CN107886947A - Image processing method and device - Google Patents

Image processing method and device Download PDF

Info

Publication number
CN107886947A
CN107886947A CN201710980039.8A CN201710980039A CN107886947A CN 107886947 A CN107886947 A CN 107886947A CN 201710980039 A CN201710980039 A CN 201710980039A CN 107886947 A CN107886947 A CN 107886947A
Authority
CN
China
Prior art keywords
voice
keyword
voice messaging
word
sound
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
Application number
CN201710980039.8A
Other languages
Chinese (zh)
Inventor
邓童虎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gree Electric Appliances Inc of Zhuhai
Original Assignee
Gree Electric Appliances Inc of Zhuhai
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Gree Electric Appliances Inc of Zhuhai filed Critical Gree Electric Appliances Inc of Zhuhai
Priority to CN201710980039.8A priority Critical patent/CN107886947A/en
Publication of CN107886947A publication Critical patent/CN107886947A/en
Priority to PCT/CN2018/100212 priority patent/WO2019076120A1/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the invention relates to the technical field of image processing, in particular to an image processing method and device. The method comprises the following steps: receiving voice information; recognizing the voice information to obtain an image processing command; and according to the image processing command, carrying out image processing on the target image to obtain the processed target image. Therefore, in the embodiment of the invention, the user does not need to manually operate the mobile terminal to process the image, but only receives the voice information of the user, so that the image processing function can be realized.

Description

The method and device of a kind of image procossing
Technical field
Embodiment of the present invention is related to technical field of image processing, more particularly to the method and dress of a kind of image procossing Put.
Background technology
With the development of science and technology, the function of the smart machine such as mobile terminal is increasingly abundant and perfect, including intelligence The image processing function of energyization, in the prior art, user carry out the process one of image procossing using smart machines such as mobile terminals As be that, first by user using the pending image of acquisition for mobile terminal, user is operated manually to mobile terminal again, to image Handled, and then handle and get desired image.
For the present inventor during the present invention is realized, there is problems with discovery in the prior art：Existing In technology, the process that user carries out image procossing using smart machines such as mobile terminals is relatively complicated, and user must be to mobile whole The smart machines such as end carry out that manually image can be being handled, and are made troubles for user, therefore, it is possible to provide it is a kind of easy, need not Manually operated image processing method is particularly necessary.
The content of the invention
Embodiment of the present invention is mainly solving the technical problems that provide a kind of simplicity, without manually operated image procossing Method and device.
In a first aspect, in order to solve the above technical problems, the technical scheme that embodiment of the present invention uses is：There is provided one The method of kind image procossing, applied to terminal device, including：
Receive voice messaging；
The voice messaging is identified, obtains image processing command；
Handled and ordered according to described image, image procossing, the target image after being handled are carried out to target image.
Optionally, described the step of being identified to the voice messaging, obtaining image processing command, includes：
The voice messaging is converted into text message；
Process object keyword and processing mode keyword are extracted from the text message；
By keyword and the processing mode crucial phrase of dealing with objects into image processing command.
Optionally, described the step of being identified to the voice messaging, obtaining image processing command, includes：
According to the voice messaging and the sound bank for being preset with keyword voice, extract in the voice messaging with presetting Have in the sound bank of keyword voice pronunciation identical word, wherein, be preset with the sound bank of keyword voice contain it is pre- If process object keyword voice and processing mode keyword voice；
According to word described in the pronunciation identical extracted, process object keyword and processing mode keyword are obtained；
By keyword and the processing mode crucial phrase of dealing with objects into image processing command.
Optionally, described handled according to described image is ordered, and the step of target image progress image procossing is included：
According to the process object keyword, process object is identified from the target image；
According to the processing mode keyword, processing is performed to the process object.
Optionally, after the step of reception voice messaging, methods described also includes：
Judge whether only include a kind of sound in the voice messaging；
If only including a kind of sound in the voice messaging, the voice word of the voice messaging top N is extracted；
Judge whether the voice word includes the sound of pre-set commands word；
If so, then voice messaging is identified into described, the step of described image processing is ordered is obtained.
Optionally, methods described also includes：
If the voice messaging includes muli-sounds, the voice word of each sound top N is extracted；
Obtain the sound that the voice word includes pre-set commands word；
Described that the voice messaging is identified, obtaining described image processing order is specially：
The sound acquired is identified, obtains described image processing order.
Second aspect, in order to solve the above technical problems, another technical scheme that embodiment of the present invention uses is：There is provided A kind of device of image procossing, applied to terminal device, including：
Speech reception module, for receiving voice messaging；
Order acquisition module, for the voice messaging to be identified, obtain image processing command；
Image processing module, ordered for being handled according to described image, image procossing is carried out to target image, handled The target image afterwards.
Optionally, the order acquisition module includes：
Text acquiring unit, for the voice messaging to be converted into text message；
Text Feature Extraction unit, it is crucial for extracting process object keyword and processing mode from the text message Word；
Order forms unit, for the process object keyword to be ordered with processing mode crucial phrase into image procossing Order.
Optionally, the order acquisition module includes：
Word acquiring unit, it is used to, according to the voice messaging and the sound bank for being preset with keyword voice, extract Pronunciation identical word in the sound bank of keyword voice is preset with described in the voice messaging, wherein, it is preset with key Default process object keyword voice and processing mode keyword voice are contained in the sound bank of word sound；
Word extraction unit, it is used for the word according to the pronunciation identical extracted, and it is crucial to obtain process object Word and processing mode keyword；
Order generation unit, it is used to processing mode crucial phrase order the process object keyword into image procossing Order.
Optionally, described image processing module includes：
Object identification unit, for according to the process object keyword, processing pair to be identified from the target image As；
Processing unit is performed, for according to the processing mode keyword, processing to be performed to the process object.
Optionally, sound judge module, for judging whether only include a kind of sound in the voice messaging；
First extraction module, if for only including a kind of sound in the voice messaging, extract the voice messaging top N Voice word；
Voice word judge module, for judging whether the voice word includes the sound of pre-set commands word；If so, then enter Enter it is described voice messaging is identified, obtain described image processing order the step of.
Optionally, described device also includes：
Second extraction module, if including muli-sounds for the voice messaging, extract the voice of each sound top N Word；
Sound screening module, the sound of pre-set commands word is included for obtaining the voice word；
Described that the voice messaging is identified, obtaining described image processing order is specially：
The sound acquired to sound screening module is identified, and obtains described image processing order.
The beneficial effect of embodiment of the present invention is：The situation of prior art is different from, in embodiments of the present invention, figure As the step of processing method includes：Receive voice messaging；The voice messaging is identified, obtains image processing command；Root Handle and order according to described image, picture editting's processing, the target image after being edited are carried out to target image.Therefore, In embodiments of the present invention, user handles image without the manually operated mobile terminal passed through, but only by reception The voice messaging of user, the function of image procossing can be realized, compared with prior art, this process is easier, saves user Time, improve operating efficiency.
Brief description of the drawings
One or more embodiments are illustrative by the picture in corresponding accompanying drawing, and these are exemplary Illustrate not form the restriction to embodiment, the element with same reference numbers label is expressed as similar member in accompanying drawing Part, unless there are special statement, composition does not limit the figure in accompanying drawing.
Fig. 1 is a kind of schematic flow sheet of the method for image procossing that embodiment of the present invention one provides；
Fig. 2 is that voice messaging is identified in a kind of image procossing that embodiment of the present invention one provides and obtains image Handle a schematic flow sheet of the method for order；
Fig. 3 is that voice messaging is identified in a kind of image procossing that embodiment of the present invention one provides and obtains image Handle another schematic flow sheet of the method for order；
Fig. 4 is according to image processing command, to mesh in a kind of image procossing that invention embodiment one provides Logo image carries out image procossing, the schematic flow sheet of the method for the target image after being handled；
Fig. 5 is a kind of schematic flow sheet of the method for image procossing that embodiment of the present invention two provides；
Fig. 6 is a kind of structural representation of the device for image procossing that embodiment of the present invention three provides；
Fig. 7 is a kind of structural representation of the device for image procossing that embodiment of the present invention four provides；
Fig. 8 is the hardware architecture diagram of the electronic equipment of execution image procossing provided in an embodiment of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with drawings and the embodiments, The present invention will be described in further detail.It should be appreciated that embodiment described herein is only to explain the present invention, It is not intended to limit the present invention.
Embodiment one
Fig. 1 to Fig. 4 is referred to, Fig. 1 is a kind of method for image procossing that embodiment of the present invention one provides, applied to end End equipment, including：
Step 101：Receive voice messaging；
When user opens the image processing function of mobile terminal, mobile terminal will gather the voice messaging of user in real time, The voice messaging is the voice that user sends in real time.
Step 102：Voice messaging is identified, obtains image processing command；
Specifically, the step of voice messaging is identified includes：
Step 1021：The voice messaging received is converted into text message；
Text information is consistent with voice messaging, text message terminal recognition easy to remove and extraction.Wherein, text envelope Breath includes dealing with objects keyword and processing mode keyword, and process object keyword is pair pending in pending picture The title of elephant, such as：Dealing with objects keyword includes " people ", " apple " and " house " etc.；Processing mode keyword is thought for user To the processing mode of pending object in picture, such as：Processing mode keyword include " cutting ", " breaking mosaic ", " U.S. face ", " bloom " and " thin face " etc..
Step 1022：Extraction process object key word and processing mode keyword from text message；
Step 1023：Will process object keyword and processing mode crucial phrase into image processing command, for example, when The voice messaging received be converted to the content that is obtained after text message for " U.S. face processing is carried out to the people in picture " when, its In, process object keyword is " people ", and processing mode keyword is " U.S. face ", then the image processing command obtained is then for " to figure People in piece carries out U.S. face ".
Certainly, in embodiment of the present invention one, voice messaging can also be identified by other means, and obtains Image processing command, for example, further referring to Fig. 3, perform following steps 1021a, step 1022a and step 1023a：
Step 1021a：According to voice messaging and the sound bank for being preset with keyword voice, extract in voice messaging and pre- Pronounce identical word in sound bank provided with keyword voice, wherein, it is preset with the sound bank of keyword voice and contains Default process object keyword voice and processing mode keyword voice；For example, it is preset with the sound bank of keyword voice Contain the process object keyword voice that " people ", " women " and " male " etc. pre-sets, and " cutting ", " beat Marseille Gram ", the processing mode keyword voice that pre-sets such as " U.S. face " and " bloom ".
Step 1022a：According to the pronunciation identical word extracted, obtain process object keyword and processing mode is closed Keyword；
Specifically, for example, if the process object keyword voice pre-set includes " women ", the place pre-set Reason mode keyword voice includes " U.S. face ", also, the pronunciation identical word extracted is " women " and " U.S. face ", then By " women " as process object keyword, " U.S. face " is used as processing mode keyword.
Step 1023a：Keyword and processing mode crucial phrase will be dealt with objects into image processing command.
Specifically, for example, if acquired process object keyword is " women ", acquired processing mode keyword For " U.S. face ", then the image processing command obtained is then " carrying out U.S. face to the women in picture ".Step 103：At image Reason order, image procossing, the target image after being handled are carried out to target image.
Further, step 103 includes：
Step 1031：Process object keyword and processing mode in image processing command according to acquired in step 102 Keyword, object corresponding with process object keyword in picture is identified using image recognition technology；
Step 1032：Processing is performed to process object according to mode corresponding to processing mode keyword.
The process object in pending image is performed according to mode corresponding to processing mode keyword and handles and generate one New images after processing.
Include in embodiment of the present invention, the step of image processing method：Receive voice messaging；The voice messaging is entered Row identification, obtains image processing command；Handled and ordered according to described image, image procossing is carried out to target image, handled The target image afterwards.Therefore, in embodiments of the present invention, mobile terminal need not receive the manually operated of user and handle Image, but only by the voice messaging for receiving user, the function of image procossing, compared with prior art, this mistake can be realized Cheng Gengjia is easy, saves user time, improves operating efficiency.
Embodiment two
Referring to Fig. 5, Fig. 5 is a kind of method for image procossing that embodiment of the present invention two provides, set applied to terminal It is standby, including：
Step 201：Receive voice messaging；
When user opens the image processing function of mobile terminal, mobile terminal will gather the voice messaging of user in real time, The voice messaging is the voice that user sends in real time.
Step 202：Judge whether only include a kind of sound in voice messaging；
Specifically, using existing speech recognition technology, judged by phonetic features such as tone color, audios be in voice messaging No includes a kind of sound.
Step 203：If only including a kind of sound in voice messaging, the voice word of voice messaging top N is extracted；
Specifically, when judging to confirm only to include a kind of sound in voice messaging according to step 202, before extracting voice messaging The voice word of N positions, optionally, N 3,5 or 7 etc.；For example, when N be 5, and the voice messaging received for " processing Order to carry out U.S. face to the women in picture ", then the voice word of 5 is " processing order is " before extraction voice messaging.
Step 204：Judge whether voice word includes pre-set commands word；
Pre-set commands word is the order word pre-set, such as：" processing order is " or " order is " etc., lift individual specific Example, when the voice word obtained according to step 203 is " processing order be ", and pre-set commands word is also " processing order is " When, it is determined that voice word includes pre-set commands word.It is when judging that voice word includes pre-set commands word, then no into step 205 Then, into step 207.
Step 205：Voice messaging is identified, obtains image processing command；
It should be noted that：The step 205 of embodiment of the present invention is based on identical inventive concept, step with step 102 205 particular content is referred to step 102, does not repeat one by one herein.
Step 206：Handled and ordered according to described image, image procossing is carried out to target image, it is described after being handled Target image；
Step 207：If voice messaging includes muli-sounds, the voice word of each sound top N is extracted；
When determining that voice messaging includes muli-sounds after execution of step 202, then extract and record N before each sound The voice word of position.
Step 208：Obtain the sound that voice word includes pre-set commands word；
Voice word in obtaining step 207 in each voice messaging includes the sound of pre-set commands word.It is further optional , in acquired voice word includes the sound of pre-set commands word, the maximum sound of volume is filtered out, the sound is performed Step 209.
Step 209：The sound acquired is identified, obtains described image processing order.
It should be noted that：The step 209 of embodiment of the present invention is based on identical inventive concept, step with step 102 209 particular content is referred to step 102, does not repeat one by one herein.
Behind execution of step 209, then perform step 206.
Include in embodiment of the present invention, the step of image processing method：Receive voice messaging；Judge be in voice messaging No includes a kind of sound, if so, extracting the voice word of voice messaging top N and judging whether voice word includes pre-set commands Word, if so, then the voice messaging is identified, image processing command is obtained, ordered further according to described image processing, to mesh Logo image carries out picture editting's processing, the target image after being handled；If judging to include muli-sounds in voice messaging, The voice word of each sound top N is then extracted, the sound that voice word includes pre-set commands word is obtained, to the sound acquired It is identified, obtains described image processing order, image procossing, the target figure after being handled are carried out to target image Picture.
Therefore, in embodiments of the present invention, mobile terminal need not receive the manually operated of user and handle image, but Only by the voice messaging for receiving user, the function of image procossing can be realized, compared with prior art, this process is simpler Just, user time is saved, improves operating efficiency.In addition, when the sound of acquisition is multiple, will also be carried for each sound The voice word of each sound top N is taken, performs image procossing respectively, or according to the maximum sound of volume, perform image procossing.
Embodiment three
Referring to Fig. 6, Fig. 6 is a kind of device 50 for image procossing that embodiment of the present invention three provides, applied to terminal Equipment, including：Speech reception module 51, order acquisition module 52 and image processing module 53；
Wherein, speech reception module 51 is used to receive voice messaging；
Order acquisition module 52 is used to the voice messaging be identified, and obtains image processing command；
Image processing module 53, which is used to be handled according to described image, orders, and carries out image procossing to target image, obtains everywhere The target image after reason.
Optionally, the order acquisition module 52 includes：Text acquiring unit 521, Text Feature Extraction unit 522 and order shape Into unit 523；
Text acquiring unit 521 is used to the voice messaging being converted to text message；
Text Feature Extraction unit 522 is used to extract process object keyword from the text message and processing mode is crucial Word；
Order forms unit 523 and is used to processing mode crucial phrase order the process object keyword into image procossing Order.
Optionally, described image processing module 53 includes：Object identification unit 531 and execution processing unit 532；
Object identification unit 531, for according to the process object keyword, processing to be identified from the target image Object；
Processing unit 532 is performed, for according to the processing mode keyword, processing to be performed to the process object.
In embodiment of the present invention, image processing method subtraction unit includes：Speech reception module 51, the and of order acquisition module 52 Image processing module 53；Perform respectively：Receive voice messaging；The voice messaging is identified, obtains image processing command； Handled and ordered according to described image, image procossing, the target image after being handled are carried out to target image.Therefore, exist In embodiment of the present invention, mobile terminal need not receive the manually operated of user and handle image, but use only by receiving The voice messaging at family, the function of image procossing can be realized, compared with prior art, this process is easier, when saving user Between, improve operating efficiency.
Embodiment four
Referring to Fig. 7, Fig. 7 is a kind of device 50 for image procossing that embodiment of the present invention four provides, applied to terminal Equipment, including：Speech reception module 51, order acquisition module 52 and image processing module 53；
Wherein, speech reception module 51 is used to receive voice messaging；
Order acquisition module 52 is used to the voice messaging be identified, and obtains image processing command；
Image processing module 53, which is used to be handled according to described image, orders, and carries out image procossing to target image, obtains everywhere The target image after reason.
Optionally, the order acquisition module 52 includes：Text acquiring unit 521, Text Feature Extraction unit 522 and order shape Into unit 523；
Text acquiring unit 521 is used to the voice messaging being converted to text message；
Text Feature Extraction unit 522 is used to extract process object keyword from the text message and processing mode is crucial Word；
Order forms unit 523 and is used to processing mode crucial phrase order the process object keyword into image procossing Order.
Optionally, the order acquisition module 52 includes：(figure is not for word acquiring unit (not shown), word extraction unit Show) and order generation unit (not shown)；
Word acquiring unit, it is used to, according to voice messaging and the sound bank for being preset with keyword voice, extract voice With being preset with the sound bank of keyword voice pronunciation identical word in information, wherein, it is preset with the voice of keyword voice Default process object keyword voice and processing mode keyword voice are contained in storehouse；
Word extraction unit, it is used for according to the pronunciation identical word extracted, obtain process object keyword and Processing mode keyword；
Order generation unit, it is used to deal with objects keyword and processing mode crucial phrase into image processing command.
Optionally, described image processing module 53 includes：Object identification unit 531 and execution processing unit 532；
Object identification unit 531, for according to the process object keyword, processing to be identified from the target image Object；
Processing unit 532 is performed, for according to the processing mode keyword, processing to be performed to the process object.
Optionally, device 50 also includes：Sound judge module 54, for judging whether only include one in the voice messaging Kind sound；
First extraction module 55, if for only including a kind of sound in the voice messaging, extract N before the voice messaging The voice word of position；
Voice word judge module 56, for judging whether the voice word includes the sound of pre-set commands word；If so, then Voice messaging is identified into described, obtains the step of described image processing is ordered.
Optionally, described device 50 also includes：
Second extraction module 57, if including muli-sounds for the voice messaging, extract the language of each sound top N Sound word；
Sound screening module 58, the sound of pre-set commands word is included for obtaining the voice word；
Described that the voice messaging is identified, obtaining described image processing order is specially：
The sound acquired to sound screening module is identified, and obtains described image processing order.
In embodiment of the present invention, image processing method subtraction unit includes：Speech reception module 51, the and of order acquisition module 52 Image processing module 53；Perform respectively：Receive voice messaging；The voice messaging is identified, obtains image processing command； Handled and ordered according to described image, image procossing, the target image after being handled are carried out to target image.Therefore, exist In embodiment of the present invention, mobile terminal need not receive the manually operated of user and handle image, but use only by receiving The voice messaging at family, the function of image procossing can be realized, compared with prior art, this process is easier, when saving user Between, improve operating efficiency.In addition, when the sound of acquisition is multiple, it will also be directed to each sound and extract each sound top N Voice word, perform image procossing respectively, or according to the maximum sound of volume, perform image procossing.
Fig. 8 is refer to, Fig. 8 is the hardware configuration signal of the electronic equipment of execution image procossing provided in an embodiment of the present invention Figure, as shown in figure 8, the electronic equipment 70 includes：
One or more processors 71 and memory 72, in Fig. 7 by taking a processor 71 as an example.
Processor 71 can be connected with memory 72 by bus or other modes, to be connected as by bus in Fig. 8 Example.
Memory 72 is used as a kind of non-volatile computer readable storage medium storing program for executing, available for storage non-volatile software journey Sequence, non-volatile computer executable program and module, as corresponding to the image procossing in the embodiment of the present invention programmed instruction/ Module (for example, speech reception module 51, order acquisition module 52 and image processing module 53 shown in accompanying drawing 6).Processor 71 Non-volatile software program, instruction and the module being stored in by operation in memory 72, so that execute server is various Application of function and data processing, that is, realize above method embodiment image procossing.
Memory 72 can include storing program area and storage data field, wherein, storing program area can storage program area, Application program required at least one function；Storage data field can store uses created number according to the device for recommending the commodity According to etc..In addition, memory 72 can include high-speed random access memory, nonvolatile memory can also be included, such as extremely Few a disk memory, flush memory device or other non-volatile solid state memory parts.In certain embodiments, memory 72 is optional including that can pass through network connection to commodity relative to the remotely located memory of processor 71, these remote memories Recommendation apparatus.The example of above-mentioned network includes but is not limited to internet, intranet, LAN, mobile radio communication and its group Close.
One or more of modules are stored in the memory 72, when by one or more of processors 71 During execution, the image procossing in above-mentioned any means embodiment is performed, for example, performing the method and step in Fig. 1 described above 101 to step 103, the method and step 1021 in Fig. 2 to step 1023, the method and step 1021a to step 1023a in Fig. 3, figure Method and step 1031 in 4 method and step 201 in Fig. 5 to step 209, realizes the module 51-53 in Fig. 6 to step 1032, Module 51-58 in unit 521-523, unit 531-532, Fig. 7, unit 521-523, unit 531-532 function.
The said goods can perform the method that the embodiment of the present invention is provided, and possesses the corresponding functional module of execution method and has Beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to the method that the embodiment of the present invention is provided.
The electronic equipment of the embodiment of the present invention exists in a variety of forms, includes but is not limited to：Server：The service of calculating is provided Equipment, the composition of server includes processor, hard disk, internal memory, system bus etc., server and general computer architecture class Seemingly, but due to needing to provide highly reliable service, thus disposal ability, stability, reliability, security, scalability, Manageability etc. requires higher.Or other have the electronic installation of data interaction function.
The embodiments of the invention provide a kind of non-volatile computer readable storage medium storing program for executing, the non-volatile computer can Read storage medium and be stored with computer executable instructions, the computer executable instructions perform above-mentioned any means by electronic equipment Image procossing in embodiment, for example, method and step 101 in Fig. 1 described above is performed to step 103, the method in Fig. 2 Step 1021 is to step 1023, method and step 1031 in the method and step 1021a to step 1023a in Fig. 3, Fig. 4 to step Method and step 201 in 1032, Fig. 5 realizes the module 51-53 in Fig. 6, unit 521-523, unit 531- to step 209 Module 51-58 in 532, Fig. 7, unit 521-523, unit 531-532 function.
The embodiments of the invention provide a kind of computer program product, including it is stored in non-volatile computer readable storage Calculation procedure on medium, the computer program include programmed instruction, are computer-executed constantly, make when described program instructs The computer performs the image procossing in above-mentioned any means embodiment, for example, performing the method step in Fig. 1 described above Rapid 101 to step 103, the method and step 1021 in Fig. 2 to step 1023, the method and step 1021a to step 1023a in Fig. 3, To step 1032, the method and step 201 in Fig. 5 realizes the module 51- in Fig. 6 to step 209 for method and step 1031 in Fig. 4 53, unit 521-523, the module 51-58 in unit 531-532, Fig. 7, unit 521-523, unit 531-532 function.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs In some or all of module realize the purpose of this embodiment scheme.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment The mode of general hardware platform can be added by software to realize, naturally it is also possible to pass through hardware.Those of ordinary skill in the art can To understand that all or part of flow realized in above-described embodiment method is can to instruct the hard of correlation by computer program Part is completed, and described program can be stored in a computer read/write memory medium, the program is upon execution, it may include as above State the flow of the embodiment of each method.Wherein, described storage medium can be magnetic disc, CD, read-only memory (Read- Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
Embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this The equivalent structure or equivalent flow conversion that description of the invention and accompanying drawing content are made, or directly or indirectly it is used in other correlations Technical field, it is included within the scope of the present invention.

Claims (12)

  1. A kind of 1. method of image procossing, applied to terminal device, it is characterised in that including：
    Receive voice messaging；
    The voice messaging is identified, obtains image processing command；
    Handled and ordered according to described image, image procossing, the target image after being handled are carried out to target image.
  2. 2. according to the method for claim 1, it is characterised in that
    Described that the voice messaging is identified, the step of obtaining image processing command, includes：
    The voice messaging is converted into text message；
    Process object keyword and processing mode keyword are extracted from the text message；
    By keyword and the processing mode crucial phrase of dealing with objects into image processing command.
  3. 3. according to the method for claim 1, it is characterised in that
    Described that the voice messaging is identified, the step of obtaining image processing command, includes：
    According to the voice messaging and the sound bank for being preset with keyword voice, extract in the voice messaging and preset with described There is pronunciation identical word in the sound bank of keyword voice, wherein, described be preset with the sound bank of keyword voice includes Default process object keyword voice and processing mode keyword voice；
    According to the pronunciation identical word extracted, process object keyword and processing mode keyword are obtained；
    By keyword and the processing mode crucial phrase of dealing with objects into image processing command.
  4. 4. according to the method in claim 2 or 3, it is characterised in that
    Described handled according to described image is ordered, and the step of target image progress image procossing is included：
    According to the process object keyword, process object is identified from the target image；
    According to the processing mode keyword, processing is performed to the process object.
  5. 5. according to the method for claim 1, it is characterised in that
    After the step of reception voice messaging, methods described also includes：
    Judge whether only include a kind of sound in the voice messaging；
    If only including a kind of sound in the voice messaging, the voice word of the voice messaging top N is extracted；
    Judge whether the voice word includes pre-set commands word；
    If so, then voice messaging is identified into described, the step of described image processing is ordered is obtained.
  6. 6. according to the method for claim 5, it is characterised in that
    Methods described also includes：
    If the voice messaging includes muli-sounds, the voice word of each sound top N is extracted；
    Obtain the sound that the voice word includes pre-set commands word；
    Described that the voice messaging is identified, obtaining described image processing order is specially：
    The sound acquired is identified, obtains described image processing order.
  7. A kind of 7. device of image procossing, applied to terminal device, it is characterised in that including：
    Speech reception module, it is used to receive voice messaging；
    Order acquisition module, it is used to the voice messaging be identified, and obtains image processing command；
    Image processing module, it, which is used to be handled according to described image, orders, and image procossing is carried out to target image, after obtaining processing The target image.
  8. 8. device according to claim 7, it is characterised in that
    The order acquisition module includes：
    Text acquiring unit, it is used to the voice messaging being converted to text message；
    Text Feature Extraction unit, it is used to from the text message extract process object keyword and processing mode keyword；
    Order forms unit, and it is used for keyword and the processing mode crucial phrase of dealing with objects into image processing command.
  9. 9. device according to claim 7, it is characterised in that
    The order acquisition module includes：
    Word acquiring unit, it is used for according to the voice messaging and the sound bank for being preset with keyword voice, extracts described Pronunciation identical word in the sound bank of keyword voice is preset with described in voice messaging, wherein, it is described to be preset with key Default process object keyword voice and processing mode keyword voice are contained in the sound bank of word sound；
    Word extraction unit, it is used for according to the pronunciation identical word extracted, obtain process object keyword and Processing mode keyword；
    Order generation unit, it is used for keyword and the processing mode crucial phrase of dealing with objects into image processing command.
  10. 10. device according to claim 8 or claim 9, it is characterised in that
    Described image processing module includes：
    Object identification unit, it is used to, according to the process object keyword, process object is identified from the target image；
    Processing unit is performed, it is used for according to the processing mode keyword, and processing is performed to the process object.
  11. 11. device according to claim 7, it is characterised in that described device also includes：
    Sound judge module, it is used to judge in the voice messaging whether only including a kind of sound；
    First extraction module, if it is used in the voice messaging only include a kind of sound, extract the voice messaging top N Voice word；
    Voice word judge module, it is used to judge whether the voice word includes pre-set commands word；If so, then into described right Voice messaging is identified, and obtains the step of described image processing is ordered.
  12. 12. device according to claim 11, it is characterised in that
    Described device also includes：
    Second extraction module, if it, which is used for the voice messaging, includes muli-sounds, extract the voice of each sound top N Word；
    Sound screening module, it is used to obtain the sound that the voice word includes pre-set commands word；
    Described that the voice messaging is identified, obtaining described image processing order is specially：
    The sound acquired to sound screening module is identified, and obtains described image processing order.
CN201710980039.8A 2017-10-19 2017-10-19 Image processing method and device Pending CN107886947A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201710980039.8A CN107886947A (en) 2017-10-19 2017-10-19 Image processing method and device
PCT/CN2018/100212 WO2019076120A1 (en) 2017-10-19 2018-08-13 Image processing method, device, storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710980039.8A CN107886947A (en) 2017-10-19 2017-10-19 Image processing method and device

Publications (1)

Publication Number Publication Date
CN107886947A true CN107886947A (en) 2018-04-06

Family

ID=61781978

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710980039.8A Pending CN107886947A (en) 2017-10-19 2017-10-19 Image processing method and device

Country Status (2)

Country Link
CN (1) CN107886947A (en)
WO (1) WO2019076120A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019076120A1 (en) * 2017-10-19 2019-04-25 格力电器（武汉）有限公司 Image processing method, device, storage medium and electronic device
CN109977254A (en) * 2019-04-03 2019-07-05 百度在线网络技术（北京）有限公司 For obtaining the method and device of image
CN111383637A (en) * 2018-12-28 2020-07-07 上海寒武纪信息科技有限公司 Signal processing device, signal processing method and related product
CN112801083A (en) * 2021-01-29 2021-05-14 百度在线网络技术（北京）有限公司 Image recognition method, device, equipment and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110784523B (en) * 2019-10-11 2022-08-02 北京地平线机器人技术研发有限公司 Target object information pushing method and device

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1014258A3 (en) * 1998-12-23 2003-11-26 Hewlett-Packard Company, A Delaware Corporation Automatic data routing via voice command annotation
US20070198258A1 (en) * 2006-02-17 2007-08-23 Inventec Appliances Corp. Method and portable device for inputting characters by using voice recognition
CN102945671A (en) * 2012-10-31 2013-02-27 四川长虹电器股份有限公司 Voice recognition method
CN103714815A (en) * 2013-12-09 2014-04-09 何永 Voice control method and device thereof
CN105446146A (en) * 2015-11-19 2016-03-30 深圳创想未来机器人有限公司 Intelligent terminal control method based on semantic analysis, system and intelligent terminal
CN106157950A (en) * 2016-09-29 2016-11-23 合肥华凌股份有限公司 Speech control system and awakening method, Rouser and household electrical appliances, coprocessor
CN106156310A (en) * 2016-06-30 2016-11-23 努比亚技术有限公司 A kind of picture processing apparatus and method
CN106250747A (en) * 2016-08-01 2016-12-21 联想(北京)有限公司 A kind of information processing method and electronic equipment
KR101713770B1 (en) * 2015-09-18 2017-03-08 주식회사 베이리스 Voice recognition system and voice recognition method therefor
CN106782563A (en) * 2016-12-28 2017-05-31 上海百芝龙网络科技有限公司 A kind of intelligent home voice interactive system

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100238323A1 (en) * 2009-03-23 2010-09-23 Sony Ericsson Mobile Communications Ab Voice-controlled image editing
JP5146429B2 (en) * 2009-09-18 2013-02-20 コニカミノルタビジネステクノロジーズ株式会社 Image processing apparatus, speech recognition processing apparatus, control method for speech recognition processing apparatus, and computer program
KR20130016644A (en) * 2011-08-08 2013-02-18 삼성전자주식회사 Voice recognition apparatus, voice recognition server, voice recognition system and voice recognition method
TW201407538A (en) * 2012-08-05 2014-02-16 Hiti Digital Inc Image capturing device and method for image processing by voice recognition
CN105912717A (en) * 2016-04-29 2016-08-31 广东小天才科技有限公司 Image-based information searching method and device
CN107886947A (en) * 2017-10-19 2018-04-06 珠海格力电器股份有限公司 Image processing method and device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1014258A3 (en) * 1998-12-23 2003-11-26 Hewlett-Packard Company, A Delaware Corporation Automatic data routing via voice command annotation
US20070198258A1 (en) * 2006-02-17 2007-08-23 Inventec Appliances Corp. Method and portable device for inputting characters by using voice recognition
CN102945671A (en) * 2012-10-31 2013-02-27 四川长虹电器股份有限公司 Voice recognition method
CN103714815A (en) * 2013-12-09 2014-04-09 何永 Voice control method and device thereof
KR101713770B1 (en) * 2015-09-18 2017-03-08 주식회사 베이리스 Voice recognition system and voice recognition method therefor
CN105446146A (en) * 2015-11-19 2016-03-30 深圳创想未来机器人有限公司 Intelligent terminal control method based on semantic analysis, system and intelligent terminal
CN106156310A (en) * 2016-06-30 2016-11-23 努比亚技术有限公司 A kind of picture processing apparatus and method
CN106250747A (en) * 2016-08-01 2016-12-21 联想(北京)有限公司 A kind of information processing method and electronic equipment
CN106157950A (en) * 2016-09-29 2016-11-23 合肥华凌股份有限公司 Speech control system and awakening method, Rouser and household electrical appliances, coprocessor
CN106782563A (en) * 2016-12-28 2017-05-31 上海百芝龙网络科技有限公司 A kind of intelligent home voice interactive system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019076120A1 (en) * 2017-10-19 2019-04-25 格力电器（武汉）有限公司 Image processing method, device, storage medium and electronic device
CN111383637A (en) * 2018-12-28 2020-07-07 上海寒武纪信息科技有限公司 Signal processing device, signal processing method and related product
CN109977254A (en) * 2019-04-03 2019-07-05 百度在线网络技术（北京）有限公司 For obtaining the method and device of image
CN112801083A (en) * 2021-01-29 2021-05-14 百度在线网络技术（北京）有限公司 Image recognition method, device, equipment and storage medium
CN112801083B (en) * 2021-01-29 2023-08-08 百度在线网络技术（北京）有限公司 Image recognition method, device, equipment and storage medium

Also Published As

Publication number Publication date
WO2019076120A1 (en) 2019-04-25

Similar Documents

Publication Publication Date Title
CN107886947A (en) Image processing method and device
CN107239666B (en) Method and system for desensitizing medical image data
US10372950B2 (en) Identification verification using a device with embedded radio-frequency identification functionality
CN111950424B (en) Video data processing method and device, computer and readable storage medium
CN110147726A (en) Business quality detecting method and device, storage medium and electronic device
US20150102948A1 (en) Multi-layer system for symbol-space based compression of patterns
CN108447471A (en) Audio recognition method and speech recognition equipment
CN109450850A (en) Auth method, device, computer equipment and storage medium
US20170011735A1 (en) Speech recognition system and method
CN109361825A (en) Meeting summary recording method, terminal and computer storage medium
CN109074808A (en) Sound control method, control device and storage medium
CN101494690A (en) Mobile terminal and unlocking method thereof
CN108536414A (en) Method of speech processing, device and system, mobile terminal
CN110598008B (en) Method and device for detecting quality of recorded data and storage medium
CN110033027A (en) A kind of item identification method, device, terminal and readable storage medium storing program for executing
CN114419363A (en) Target classification model training method and device based on label-free sample data
CN112612877A (en) Multi-type message intelligent reply method, device, computer equipment and storage medium
CN107910006A (en) Audio recognition method, device and multiple source speech differentiation identifying system
CN113051384A (en) User portrait extraction method based on conversation and related device
CN108133209A (en) Target area searching method and its device in a kind of text identification
CN115222047A (en) Model training method, device, equipment and storage medium
US11227624B2 (en) Method and system using successive differences of speech signals for emotion identification
US9443139B1 (en) Methods and apparatus for identifying labels and/or information associated with a label and/or using identified information
CN106775810A (en) The wiring method and device of configuration file in distributed file system
CN106294659A (en) Question searching method and device based on intelligent terminal

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180406

RJ01 Rejection of invention patent application after publication