Link |
|---|---|
| CN (7) | CN204046697U (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104157171A (en) * | 2014-08-13 | 2014-11-19 | 三星电子（中国）研发中心 | Point-reading system and method thereof |
| CN104199834A (en) * | 2014-08-04 | 2014-12-10 | 徐�明 | Method and system for interactively obtaining and outputting remote resources on surface of information carrier |
| CN104217197A (en) * | 2014-08-27 | 2014-12-17 | 华南理工大学 | Touch reading method and device based on visual gestures |
| WO2016029779A1 (en) * | 2014-08-28 | 2016-03-03 | 深圳市国华识别科技开发有限公司 | Image identification based interactive control system and method for smart television |
| CN107977694A (en) * | 2017-11-28 | 2018-05-01 | 上海汇像信息技术有限公司 | A kind of sample is taken pictures the automatic analysis system of typing and identification |
| CN108156374A (en) * | 2017-12-25 | 2018-06-12 | 努比亚技术有限公司 | A kind of image processing method, terminal and readable storage medium storing program for executing |
| CN108845786A (en) * | 2018-05-31 | 2018-11-20 | 北京智能管家科技有限公司 | Intelligent reading partner method, apparatus, equipment and storage medium |
| CN108875694A (en) * | 2018-07-04 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Speech output method and device |
| CN109448453A (en) * | 2018-10-23 | 2019-03-08 | 北京快乐认知科技有限公司 | Point based on image recognition tracer technique reads answering method and system |
| CN109726697A (en) * | 2019-01-04 | 2019-05-07 | 北京灵优智学科技有限公司 | Merge the Online Video system and method for AV video communication and the identification of AI material object |
| CN111698384A (en) * | 2020-06-22 | 2020-09-22 | 上海肇观电子科技有限公司 | Image processing apparatus |
| CN113496637A (en) * | 2021-06-18 | 2021-10-12 | 湖南华壹影业有限公司 | Auxiliary training system for image information space-time scanning |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204046697U (en) * | 2013-01-25 | 2014-12-24 | 陈旭 | A kind of graphics context collection recognition device |
| US9973671B2 (en) * | 2014-08-27 | 2018-05-15 | Symbol Technologies, Llc | Method and apparatus for directing data capture devices in a mobile unit with a single operation |
| CN104793852A (en) * | 2015-04-02 | 2015-07-22 | 广东小天才科技有限公司 | Method and device for detecting page upturning movement on electronic reading machine |
| CN104766501B (en) * | 2015-04-09 | 2017-07-14 | 广东小天才科技有限公司 | A kind of point reader and its method for correcting coordinate |
| CN105046253B (en) * | 2015-06-24 | 2018-05-11 | 山西同方知网数字出版技术有限公司 | A kind of paper strip of paper used for sealing automatic recognition system and method based on OCR |
| CN105139699A (en) * | 2015-08-04 | 2015-12-09 | 广东小天才科技有限公司 | Method and device for automatically turning pages |
| CN105447499B (en) * | 2015-10-23 | 2018-09-04 | 北京爱乐宝机器人科技有限公司 | A kind of books interactive approach, device and equipment |
| CN106408560B (en) * | 2016-09-05 | 2020-01-03 | 广东小天才科技有限公司 | Method and device for rapidly acquiring effective image |
| CN106515258B (en) * | 2016-11-10 | 2017-12-19 | 深圳市科迈爱康科技有限公司 | Notebook, intelligent terminal and notebook content indexing creation method |
| CN108242233B (en) * | 2016-12-26 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Audio data playing method and device |
| CN107085724A (en) * | 2017-03-31 | 2017-08-22 | 上海斐讯数据通信技术有限公司 | A kind of book pages information carrying means and method |
| CN107657747A (en) * | 2017-10-17 | 2018-02-02 | 梁北洪 | A kind of books, system of studying at school on a temporary basis and its encouragement reading method |
| CN108257615A (en) * | 2018-01-15 | 2018-07-06 | 北京物灵智能科技有限公司 | A kind of user language appraisal procedure and system |
| CN108536287B (en) * | 2018-03-26 | 2021-03-02 | 深圳市同维通信技术有限公司 | Method and device for reading according to user instruction |
| CN108762507B (en) * | 2018-05-30 | 2021-05-04 | 辽东学院 | Image tracking method and device |
| WO2020034519A1 (en) * | 2018-08-17 | 2020-02-20 | 中国图书进出口（集团）大连有限公司 | Spatial audio reading system and method |
| CN109703232A (en) * | 2018-11-30 | 2019-05-03 | 数景智能科技(宁波)有限公司 | A kind of intelligence books note |
| CN109753554B (en) * | 2019-01-14 | 2021-03-30 | 广东小天才科技有限公司 | Searching method based on three-dimensional space positioning and family education equipment |
| CN111583734A (en) * | 2019-02-19 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Touch reading method and touch reading pen |
| CN111695372B (en) * | 2019-03-12 | 2023-10-27 | 阿里巴巴集团控股有限公司 | Click-to-read method and click-to-read data processing method |
| CN110060524A (en) * | 2019-04-30 | 2019-07-26 | 广东小天才科技有限公司 | The method and reading machine people that a kind of robot assisted is read |
| CN110287881A (en) * | 2019-06-26 | 2019-09-27 | 上海交通大学 | Books identifying system, books recognition methods, electronic device and storage medium |
| CN110489005B (en) * | 2019-06-28 | 2022-12-27 | 浙江工业大学 | Two-dimensional point display with touch positioning function and two-dimensional contact driving method thereof |
| CN110992738A (en) * | 2019-10-21 | 2020-04-10 | 北京十分科技有限公司 | Automatic reading method and device for reading material |
| CN111178348B (en) * | 2019-12-09 | 2024-03-22 | 广东小天才科技有限公司 | Method for tracking target object and sound box equipment |
| CN110949037A (en) * | 2019-12-16 | 2020-04-03 | 中国工程物理研究院激光聚变研究中心 | Automatic identification and ejection device for file box |
| CN111027341A (en) * | 2019-12-28 | 2020-04-17 | 安徽硕威智能科技有限公司 | Interaction method, device and system based on OID two-dimensional password identification and storage medium thereof |
| CN111701883A (en) * | 2020-07-01 | 2020-09-25 | 湖南德荣医疗器械物流配送服务有限公司 | Intelligent sorting equipment and method for intelligent warehousing |
| CN112329563A (en) * | 2020-10-23 | 2021-02-05 | 复旦大学 | Intelligent reading auxiliary method and system based on raspberry pie |
| CN112258911B (en) * | 2020-11-12 | 2021-11-09 | 吉林农业科技学院 | English word memory device based on time delay detects |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1952974A (en) * | 2006-11-10 | 2007-04-25 | 中山大学 | Automatic pinpoint system and method of books in library |
| CN200944633Y (en) * | 2006-08-15 | 2007-09-05 | 沈洪 | Multi-scene imaging apparatus |
| CN201035576Y (en) * | 2006-12-20 | 2008-03-12 | 北京恒基伟业投资发展有限公司 | Device of implementing instant translation using digital camera technique |
| CN201063025Y (en) * | 2007-05-11 | 2008-05-21 | 葛宇 | Detecting apparatus with multiple angle camera head |
| CN201097383Y (en) * | 2007-01-12 | 2008-08-06 | 林良锐 | Book hearing machine |
| CN201294001Y (en) * | 2008-11-26 | 2009-08-19 | 佛山市安讯智能科技有限公司 | Recognizer for collecting and processing image words |
| CN101527828A (en) * | 2009-04-14 | 2009-09-09 | 深圳华为通信技术有限公司 | Image acquisition equipment |
| CN201315627Y (en) * | 2008-12-30 | 2009-09-23 | 蒋清晓 | Multifunctional portable-type electronic typoscope |
| CN101630193A (en) * | 2008-07-15 | 2010-01-20 | 张雪峰 | Hand induction equipment |
| CN201611477U (en) * | 2010-03-12 | 2010-10-20 | 北京汇冠新技术股份有限公司 | Optical touch screen |
| CN201622581U (en) * | 2010-04-08 | 2010-11-03 | 陶懿 | Processing device of image taking and character recognition |
| CN101882014A (en) * | 2009-12-29 | 2010-11-10 | 胡世曦 | Method for judging whether target point belongs to plane, mouse and touch screen |
| CN102110332A (en) * | 2009-12-24 | 2011-06-29 | 上海阿艾依智控***有限公司 | Book registering and managing device based on computer vision and radio frequency identification technology |
| CN102566603A (en) * | 2012-02-29 | 2012-07-11 | 天津天地伟业数码科技有限公司 | Architecture and method for positioning dome camera |
| CN102682608A (en) * | 2012-05-16 | 2012-09-19 | 江苏尤特斯新技术有限公司 | Method for image forensics of motor vehicle plate covering and staining behaviors |
| CN202551228U (en) * | 2012-02-16 | 2012-11-21 | 北京奥美达科技有限公司 | Visual aid |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1202471C (en) * | 2001-09-19 | 2005-05-18 | 力新国际科技股份有限公司 | Book makign system and method |
| US7660458B1 (en) * | 2004-12-14 | 2010-02-09 | Google Inc. | Three-dimensional model construction using unstructured pattern |
| CN2786695Y (en) * | 2005-04-06 | 2006-06-07 | 极鼎科技股份有限公司 | Interactive studying equipment |
| CN2807364Y (en) * | 2005-06-24 | 2006-08-16 | 赵舜培 | Electronic learning auxiliary device |
| CN201194112Y (en) * | 2008-05-12 | 2009-02-11 | 刘建生 | Video shooting type multifunctional click-to-read machine |
| CN101676970B (en) * | 2008-09-16 | 2013-03-20 | 深圳市王菱科技开发有限公司 | Reading processing system with multiple electronic read data functions |
| US8332741B2 (en) * | 2008-12-08 | 2012-12-11 | Qurio Holdings, Inc. | Method and system for on-demand narration of a customized story |
| CN201364654Y (en) * | 2009-03-11 | 2009-12-16 | 中国长城计算机深圳股份有限公司 | Book point-reading system |
| CN201540655U (en) * | 2009-05-13 | 2010-08-04 | 崔伟 | Phonic book |
| CN101833663B (en) * | 2010-04-21 | 2012-10-10 | 北方工业大学 | Binocular electronic reader |
| CN204046697U (en) * | 2013-01-25 | 2014-12-24 | 陈旭 | A kind of graphics context collection recognition device |
-
2014
- 2014-01-21 CN CN201420038757.5U patent/CN204046697U/en not_active Expired - Fee Related
- 2014-01-21 CN CN201420037927.8U patent/CN203773763U/en not_active Expired - Fee Related
- 2014-01-21 CN CN201710012059.6A patent/CN106803864A/en not_active Withdrawn
- 2014-01-21 CN CN201710012058.1A patent/CN106791262A/en not_active Withdrawn
- 2014-01-21 CN CN201410027696.7A patent/CN103763453B/en not_active Expired - Fee Related
- 2014-01-21 CN CN201410028668.7A patent/CN103761893B/en not_active Expired - Fee Related
- 2014-01-21 CN CN201710012060.9A patent/CN106791263A/en not_active Withdrawn
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200944633Y (en) * | 2006-08-15 | 2007-09-05 | 沈洪 | Multi-scene imaging apparatus |
| CN1952974A (en) * | 2006-11-10 | 2007-04-25 | 中山大学 | Automatic pinpoint system and method of books in library |
| CN201035576Y (en) * | 2006-12-20 | 2008-03-12 | 北京恒基伟业投资发展有限公司 | Device of implementing instant translation using digital camera technique |
| CN201097383Y (en) * | 2007-01-12 | 2008-08-06 | 林良锐 | Book hearing machine |
| CN201063025Y (en) * | 2007-05-11 | 2008-05-21 | 葛宇 | Detecting apparatus with multiple angle camera head |
| CN101630193A (en) * | 2008-07-15 | 2010-01-20 | 张雪峰 | Hand induction equipment |
| CN201294001Y (en) * | 2008-11-26 | 2009-08-19 | 佛山市安讯智能科技有限公司 | Recognizer for collecting and processing image words |
| CN201315627Y (en) * | 2008-12-30 | 2009-09-23 | 蒋清晓 | Multifunctional portable-type electronic typoscope |
| CN101527828A (en) * | 2009-04-14 | 2009-09-09 | 深圳华为通信技术有限公司 | Image acquisition equipment |
| CN102110332A (en) * | 2009-12-24 | 2011-06-29 | 上海阿艾依智控***有限公司 | Book registering and managing device based on computer vision and radio frequency identification technology |
| CN101882014A (en) * | 2009-12-29 | 2010-11-10 | 胡世曦 | Method for judging whether target point belongs to plane, mouse and touch screen |
| CN201611477U (en) * | 2010-03-12 | 2010-10-20 | 北京汇冠新技术股份有限公司 | Optical touch screen |
| CN201622581U (en) * | 2010-04-08 | 2010-11-03 | 陶懿 | Processing device of image taking and character recognition |
| CN202551228U (en) * | 2012-02-16 | 2012-11-21 | 北京奥美达科技有限公司 | Visual aid |
| CN102566603A (en) * | 2012-02-29 | 2012-07-11 | 天津天地伟业数码科技有限公司 | Architecture and method for positioning dome camera |
| CN102682608A (en) * | 2012-05-16 | 2012-09-19 | 江苏尤特斯新技术有限公司 | Method for image forensics of motor vehicle plate covering and staining behaviors |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199834A (en) * | 2014-08-04 | 2014-12-10 | 徐�明 | Method and system for interactively obtaining and outputting remote resources on surface of information carrier |
| CN104199834B (en) * | 2014-08-04 | 2018-11-27 | 徐�明 | The method and system for obtaining remote resource from information carrier surface interactive mode and exporting |
| CN104157171B (en) * | 2014-08-13 | 2016-11-09 | 三星电子（中国）研发中心 | A kind of point-of-reading system and method thereof |
| CN104157171A (en) * | 2014-08-13 | 2014-11-19 | 三星电子（中国）研发中心 | Point-reading system and method thereof |
| CN104217197B (en) * | 2014-08-27 | 2018-04-13 | 华南理工大学 | A kind of reading method and device of view-based access control model gesture |
| CN104217197A (en) * | 2014-08-27 | 2014-12-17 | 华南理工大学 | Touch reading method and device based on visual gestures |
| WO2016029779A1 (en) * | 2014-08-28 | 2016-03-03 | 深圳市国华识别科技开发有限公司 | Image identification based interactive control system and method for smart television |
| US10893316B2 (en) | 2014-08-28 | 2021-01-12 | Shenzhen Prtek Co. Ltd. | Image identification based interactive control system and method for smart television |
| CN107977694A (en) * | 2017-11-28 | 2018-05-01 | 上海汇像信息技术有限公司 | A kind of sample is taken pictures the automatic analysis system of typing and identification |
| CN107977694B (en) * | 2017-11-28 | 2021-07-13 | 倍仪昇智能科技(苏州)有限公司 | Automatic analysis system for photographing, inputting and identifying samples |
| CN108156374B (en) * | 2017-12-25 | 2020-12-08 | 努比亚技术有限公司 | Image processing method, terminal and readable storage medium |
| CN108156374A (en) * | 2017-12-25 | 2018-06-12 | 努比亚技术有限公司 | A kind of image processing method, terminal and readable storage medium storing program for executing |
| CN108845786A (en) * | 2018-05-31 | 2018-11-20 | 北京智能管家科技有限公司 | Intelligent reading partner method, apparatus, equipment and storage medium |
| CN108875694A (en) * | 2018-07-04 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Speech output method and device |
| CN109448453A (en) * | 2018-10-23 | 2019-03-08 | 北京快乐认知科技有限公司 | Point based on image recognition tracer technique reads answering method and system |
| CN109726697A (en) * | 2019-01-04 | 2019-05-07 | 北京灵优智学科技有限公司 | Merge the Online Video system and method for AV video communication and the identification of AI material object |
| CN109726697B (en) * | 2019-01-04 | 2021-07-20 | 北京灵优智学科技有限公司 | Online video system and method integrating AV video communication and AI real object identification |
| CN111698384A (en) * | 2020-06-22 | 2020-09-22 | 上海肇观电子科技有限公司 | Image processing apparatus |
| CN111698384B (en) * | 2020-06-22 | 2022-06-21 | 上海肇观电子科技有限公司 | Image processing apparatus |
| CN113496637A (en) * | 2021-06-18 | 2021-10-12 | 湖南华壹影业有限公司 | Auxiliary training system for image information space-time scanning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106803864A (en) | 2017-06-06 |
| CN204046697U (en) | 2014-12-24 |
| CN203773763U (en) | 2014-08-13 |
| CN103763453B (en) | 2019-09-10 |
| CN106791263A (en) | 2017-05-31 |
| CN103761893A (en) | 2014-04-30 |
| CN106791262A (en) | 2017-05-31 |
| CN103761893B (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103763453A (en) | Image and text collection and recognition device | |
| KR102559028B1 (en) | Method and apparatus for recognizing handwriting | |
| CN111050017A (en) | Picture and text photographing equipment | |
| EP2311018B1 (en) | Aiding device for reading a printed text | |
| KR102147935B1 (en) | Method for processing data and an electronic device thereof | |
| CN109409234B (en) | Method and system for assisting students in problem location learning | |
| CN108762507B (en) | Image tracking method and device | |
| CN105590486A (en) | Machine vision-based pedestal-type finger reader, related system device and related method | |
| WO2019033656A1 (en) | Board-writing processing method, device and apparatus, and computer-readable storage medium | |
| CN104835361B (en) | A kind of electronic dictionary | |
| CN108805108A (en) | A kind of writing on the blackboard person's handwriting recording method | |
| CN110059678A (en) | A kind of detection method, device and computer readable storage medium | |
| CN111179650A (en) | Platform system for automatic documenting of paper writing board writing and explanation | |
| CN111539408A (en) | Intelligent point reading scheme based on photographing and object recognizing | |
| von Agris et al. | Signum database: Video corpus for signer-independent continuous sign language recognition | |
| Saleous et al. | Read2Me: A cloud-based reading aid for the visually impaired | |
| CN112306601A (en) | Application interaction method and device, electronic equipment and storage medium | |
| US20230050987A1 (en) | Apparatus for fastening an imaging device at a predetermined arrangement for image capture and detecting regions of interest in an image using image processing | |
| CN109948600A (en) | A kind of intelligence Text region pen and character identification system | |
| CN110971924A (en) | Method, device, storage medium and system for beautifying in live broadcast process | |
| WO2023272608A1 (en) | Picture book assisted reading method, and electronic device | |
| CN111753715B (en) | Method and device for shooting test questions in click-to-read scene, electronic equipment and storage medium | |
| CN107301416A (en) | A kind of on-line acquisition system and its method to hand-written process | |
| CN111914563A (en) | Intention recognition method and device combined with voice | |
| TWI312487B (en) | A snapshot characters recognition system of a hand-carried data processing device and its 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190910 Termination date: 20210121 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |