WO2020037534A1 - 一种图像处理方法、装置以及计算机存储介质 - Google Patents

一种图像处理方法、装置以及计算机存储介质 Download PDF

Info

Publication number
WO2020037534A1
WO2020037534A1 PCT/CN2018/101695 CN2018101695W WO2020037534A1 WO 2020037534 A1 WO2020037534 A1 WO 2020037534A1 CN 2018101695 W CN2018101695 W CN 2018101695W WO 2020037534 A1 WO2020037534 A1 WO 2020037534A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
image
information
processed
keywords
Prior art date
Application number
PCT/CN2018/101695
Other languages
English (en)
French (fr)
Inventor
谢琴
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
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 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to CN201880096298.7A priority Critical patent/CN112534422A/zh
Priority to PCT/CN2018/101695 priority patent/WO2020037534A1/zh
Publication of WO2020037534A1 publication Critical patent/WO2020037534A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Definitions

  • the embodiments of the present application relate to the technical field of information processing, and in particular, to an image processing method, device, and computer storage medium.
  • the main purpose of the embodiments of the present application is to provide an image processing method, device, and computer storage medium, which not only improves the comprehensiveness of photographic shorthand information, but also solves the problem of redundant and meaningless information search results. Further improve the accuracy and intelligence of information collection.
  • an embodiment of the present application provides an image processing method, where the method includes:
  • the search result is recorded in photographic shorthand information corresponding to the image to be processed.
  • an embodiment of the present application provides an image processing apparatus, where the image processing apparatus includes: a first acquisition section, a recognition section, a second acquisition section, a third acquisition section, and a recording section;
  • the first obtaining part is configured to obtain an image to be processed based on a shorthand application
  • the recognition section is configured to perform image recognition on the image to be processed to obtain one or more recognized objects
  • the second obtaining part is configured to obtain a keyword of the image to be processed according to the obtained identified object
  • the third obtaining part is configured to obtain a search result matching the keyword according to the keyword
  • the recording section is configured to record the search result in photographic shorthand information corresponding to the image to be processed.
  • an embodiment of the present application provides an image processing apparatus, where the image processing apparatus includes: a memory and a processor;
  • the memory is configured to store a computer program capable of running on the processor
  • the processor is configured to execute the steps of the method according to the first aspect when the computer program is run.
  • an embodiment of the present application provides a computer storage medium that stores an image processing program, and when the image processing program is executed by at least one processor, the steps of the method according to the first aspect are implemented.
  • an embodiment of the present application provides a mobile terminal installed with a shorthand application, and the mobile terminal includes at least the image processing apparatus according to the second aspect or the third aspect.
  • An embodiment of the present application provides an image processing method, device, and computer storage medium.
  • the method is applied to a mobile terminal having a shorthand function.
  • the method includes: obtaining a to-be-processed image based on a shorthand application program; Image recognition to obtain one or more identified objects; to obtain keywords of the image to be processed according to the obtained identified objects; to obtain search results matching the keywords according to the keywords Record the search result in the photographic shorthand information corresponding to the image to be processed; thus not only improving the comprehensiveness of the photographic shorthand information, but also solving the problem of redundant and meaningless information search results, further improving the information The accuracy and intelligence of the collection.
  • FIG. 1 is a schematic diagram of a hardware structure of a mobile terminal according to an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a communication network system according to an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of an image processing method according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of selecting a shorthand information recording mode according to an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of shooting an image to be processed according to an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a second search information ranking according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of another sort of second search information according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a search result display interface according to an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of marking an image to be processed according to an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 15 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 16 is a schematic diagram of a specific hardware structure of an image processing apparatus according to an embodiment of the present application.
  • the terminal can be implemented in various forms.
  • the terminals described in this application may include devices such as smartphones, tablets, laptops, PDAs, Personal Digital Assistants (PDAs), Portable Media Players (PMPs), and wireless handheld devices.
  • PDAs Personal Digital Assistants
  • PMPs Portable Media Players
  • wireless handheld devices such as smartphones, tablets, laptops, PDAs, Personal Digital Assistants (PDAs), Portable Media Players (PMPs), and wireless handheld devices.
  • Navigation devices wearable devices, and other mobile terminals, as well as fixed terminals such as digital TVs and desktop computers.
  • a mobile terminal will be taken as an example for description.
  • the configuration according to the embodiment of the present application can also be applied to a fixed type terminal.
  • FIG. 1 shows a schematic diagram of a hardware structure of a mobile terminal for implementing various embodiments of the present application.
  • the mobile terminal 10 may include: an RF (Radio Frequency) unit 101 and an A / V ( (Audio / video) input unit 102, display unit 103, user input unit 104, sensor 105, camera 106, memory 107, processor 108, and power supply 109.
  • RF Radio Frequency
  • a / V (Audio / video) input unit 102
  • display unit 103 user input unit 104
  • sensor 105 sensor
  • camera 106 memory 107
  • processor 108 processor 108
  • the radio frequency unit 101 can be used for receiving and sending signals during the process of transmitting and receiving information. Specifically, the downlink information of the base station is received and processed by the processor 110; in addition, the uplink data is sent to the base station.
  • the radio frequency unit 101 includes, but is not limited to, an antenna, at least one amplifier, a coupler, a low noise amplifier, a duplexer, and the like.
  • the radio frequency unit 101 may also communicate with a network device or other devices through wireless communication.
  • the A / V input unit 102 is used to receive audio or video signals.
  • the A / V input unit 102 may include a graphics processing unit (Graphics Processing Unit, GPU) 1021 and a microphone 1022.
  • the graphics processor 1021 pairs a still picture obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode or The video image data is processed.
  • the processed image frames may be displayed on the display unit 103.
  • the image frames processed by the graphics processor 1021 may be stored in the memory 107 (or other storage medium) or transmitted via the radio frequency unit 101.
  • the microphone 1022 can receive sound (audio data) via the microphone 1022 in a phone call mode, a recording mode, a voice recognition mode, and the like, and can process such sound into audio data.
  • the microphone 1022 may implement various types of noise cancellation (or suppression) algorithms to remove (or suppress) noise or interference generated during the process of receiving and transmitting audio signals.
  • the display unit 103 is configured to display information input by the user or information provided to the user.
  • the display unit 103 may include a display panel 1031, and the display panel 1031 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • the user input unit 104 may be configured to receive inputted numeric or character information, and generate key signal inputs related to user settings and function control of the mobile terminal.
  • the user input unit 104 may include a touch panel 1041 and other input devices 1042.
  • the touch panel 1041 also referred to as a touch screen, may collect a user's touch operations on or near it, and according to a preset program, Drive corresponding connection devices;
  • other input devices 1042 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume + button, volume-button, power button, etc.), trackball, mouse, joystick, etc. , Specifically not limited here.
  • the touch panel 1041 may cover the display panel 1031.
  • the touch panel 1041 detects a touch operation on or near the touch panel 1041, the touch panel 1041 transmits the touch operation to the processor 108 to determine the type of the touch event.
  • the type provides corresponding visual output on the display panel 1051.
  • the touch panel 1041 and the display panel 1031 are implemented as two independent components to implement input and output functions of the mobile terminal, in some embodiments, the touch panel 1041 and the display panel 1031 may be integrated.
  • the implementation of the input and output functions of the mobile terminal is not specifically limited here.
  • the mobile terminal 10 further includes at least one sensor 105, such as a light sensor, an image sensor, a motion sensor, and other sensors.
  • the light sensor is mainly composed of light-sensitive elements, and the brightness of the display panel 1031 can be adjusted according to the brightness of the ambient light.
  • the image sensor is an important part of a digital camera. The image is converted into an electric signal in a proportional relationship with the light image.
  • the motion sensor is a component that changes non-electricity (such as speed and pressure) into electric power. According to the non-electricity converted, the motion sensor can include a pressure sensor and a speed.
  • fingerprint sensors, iris sensors, molecular sensors, gyroscopes, infrared sensors, and other sensors that can be configured on the mobile terminal 10 are not described herein.
  • the camera 106 is a video input device, also known as a computer camera, electronic eye, etc.
  • the camera 106 generally has basic functions such as video recording / dissemination and still image capture. It is a photosensitive component in the camera after collecting images through the lens The circuit and the control component process the captured image and convert it into a digital signal, and then store it in the memory 107.
  • the camera 106 may include a front camera, a rear camera, and the like.
  • the memory 107 can be used to store software programs and various data.
  • the memory 107 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, at least one application required by a function (such as a recording function and an image playback function), etc .; the storage data area may store data according to a mobile terminal. Use the created data (such as audio data and image data).
  • the processor 108 is a control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.
  • the processor 108 runs or executes software programs and / or modules stored in the memory 107 and calls data stored in the memory 107. , Perform various functions of the mobile terminal and process data, so as to monitor the mobile terminal as a whole.
  • the processor 108 may include one or more processing units; preferably, the processor 108 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and an application program, etc.
  • the processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 108.
  • the mobile terminal 10 may further include a power source 109 (such as a battery) for supplying power to various components.
  • a power source 109 such as a battery
  • the power source 109 may be logically connected to the processor 108 through a power management system, so as to manage charging, discharging, and power consumption management through the power management system. And other functions.
  • the mobile terminal 10 may further include a Bluetooth module, a WiFi module, and the like, and details are not described herein again.
  • FIG. 2 shows a schematic architecture diagram of a communication network system according to an embodiment of the present application.
  • the communication network system 20 includes a mobile terminal 201 and a server 202, and the mobile terminal 201 and the server 202 are located in a communication network 203.
  • the mobile terminal 201 and the server 202 exchange information through a communication network 203.
  • the mobile terminal 201 may be the mobile terminal 10 described above, the server 202 may be a database, a web server, a data server, a web server, etc., and the communication network 203 may be a wireless network or Wired networks, such as Long Term Evolution (LTE) networks, Global System of Mobile (GSM) networks, Code Division Multiple Access 2000 (CDMA2000) networks, and Broadband Code Division Multiple Access (Wide Band, Code, Division, Multiple Access, WCDMA) networks and new communication networks in the future are not limited here.
  • LTE Long Term Evolution
  • GSM Global System of Mobile
  • CDMA2000 Code Division Multiple Access 2000
  • WCDMA Broadband Code Division Multiple Access
  • the existing image is used to extract the text from the image, and then the extracted text is copied and pasted into the notepad for saving, or the extracted text is copied and pasted into the search engine for searching.
  • the whole process is tedious, and The search results obtained are redundant, and there are also department
  • the problem of meaningless search results reduces the accuracy and intelligence of information collection.
  • the embodiment of the present application based on the shorthand application, in order to ensure the comprehensiveness of the shorthand information and improve the accuracy and intelligence of information collection, the following The embodiments of the present application will be described in detail with reference to the drawings.
  • the method may include:
  • S302 Perform image recognition on the image to be processed to obtain one or more recognized objects
  • the technical solution shown in FIG. 3 is mainly applied to a mobile terminal having a shorthand function.
  • the mobile terminal needs to quickly record the inspiration information; first, the entry of the shorthand application program needs to be called, and the shorthand
  • the camera function in the application can obtain images to be processed.
  • one or more recognized objects can be obtained by performing image recognition on the to-be-processed image; according to the obtained identified object, keywords of the to-be-processed image are obtained; The keywords are used to obtain search results matching the keywords; the search results are recorded in photographic shorthand information corresponding to the image to be processed; thereby not only improving the comprehensiveness of photographic shorthand information, but also solving It solves the problem of redundant and meaningless information search results, and further improves the accuracy and intelligence of information collection.
  • the obtaining a to-be-processed image based on a shorthand application includes:
  • the selection instruction being used to instruct selection of a photographic shorthand mode
  • the user when the user needs to record inspiration or temporary ideas, the user needs to open the shorthand application; in general, the user can perform a touch operation on the touch panel of the mobile terminal, or by pressing a physical button of the mobile terminal (Such as the volume + button and power button combination) to perform a pressing operation, or to open a shorthand application by performing a voice operation on the mobile terminal's voice assistant (such as "I want to record inspiration", "Help me quickly record an idea").
  • a touch operation on the touch panel of the mobile terminal or by pressing a physical button of the mobile terminal (Such as the volume + button and power button combination) to perform a pressing operation, or to open a shorthand application by performing a voice operation on the mobile terminal's voice assistant (such as "I want to record inspiration", "Help me quickly record an idea").
  • the mobile terminal receives the shorthand opening instruction to open the shorthand application; then receives a selection instruction in the shorthand application program interface to select the recording mode of shorthand information, and shorthand information can be written by shorthand, voice shorthand, and taking shorthand
  • Three modes are used for recording; refer to FIG. 4, which shows a structure diagram of selecting a shorthand information recording mode according to an embodiment of the present application; as shown in FIG. 4, part 401 represents a text shorthand mode, and part 402 represents a voice shorthand mode. Part 403 indicates the shorthand mode for taking pictures; when the user When the 403 part is selected, it is indicated that the shorthand information is recorded in a photo shorthand mode.
  • the mobile terminal can obtain a to-be-processed image by using a photographing instruction generated by a photographing operation input by the user; see FIG. 5, which illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • FIG. 5 illustrates an embodiment of the present application.
  • Part 501 indicates exiting the shorthand mode for photographing
  • part 502 indicates that Part 503 represents the interchange of the rear camera and the front camera; when
  • the method before performing image recognition on the image to be processed to obtain one or more recognized objects, the method further includes:
  • Preprocessing the image to be processed according to a preset processing strategy Preprocessing the image to be processed according to a preset processing strategy.
  • the preset processing strategy refers to a method of preprocessing an image to be processed; in order to obtain a high-definition and high-quality image to be processed, linear correction, noise reduction, removal of dead pixels, interpolation, and Any one of the methods such as white balance is used to preprocess the image to be processed.
  • the processing of any one of the methods of linear correction, noise reduction, dead pixel removal, interpolation, and white balance can make the image to be processed change. It is clearer and more conducive to the recognition of the identified object in the image to be processed subsequently.
  • the performing image recognition on the image to be processed to obtain one or more recognized objects includes:
  • Performing image recognition on the image to be processed, and obtaining the identified object according to the recognition result includes at least one of the following: object information, scenery information, person information, movie information, brand information, and text information .
  • the image to be processed includes one or more types of recognized objects among objects, landscapes, people, movies, brands, and text.
  • the identified object in the image to be processed can be identified through Optical Character Recognition (OCR) technology, Baidu image recognition technology, or even other image recognition software, which is not specifically limited in the embodiment of the present application.
  • OCR Optical Character Recognition
  • Baidu image recognition technology or even other image recognition software, which is not specifically limited in the embodiment of the present application.
  • the to-be-processed image contains a person's face
  • the person information in the to-be-processed image can also be recognized by face recognition technology
  • the to-be-processed image contains text, it can also be recognized by other character recognition methods Text information in the image to be processed. For example, taking the to-be-processed image shown in part 504 in FIG.
  • the OCR technology can be used to identify from the to-be-processed image the character information shown in part 504-1 is "Zhang San", part 504-2 The brand information shown is “a certain treasure”, and the text information shown in section 504-3 is "a certain treasure spokesperson Zhang San”. Therefore, the identified objects identified in the image to be processed shown in section 504 include: “Zhang Three ",” a certain treasure "and” a certain treasure spokesperson Zhang San ".
  • the keyword extraction algorithm can be PageRank algorithm, TextRank algorithm, LDA algorithm, TFIDF algorithm, etc .;
  • the identified object is searched and matched with a preset keyword database, and the successfully identified identified object is used as a keyword according to the matching result.
  • the preset keyword database is based on a plurality of keywords issued by the received server in advance. Established; here, the manner of obtaining keywords is not specifically limited in the embodiment of the present application.
  • the identified identified objects include: “Zhang San”, “A certain treasure” and “A certain treasure spokesperson Zhang San”. According to these To identify the objects, the mobile terminal performs query matching on the identified objects with a preset keyword database, and uses the successfully matched identified objects as keywords according to the matching result. For example, the obtained keywords include “Zhang San”, “Spokesperson” And "some treasure”.
  • search results matching the keywords include:
  • second search information corresponding to the keywords that have been successfully matched based on the matching result; wherein the second search information is the first search information whose degree of matching with the keywords is not less than a preset matching threshold;
  • the second search information that is ranked a predetermined number ahead is determined as the search result of the keyword.
  • first search information or the second search information generally includes a search information title, that is, there is a corresponding relationship between the search information title and the search information.
  • Match keywords with the first search information in the preset information database that is, match keywords with the first search information title in the first search information, and between different first search information titles and keywords Has different matching degrees.
  • the degree of matching is considered to be 100%; if the field in the title of the first search information is exactly the same as the keyword, the degree of matching is considered to be 50%;
  • the degree can also be measured by the text similarity between the title of the first search information and the keywords; in the embodiment of the present application, a suitable matching method can be selected according to actual needs, which is not specifically limited in the application embodiment.
  • the second search information is sorted according to the degree of matching. At this time, a predetermined number of second search information that is ranked higher is selected as a keyword. Search results; where the predetermined number is determined according to actual application requirements, and the predetermined number may be one, five, or ten, which is not specifically limited in the embodiment of the present application.
  • the keywords obtained by the mobile terminal include "Zhang San”, “Spokesperson", and "some treasure”.
  • the first search information is matched in the first search information.
  • the mobile terminal can obtain the second search information that is successfully matched from the pre-stored information.
  • the second search information title can be used to Instead of sorting and displaying the second search information, the user can view the details of each search information by further clicking operations; see FIG. 6, which shows a structure of a second search information ranking provided by an embodiment of the present application. Schematic diagram; as shown in FIG.
  • the ranking results of the second search information include "Zhang San captured another generation of spokespersons into a certain treasure spokesperson", "Some Bao spokespersons replaced with Li Si and Zhang San”, “Zhang San spokesperson a treasure”, “Li Si and Zhang Sanmoubao launched new male and female spokespersons”, “Zhang San held a Bao full-frame micro-single shot advertisement” and "A Zhangbao's micro-single shot” released in advance "and so on.
  • the method further includes:
  • the preset information database is established.
  • the mobile terminal receives a search instruction containing the keyword, generates a search request according to the search instruction, and then sends the search request to the server ;
  • the server will respond to the search request, and the server determines the first search information to be issued; then the server returns these first search information to the mobile terminal, and the mobile terminal will
  • the first search information is used to establish a preset information database.
  • the first search information includes the first search information title, that is, the preset information database also includes the correspondence between the first search information title and the first search information. .
  • the second search information can be sorted according to the degree of matching, in addition to the user's personalized needs, for different users.
  • the ranking is predetermined according to the ranking result
  • the method further includes:
  • the ranking result of the second search information is adjusted.
  • the user log mainly contains the content of historical search records such as user information, time, address, search keywords, search results, and corresponding search times; for example, when a user searches for any keyword in a browser or other applications
  • historical search records are also generated in the corresponding user logs; deep learning is performed on the user's historical search records, such as the Convolutional Neural Network (CNN) algorithm
  • CNN Convolutional Neural Network
  • the historical search records of training are used as training samples to obtain the auxiliary search model; the ranking of the second search information is adjusted according to the auxiliary search model, and the search information with high user attention is ranked first, so that the final search can be obtained
  • the result is high user attention and search information that is of interest to the user.
  • the cut with "Zhang San” can be higher Search information adjusted to the forefront, such as “Zhang San captured another generation of spokesperson for a certain treasure”, “Zhang San held a treasure full-frame micro single shot advertisement” and "a treasure micro single that was released in advance by Zhang San”
  • the adjusted ranking results include “Zhang San has won another generation of spokesperson for a certain treasure”, “Zhang San holds a treasure full-frame micro-single shot advertisement”, “A treasure micro-single issued by Zhang San in advance”, “ “Zhang San endorses a certain treasure”, “Li Si and Zhang Sanmou Bao use new male and female spokespersons” and "Some Bao endorsements are replaced by Li Si and Zhang San", as shown in FIG.
  • search results can be search content displayed in text form, network address information corresponding to the search content, or even application interface information corresponding to the search content. Implementation in this application In the example, this is not specifically limited.
  • the method further includes:
  • the search result may be displayed in a current display interface of the shorthand application.
  • the current display of the shorthand application Interface which can display the search result according to a preset card format, can also display in a browse web page format, and can also display according to an application interface; see FIG.
  • FIG. 8 which shows a search result provided by an embodiment of the present application Schematic diagram of the display interface; where the content shown in Figure 8 is the search result, this part includes the search information title (such as 801) and search information content (such as 802) displayed in text form; here, the search results
  • the search information title and search information content displayed in text form it may also include network address information corresponding to the search information content and application interface information corresponding to the search information content; when the search results correspond to the search information content When the network address information, you can directly call the browser to load the network address for display; when searching When the result is the application interface information corresponding to the search information content, the corresponding application program can be started, and then the search result is displayed through the application program.
  • the determined keywords may also be used as tags to mark the images to be processed.
  • the method further includes:
  • the keywords can be labeled as tags of the image to be processed, and the labeled tags can be recorded as part of the shorthand information for photographing.
  • the image to be processed shown in part 504 in FIG. 5 is still taken as an example.
  • the keywords obtained include “Zhang San”, “Spokesperson”, and “a certain treasure”. These keywords are used as tags for the images to be processed.
  • FIG. 9 shows a schematic structural diagram of marking an image to be processed according to an embodiment of the present application. As shown in FIG. 9, part 901 represents tag information, part 902 represents an image to be processed, and part 903 represents “repetition”.
  • “Shot” button, part 904 means “save” button; among them, the tag information in part 901 is browsed in a horizontal sliding mode, and the content of each tag marked does not exceed 200 words, and the tag information in part 901 automatically includes keywords in addition to the mobile terminal.
  • tags users can also add tags manually; when the user is not satisfied with the image to be processed shown in section 902, the user can click the "Retake” button shown in section 903 to reacquire the image to be processed; finally The user clicks the "Save” button shown in part 904, which can cause the mobile terminal to record these marks and images to be processed as shorthand information for taking pictures. Based on these labels help users deal with processing images for viewing and sorting.
  • the recording the search result in photographic shorthand information corresponding to the image to be processed includes:
  • the search result is recorded in the photographic shorthand information as an attachment.
  • the search result display interface shown in FIG. 8 is still taken as an example.
  • the above display page includes part 803
  • This embodiment provides an image processing method applied to a mobile terminal having a shorthand function.
  • the method includes: obtaining a to-be-processed image based on a shorthand application; performing image recognition on the to-be-processed image to obtain one or more An identified object; obtaining keywords of the image to be processed according to the obtained identified object; obtaining search results matching the keywords according to the keywords; and recording the search results in
  • the photographic shorthand information corresponding to the image to be processed not only improves the comprehensiveness of the photographic shorthand information, but also solves the problem of redundant and meaningless information search results, and further improves the accuracy and intelligence of information collection.
  • FIG. 10 it illustrates a composition of an image processing apparatus 100 provided by an embodiment of the present application.
  • the image processing apparatus 100 may include: a first obtaining section 1001 and a identifying section 1002. , Second acquisition section 1003, third acquisition section 1004, and recording section 1005;
  • the first acquiring section 1001 is configured to acquire an image to be processed based on a shorthand application
  • the recognition section 1002 is configured to perform image recognition on the image to be processed to obtain one or more recognized objects;
  • the second acquiring section 1003 is configured to acquire keywords of the image to be processed according to the obtained identified object
  • the third obtaining section 1004 is configured to obtain a search result matching the keyword according to the keyword;
  • the recording section 1005 is configured to record the search result in photographic shorthand information corresponding to the image to be processed.
  • the first obtaining part 1001 is configured as:
  • the selection instruction being used to instruct selection of a photographic shorthand mode
  • the image processing apparatus 100 further includes a preprocessing section 1006 configured to:
  • Preprocessing the image to be processed according to a preset processing strategy Preprocessing the image to be processed according to a preset processing strategy.
  • the identification part 1002 is configured as:
  • Performing image recognition on the image to be processed, and obtaining the identified object according to the recognition result includes at least one of the following: object information, scenery information, person information, movie information, brand information, and text information .
  • the third obtaining part 1004 is configured as:
  • second search information corresponding to the keywords that have been successfully matched based on the matching result; wherein the second search information is the first search information whose degree of matching with the keywords is not less than a preset matching threshold;
  • the second search information that is ranked a predetermined number ahead is determined as the search result of the keyword.
  • the image processing apparatus 100 further includes a establishing section 1007 configured to:
  • the preset information database is established.
  • the image processing apparatus 100 further includes an adjustment section 1008 configured to:
  • the ranking result of the second search information is adjusted.
  • the image processing apparatus 100 further includes a display portion 1009 configured to:
  • the image processing apparatus 100 further includes a marking portion 1010 configured to:
  • the recording section 1005 is configured as:
  • the search result is recorded in the shorthand information as an attachment.
  • the “part” may be a part of a circuit, a part of a processor, a part of a program or software, etc., of course, it may be a unit, a module, or a non-modular.
  • each component in this embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above integrated unit may be implemented in the form of hardware or in the form of software functional modules.
  • the integrated unit is implemented in the form of a software functional module and is not sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of this embodiment is essentially or It is said that a part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium and includes several instructions for making a computer device (can It is a personal computer, a server, or a network device) or a processor (processor) to perform all or part of the steps of the method described in this embodiment.
  • the foregoing storage media include: U disks, mobile hard disks, read only memories (ROM, Read Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.
  • this embodiment provides a computer storage medium that stores an image processing program, and when the image processing program is executed by at least one processor, the image processing program in the technical solution shown in FIG. 3 is implemented. Method steps.
  • FIG. 16 shows a specific hardware structure of the image processing apparatus 100 provided in the embodiment of the present application, which may include: a network interface 1601, a memory 1602, and a processor 1603;
  • the various components are coupled together by a bus system 1604.
  • the bus system 1604 is used to implement connection and communication between these components.
  • the bus system 1604 includes a power bus, a control bus, and a status signal bus in addition to the data bus.
  • various buses are labeled as the bus system 1604 in FIG. 16.
  • the network interface 1601 is used to receive and send signals during the process of transmitting and receiving information with other external network elements;
  • a memory 1602 configured to store a computer program capable of running on the processor 1603;
  • the processor 1603 is configured to, when running the computer program, execute:
  • the search result is recorded in photographic shorthand information corresponding to the image to be processed.
  • the memory 1602 in the embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), and an electronic memory. Erase programmable read-only memory (EPROM, EEPROM) or flash memory.
  • the volatile memory may be Random Access Memory (RAM), which is used as an external cache.
  • RAM Static Random Access Memory
  • DRAM Dynamic Random Access Memory
  • Synchronous Dynamic Random Access Memory Synchronous Dynamic Random Access Memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM DDRSDRAM
  • enhanced SDRAM ESDRAM
  • synchronous connection dynamic random access memory Synchronous DRAM, SLDRAM
  • Direct RAMbus RAM Direct RAMbus RAM, DRRAM
  • the memory 1602 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
  • the processor 1603 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by using hardware integrated logic circuits or instructions in the form of software in the processor 1603.
  • the above processor 1603 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA), or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware decoding processor, or may be executed and completed by using a combination of hardware and software modules in the decoding processor.
  • the software module may be located in a mature storage medium such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, and the like.
  • the storage medium is located in the memory 1602, and the processor 1603 reads the information in the memory 1602 and completes the steps of the foregoing method in combination with its hardware.
  • the embodiments described herein may be implemented by hardware, software, firmware, middleware, microcode, or a combination thereof.
  • the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSP), digital signal processing devices (DSPD), programmable Logic device (Programmable Logic Device, PLD), Field Programmable Gate Array (FPGA), general purpose processor, controller, microcontroller, microprocessor, other for performing the functions described in this application Electronic unit or combination thereof.
  • ASICs application-specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable Logic Device
  • FPGA Field Programmable Gate Array
  • controller microcontroller
  • microprocessor other for performing the functions described in this application Electronic unit or combination thereof.
  • the techniques described herein can be implemented through modules (e.g., procedures, functions, etc.) that perform the functions described herein.
  • Software codes may be stored in a memory and executed by a processor.
  • the memory may be implemented in the processor or external to the processor.
  • the processor 1603 is further configured to execute the steps of the image processing method in the technical solution shown in FIG. 3 when the computer program is run.
  • an embodiment of the present application further provides a mobile terminal, wherein the mobile terminal is installed with a shorthand application, and the mobile terminal includes at least the image processing apparatus 100 as described above.
  • an image to be processed is acquired based on a shorthand application; image recognition is performed on the image to be processed to obtain one or more identified objects; and the object to be processed is acquired according to the obtained identified objects.

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种图像处理方法、装置及计算机存储介质，该方法应用于具有速记功能的移动终端，该方法包括：基于速记应用程序，获取待处理图像（S301）；对所述待处理图像进行图像识别，得到一个或多个被识别对象（S302）；根据所述得到的所述被识别对象，获取所述待处理图像的关键词（S303）；根据所述关键词，获取与所述关键词相匹配的搜索结果（S304）；将所述搜索结果记录于所述待处理图像对应的拍照速记信息中（S305）；该方法完善了拍照速记信息的全面性，提高了信息搜集的准确性和智能性。

Description

一种图像处理方法、装置以及计算机存储介质 技术领域
本申请实施例涉及信息处理的技术领域，尤其涉及一种图像处理方法、装置以及计算机存储介质。
背景技术
随着科学技术的快速发展，人们的生活节奏和工作节奏越来越快，日常需要处理的事情也越来越多。通过便签存储信息是当前一种常用的信息管理方式，用户可以通过便签工具在终端上设置多个便签，分别在每个便签的信息展示页面输入详细信息，后续即可在信息展示页面中查看该详细信息。
但是，现有的便签工具功能还不够完善，尤其是在拍照场景中的应用，不能满足用户的使用需求。
发明内容
有鉴于此，本申请实施例的主要目的在于提供一种图像处理方法、装置以及计算机存储介质，不仅完善了拍照速记信息的全面性，而且还解决了信息搜索结果冗余且无意义的问题，进一步提高了信息搜集的准确性和智能性。
为达到上述目的，本申请实施例的技术方案可以如下实现：
第一方面，本申请实施例提供了一种图像处理方法，所述方法包括：
基于速记应用程序，获取待处理图像；
对所述待处理图像进行图像识别，得到一个或多个被识别对象；
根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
根据所述关键词，获取与所述关键词相匹配的搜索结果；
将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
第二方面，本申请实施例提供了一种图像处理装置，所述图像处理装置包括：第一获取部分、识别部分、第二获取部分、第三获取部分和记录部分；
所述第一获取部分，配置为基于速记应用程序，获取待处理图像；
所述识别部分，配置为对所述待处理图像进行图像识别，得到一个或多个被识别对象；
所述第二获取部分，配置为根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
所述第三获取部分，配置为根据所述关键词，获取与所述关键词相匹配的搜索结果；
所述记录部分，配置为将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
第三方面，本申请实施例提供了一种图像处理装置，所述图像处理装置包括：存储器和处理器；
所述存储器，用于存储能够在所述处理器上运行的计算机程序；
所述处理器，用于在运行所述计算机程序时，执行第一方面所述的方法的步骤。
第四方面，本申请实施例提供了一种计算机存储介质，所述计算机存储介质存储有图像处理程序，所述图像处理程序被至少一个处理器执行时实现第一方面所述的方法的步骤。
第五方面，本申请实施例提供了一种移动终端，所述移动终端安装有速记应用程序，所述移动终端至少包括如第二方面或者第三方面所述的图像处理装置。
本申请实施例提供了一种图像处理方法、装置及计算机存储介质，该方法应用于具有速记功能的移动终端，该方法包括：基于速记应用程序，获取待处理图像；对所述待处理图像进行图像识别，得到一个或多个被识别对象；根据所述得到的所述被识别对象，获取所述待处理图像的关键词；根据所述关键词，获取与所述关键词相匹配的搜索结果；将所述搜索结果记录于所述待处理图像对应的拍照速记信息中；从而不仅完善了拍照速记信息的全面性，而且还解决了信息搜索结果冗余且无意义的问题，进一步提高了信息搜集的准确性和智能性。
附图说明
图1为本申请实施例提供的一种移动终端的硬件结构示意图；
图2为本申请实施例提供的一种通信网络系统的架构示意图；
图3为本申请实施例提供的一种图像处理方法的流程示意图；
图4为本申请实施例提供的一种选择速记信息记录模式的结构示意图；
图5为本申请实施例提供的一种拍摄待处理图像的结构示意图；
图6为本申请实施例提供的一种第二搜索信息排序的结构示意图；
图7为本申请实施例提供的另一种第二搜索信息排序的结构示意图；
图8为本申请实施例提供的一种搜索结果显示界面的结构示意图；
图9为本申请实施例提供的一种标记待处理图像的结构示意图；
图10为本申请实施例提供的一种图像处理装置的组成结构示意图；
图11为本申请实施例提供的另一种图像处理装置的组成结构示意图；
图12为本申请实施例提供的又一种图像处理装置的组成结构示意图；
图13为本申请实施例提供的再一种图像处理装置的组成结构示意图；
图14为本申请实施例提供的再一种图像处理装置的组成结构示意图；
图15为本申请实施例提供的再一种图像处理装置的组成结构示意图；
图16为本申请实施例提供的一种图像处理装置的具体硬件结构示意图。
具体实施方式
为了能够更加详尽地了解本申请实施例的特点与技术内容，下面结合附图对本申请实施例的实现进行详细阐述，所附附图仅供参考说明之用，并非用来限定本申请实施例。
在后续的描述中，使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本申请的说明，其本身没有特定的意义。因此，“模块”、“部件”或“单元”可以混合地使用。
终端可以以各种形式来实施。例如，本申请中描述的终端可以包括诸如智能手机、平板电脑、笔记本电脑、掌上电脑、个人数字助理(Personal Digital Assistant，PDA)、便捷式媒体播放器(Portable Media Player，PMP)、无线手持设备、导航装置、可穿戴设备等移动终端，以及诸如数字TV、台式计算机等固定终端。
后续描述中将以移动终端为例进行说明，本领域技术人员将理解的是，除了特别用于移动目的的元件之外，根据本申请的实施方式的构造也能够应用于固定类型的终端。
示例性的，参见图1，其示出了为实现本申请各个实施例的一种移动终端的硬件结构示意图，该移动终端10可以包括：RF(Radio Frequency，射频)单元101、A/V(音频/视频)输入单元102、显示单元103、用户输入单元104、传感器105、摄像头106、存储器107、处理器108、以及电源109等部件。本领域技术人员可以理解，图1中示出的移动终端结构并不构成对移动终端的限定，移动终端可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
下面结合图1对移动终端的各个部件进行具体的介绍：
射频单元101可用于收发信息过程中，信号的接收和发送。具体的，将基站的下行信息接收后，给处理器110处理；另外，将上行数据发送给基站。通常，射频单元101包括但不限于天线、至少一个放大器、耦合器、低噪声放大器、双工器等。射频单元101还可以通过无线通信与网络设备或者其他设备通信。
A/V输入单元102用于接收音频或视频信号。A/V输入单元102可以包括图形处理器(Graphics Processing Unit，GPU)1021和麦克风1022，图形处理器1021对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。处理后的图像帧可以显示在显示单元103上。经图形处理器1021处理后的图像帧可以存储在存储器107(或其它存储介质)中或者经由射频单元101进行发送。麦克风 1022可以在电话通话模式、记录模式、语音识别模式等等运行模式中经由麦克风1022接收声音(音频数据)，并且能够将这样的声音处理为音频数据。麦克风1022可以实施各种类型的噪声消除(或抑制)算法以消除(或抑制)在接收和发送音频信号的过程中产生的噪声或者干扰。
显示单元103用于显示由用户输入的信息或提供给用户的信息。显示单元103可包括显示面板1031，可以采用液晶显示器(Liquid Crystal Display，LCD)、有机发光二极管(Organic Light-Emitting Diode，OLED)等形式来配置显示面板1031。
用户输入单元104可用于接收输入的数字或字符信息，以及产生与移动终端的用户设置以及功能控制有关的键信号输入。具体地，用户输入单元104可包括触控面板1041以及其他输入设备1042；其中，触控面板1041，也称为触摸屏，可收集用户在其上或附近的触摸操作，并根据预先设定的程式驱动相应的连接装置；其他输入设备1042可以包括但不限于物理键盘、功能键(比如音量+按键、音量-按键、电源按键等)、轨迹球、鼠标、操作杆等中的一种或多种，具体此处不做限定。
进一步的，触控面板1041可覆盖显示面板1031，当触控面板1041检测到在其上或附近的触摸操作后，传送给处理器108以确定触摸事件的类型，随后处理器108根据触摸事件的类型在显示面板1051上提供相应的视觉输出。虽然在图1中，触控面板1041与显示面板1031是作为两个独立的部件来实现移动终端的输入和输出功能，但是在某些实施例中，可以将触控面板1041与显示面板1031集成而实现移动终端的输入和输出功能，具体此处不做限定。
移动终端10还包括至少一种传感器105，比如光传感器、图像传感器、运动传感器以及其他传感器。具体地，光传感器主要有光敏元件组成，可根据环境光线的明暗来调节显示面板1031的亮度；图像传感器是组成数字摄像头的重要组成部分，利用光电器件的光电转换功能，将感光面上的光像转换为与光像成相应比例关系的电信号；运动传感器是将非电量(比如速度、压力)的变化转变为电量变化的元件，根据转换的非电量不同，运动传感器可以包括压力传感器、速度传感器等；此外，移动终端10还可配置的指纹传感器、虹膜传感器、分子传感器、陀螺仪、红外线传感器等其他传感器，在此不再赘述。
摄像头106是一种视频输入设备，又称之为电脑相机、电子眼等；摄像头106一般具有视频摄像/传播和静态图像捕捉等基本功能，它是借由镜头采集图像之后，由摄像头内的感光组件电路及控制组件对所采集的图像进行处理并转换成数字信号，然后存储于存储器107中。摄像头106可以包括前置摄像头和后置摄像头等。
存储器107可用于存储软件程序以及各种数据。存储器107可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一 个功能所需的应用程序(比如录音功能和图像播放功能)等；存储数据区可存储根据移动终端的使用所创建的数据(比如音频数据和图像数据)等。
处理器108是移动终端的控制中心，利用各种接口和线路连接整个移动终端的各个部分，通过运行或执行存储在存储器107内的软件程序和/或模块，以及调用存储在存储器107内的数据，执行移动终端的各种功能和处理数据，从而对移动终端进行整体监控。处理器108可包括一个或多个处理单元；优选的，处理器108可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器108中。
移动终端10还可以包括给各个部件供电的电源109(比如电池)，优选的，电源109可以通过电源管理系统与处理器108逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。
尽管图1未示出，移动终端10还可以包括蓝牙模块、WiFi模块等，在此不再赘述。
为了便于理解本申请实施例，下面对本申请的移动终端所应用的通信网络系统进行描述。
参见图2，图2示出了本申请实施例提供的一种通信网络系统的架构示意图，该通信网络系统20包括移动终端201和服务器202，移动终端201和服务器202位于通信网络203中；其中，移动终端201和服务器202通过通信网络203进行信息交互，移动终端201可以是上述的移动终端10，服务器202可以是数据库、网络服务器、数据服务器以及Web服务器等，通信网络203可以是无线网络或者有线网络，比如长期演进(Long Term Evolution，LTE)网络、全球移动通信(Global System of Mobile communication，GSM)网络、码分多址2000(Code Division Multiple Access 2000，CDMA2000)网络、宽带码分多址(Wide band Code Division Multiple Access,WCDMA)网络以及未来新的通信网络等，此处不做限定。
基于上述移动终端硬件结构以及通信网络系统，当人们在某一瞬间突然涌现一个灵感的时候，通常都是采用纸和笔或者是用移动终端备忘录/便签工具来进行记录，但是很多时候又苦于没有纸和笔，或者是打开移动终端的备忘录/便签工具的过程太过繁琐，从而导致该灵感被遗忘；这时候，速记应用程序就起到了关键性作用；其中，速记应用程序是在移动终端锁屏状态下能够一键打开的应用程序，可以同时支持文字、语音以及图像信息的快速记录；然而当用户得到一张图像时，目前需要先把该图像保存到本地设备上，然后针对本地设备中已经存在的图像来进行图像中的文字提取，再把提取出的文字复制及粘贴到记事本中进行保存，或者将提取出的文字复制及粘贴到搜索引擎中进行搜索，整个过程比较繁琐，而且所得到的搜索结果比较冗余，还存在部分搜索结果无意义的问题，降低了信息搜 集的准确性和智能性；在本申请实施例中，基于速记应用程序，为了保证拍照速记信息的全面性和提高信息搜集的准确性和智能性，下面结合附图对本申请实施例进行详细介绍。
参见图3，其示出了本申请实施例提供的一种图像处理方法的流程，该方法可以包括：
S301：基于速记应用程序，获取待处理图像；
S302：对所述待处理图像进行图像识别，得到一个或多个被识别对象；
S303：根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
S304：根据所述关键词，获取与所述关键词相匹配的搜索结果；
S305：将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
对于图3所示的技术方案，主要应用于具有速记功能的移动终端，当用户突然具有灵感的时候，这时移动终端需要快速记录该灵感信息；首先需要调用速记应用程序的入口，通过该速记应用程序中的拍照功能可以获得待处理图像。
这样，在获取到待处理图像之后，通过对待处理图像进行图像识别，可以得到一个或多个被识别对象；根据所述得到的所述被识别对象，获取所述待处理图像的关键词；根据所述关键词，获取与所述关键词相匹配的搜索结果；将所述搜索结果记录于所述待处理图像对应的拍照速记信息中；从而不仅完善了拍照速记信息的全面性，而且还解决了信息搜索结果冗余且无意义的问题，进一步提高了信息搜集的准确性和智能性。
对于图3所示的技术方案，在一种可能的实现方式中，所述基于速记应用程序，获取待处理图像，包括：
接收速记开启指令，所述速记开启指令用于指示打开速记应用程序；
接收选择指令，所述选择指令用于指示选择拍照速记模式；
接收拍照指令，根据所述拍照指令获取所述待处理图像。
举例来说，当用户需要记录灵感或者临时想法的时候，这时用户需要打开速记应用程序；一般来说，用户可以通过对移动终端的触控面板执行触摸操作，或者通过对移动终端的实体按键(比如音量+按键和电源按键组合)执行按压操作，还可以通过对移动终端的语音助手执行语音操作(比如“我要记录灵感”、“帮我快速记录个想法”等语音)来打开速记应用程序，这样基于用户的操作，移动终端接收速记开启指令以打开速记应用程序；然后在速记应用程序界面接收选择指令来选取速记信息的记录模式，速记信息可以通过文字速记、语音速记和拍照速记等三种模式进行记录；参见图4，其示出了本申请实施例提供的一种选择速记信息记录模式的结构示意图；如图4所示，401部分表示文字速记模式，402部分表示语音速记模式，403部分表示拍照速记模式；当用户选择403部分时，表明了速记信 息以拍照速记模式进行记录，此时移动终端可以通过用户输入的拍照操作所生成的拍照指令来获取待处理图像；参见图5，其示出了本申请实施例提供的一种拍摄待处理图像的结构示意图；如图5所示，当用户选择拍照速记模式之后，进入图5所示的界面，501部分表示退出拍照速记模式，502部分表示对图5所示的待处理图像进行拍摄，503部分表示后置摄像头和前置摄像头的互换；当用户点击502部分对应的按钮之后，可以得到所拍摄的504部分所示的待处理图像。需要说明的是，待处理图像可以通过前置摄像头拍摄，也可以通过后置摄像头拍摄，同时该拍摄保留了闪光灯功能(闪光灯默认处于关闭状态)，待处理图像甚至还可以是加载本地预先存储的图像，本申请实施例对此不作具体限定。
对于图3所示的技术方案，在一种可能的实现方式中，在所述对所述待处理图像进行图像识别，得到一个或多个被识别对象之前，所述方法还包括：
对所述待处理图像按照预设的处理策略进行预处理。
需要说明的是，所述预设的处理策略是指对待处理图像进行预处理的方式；为了获取高清晰和高质量的待处理图像，可以通过线性纠正、降噪、去坏点、内插以及白平衡等方式中的任一项对待处理图像进行预处理。举例来说，以图5中504部分所示的待处理图像为例，通过线性纠正、降噪、去坏点、内插以及白平衡等方式中任一项的处理，可以使得待处理图像变得更为清晰，更有利于后续对待处理图像中的被识别对象进行识别。
对于图3所示的技术方案，在一种可能的实现方式中，所述对所述待处理图像进行图像识别，得到一个或多个被识别对象，包括：
对所述待处理图像进行图像识别，根据所述识别的结果得到所述被识别对象包括下述各项中的至少一项：物体信息、风景信息、人物信息、电影信息、品牌信息和文字信息。
需要说明的是，待处理图像中包括物体、风景、人物、电影、品牌和文字中的一种或多种被识别对象。对待处理图像进行识别，可以通过光学字符识别(Optical Character Recognition，OCR)技术、百度识图技术、甚至其他图像识别软件来识别出待处理图像中的被识别对象，本申请实施例不作具体限定。另外，当待处理图像中包含有人脸时，也可以通过人脸识别技术来识别出待处理图像中的人物信息；当待处理图像中包含有文字时，也可以通过其他字符识别方法来识别出待处理图像中的文字信息。举例来说，以图5中504部分所示的待处理图像为例，利用OCR技术可以从该待处理图像中识别出504-1部分所示的人物信息是“张三”，504-2部分所示的品牌信息是“某宝”，504-3部分所示的文字信息是“某宝代言人张三”，因此，504部分所示的待处理图像中所确定的被识别对象包括：“张三”、“某宝”和“某宝代言人张三”。
还需要说明的是，在得到被识别对象之后，还需要获取待处理图像的 关键词。针对被识别对象，可以利用关键词提取算法从被识别对象中提取出关键词，其中，关键词提取算法可以是PageRank算法、TextRank算法、LDA算法以及TFIDF算法等；针对被识别对象，也可以将被识别对象与预设关键词库进行查询匹配，根据匹配结果，将匹配成功的被识别对象作为关键词，其中，预设关键词库是根据接收到的服务器下发的多个关键词来预先建立的；这里，对于获取关键词的方式，本申请实施例不作具体限定。
举例来说，仍以图5中504部分所示的待处理图像为例，所确定出的被识别对象包括：“张三”、“某宝”和“某宝代言人张三”，根据这些被识别对象，移动终端将这些被识别对象与预设关键词库进行查询匹配，根据匹配结果，将成功匹配的被识别对象作为关键词，比如所获得的关键词包括“张三”、“代言人”和“某宝”。
可以理解地，在得到关键词之后，可以根据关键词来获取对应的搜索结果；因此，对于图3所示的技术方案，在一种可能的实现方式中，所述根据所述关键词，获取与所述关键词相匹配的搜索结果，包括：
将所述关键词与预设信息库中第一搜索信息进行匹配；
基于所述匹配结果，获取匹配成功的所述关键词对应的第二搜索信息；其中，所述第二搜索信息为与所述关键词的匹配度不小于预设匹配阈值的第一搜索信息；
根据所述匹配度对所述第二搜索信息进行排序，获取所述第二搜索信息的排序结果；
根据所述排序结果，将排序靠前预定数量的第二搜索信息确定为所述关键词的搜索结果。
需要说明的是，无论是第一搜索信息，还是第二搜索信息，一般都包含有搜索信息标题，即搜索信息标题与搜索信息之间具有对应关系。将关键词与预设信息库中第一搜索信息进行匹配，也就是说，将关键词与第一搜索信息中的第一搜索信息标题进行匹配，不同的第一搜索信息标题与关键词之间具有不同的匹配度。比如若第一搜索信息标题与关键词完全相同，则认为匹配度为百分之百；若第一搜索信息标题中的字段与部分关键词完全相同，则认为匹配度为百分之五十；其中，匹配度还可以通过第一搜索信息标题与关键词之间的文本相似度进行衡量；在本申请实施例中，可以根据实际需要选择合适的匹配方式，申请实施例对此不作具体限定。在将关键词与第一搜索信息中的第一搜索信息标题进行匹配之后，根据匹配结果，可以获取到与所述关键词的匹配度不小于预设匹配阈值的第二搜索信息标题，根据搜索信息标题与搜索信息之间的对应关系，也就获得了第二搜索信息；将第二搜索信息按照匹配度的大小进行排序，这时候选取排序靠前预定数量的第二搜索信息作为关键词的搜索结果；其中，预定数量根据实际应用的需求确定，预定数量可以是1个，也可以是5个，还可以是10个，本申请实施例不作具体限定。
举例来说，仍以图5中504部分所示的待处理图像为例，移动终端所获得的关键词包括“张三”、“代言人”和“某宝”，将关键词与预设信息库中第一搜索信息进行匹配，根据匹配结果，移动终端可以从预存信息中获取到匹配成功的第二搜索信息；为了方便示例，再加上显示空间的局限性，可以用第二搜索信息标题来代替第二搜索信息进行排序及显示，然后用户通过进一步的点击操作可以查看每个搜索信息的详细内容；参见图6，其示出了本申请实施例提供的一种第二搜索信息排序的结构示意图；如图6所示，第二搜索信息的排序结果包括“张三又斩获一代言成某宝代言人”、“某宝代言人换成李四和张三”、“张三代言某宝”、“李四和张三某宝启用新男女代言人”、“张三手持某宝全画幅微单拍广告”和“被张三‘提前发布’的某宝微单”等。
可以理解地，在将所述关键词与预设信息库中第一搜索信息进行匹配之前，还需要建立预设信息库；因此，在上述实现方式中，具体地，在所述将所述关键词与预设信息库中第一搜索信息进行匹配之前，所述方法还包括：
接收包含所述关键词的搜索指令，根据所述搜索指令生成搜索请求；
将所述搜索请求发送给服务器；
基于所述服务器对所述搜索请求的响应，接收所述服务器返回的第一搜索信息；
基于所述第一搜索信息，建立所述预设信息库。
需要说明的是，在得到关键词之后，当需要针对该关键词进行信息搜索时，移动终端接收包含所述关键词的搜索指令，并根据搜索指令生成搜索请求，然后将该搜索请求发送给服务器；服务器在接收到该搜索请求之后会针对该搜索请求做出响应，由服务器确定出需要下发的第一搜索信息；然后服务器将这些第一搜索信息返回给移动终端，移动终端则会根据这些第一搜索信息来建立预设信息库；其中，由于第一搜索信息包含有第一搜索信息标题，即预设信息库中还包含了第一搜索信息标题与第一搜索信息之间的对应关系。
可以理解地，为了使所获得的搜索结果更贴近用户的喜好，对于第二搜索信息的排序，除了可以按照匹配度的大小来排序之外，考虑到用户的个性化需求，针对不同的用户来展示其关注度较高的搜索信息，这时候也可以结合用户的喜好对排序进行个性化调整；因此，在上述实现方式中，具体地，在所述根据所述排序结果，将排序靠前预定数量的第二搜索信息确定为所述关键词的搜索结果之前，所述方法还包括：
基于用户日志信息，获取用户的历史搜索记录；其中，所述历史搜索记录包含有搜索关键词、搜索结果和对应的搜索次数；
对所述历史搜索记录进行深度学习，获得辅助搜索模型；
基于所述辅助搜索模型，调整所述第二搜索信息的排序结果。
需要说明的是，用户日志主要包含有用户信息、时间、地址、搜索关键词、搜索结果以及对应的搜索次数等历史搜索记录的内容；比如当用户在浏览器或者其他应用程序中对任意关键词进行搜索、点击、浏览等相关操作时，也会在相应的用户日志中生成历史搜索记录；对于用户的历史搜索记录进行深度学习，比如卷积神经网络(Convolutional Neural Network，CNN)算法，将用户的历史搜索记录作为训练样本进行训练，可以得到辅助搜索模型；根据辅助搜索模型来对第二搜索信息的排序进行调整，将用户关注度高的搜索信息排序在前面，从而可以使得最终得到的搜索结果是用户关注度高的，而且是用户感兴趣的搜索信息。举例来说，假定用户经常搜索张三，也就是用户对“张三”这位人物信息比较关注，那么针对图6所示的第二搜索信息排序，可以将和“张三”切度更高的搜索信息调整到最前面，比如“张三又斩获一代言成某宝代言人”、“张三手持某宝全画幅微单拍广告”和“被张三‘提前发布’的某宝微单”，调整之后的排序结果包括“张三又斩获一代言成某宝代言人”、“张三手持某宝全画幅微单拍广告”、“被张三‘提前发布’的某宝微单”、“张三代言某宝”、“李四和张三某宝启用新男女代言人”和“某宝代言人换成李四和张三”，如图7所示的本申请实施例提供的另一种第二搜索信息排序的结构示意图；根据调整后的排序结果，假定预订数量为2个，则可以确定出关键词包括“张三”、“代言人”和“某宝”所对应的搜索结果为排序在最前面2个的“张三又斩获一代言成某宝代言人”和“张三手持某宝全画幅微单拍广告”；由于图7所示的第二搜索信息排序结合了用户的喜好而做了调整，也就是说，最终得到的搜索结果为“张三又斩获一代言成某宝代言人”和“张三手持某宝全画幅微单拍广告”是用户关注度高的、感兴趣的搜索信息。
还需要说明的是，搜索结果可以是以文字形式所展示的搜索内容，也可以是与该搜索内容对应的网络地址信息，甚至还可以是与该搜索内容对应的应用接口信息，在本申请实施例中，对此不作具体限定。
对于图3所示的技术方案，在一种可能的实现方式中，在所述根据所述关键词，获取与所述关键词相匹配的搜索结果之后，所述方法还包括：
基于所述速记应用程序的当前显示界面，将所述搜索结果进行显示。
需要说明的是，在得到搜索结果之后，可以将搜索结果在所述速记应用程序的当前显示界面中进行显示。举例来说，在确定出搜索结果为“张三又斩获一代言成某宝代言人”和“张三手持某宝全画幅微单拍广告”的搜索信息之后，在所述速记应用程序的当前显示界面，可以将该搜索结果按照预设卡片格式进行显示，也可以按照浏览网页格式进行显示，还可以按照应用接口进行显示；参见图8，其示出了本申请实施例提供的一种搜索结果显示界面的结构示意图；其中，图8中所示的内容即为搜索结果，该部分包括以文字形式展示的搜索信息标题(如801部分)和搜索信息内容(如802部分)；这里，搜索结果包括除了以文字形式所展示的搜索信息标 题和搜索信息内容之外，还可以包括与搜索信息内容对应的网络地址信息、与搜索信息内容对应的应用接口信息；当搜索结果为搜索信息内容对应的网络地址信息时，可以直接调用浏览器加载该网络地址进行显示；当搜索结果为该搜索信息内容对应的应用接口信息时，可以启动相应的应用程序，随后通过该应用程序进行搜索结果的显示。
可以理解地，为了方便后续对待处理图像的查看和分类，还可以将所确定出的关键词作为标签对待处理图像进行标记；对于图3所示的技术方案，在一种可能的实现方式中，在所述根据所述得到的所述被识别对象，获取所述待处理图像的关键词之后，所述方法还包括：
根据所述关键词，对所述待处理图像进行标记。
需要说明的是，在得到关键词之后，可以将关键词作为待处理图像的标签进行标记，并且可以将所标记的标签作为拍照速记信息的一部分进行记录。举例来说，仍以图5中504部分所示的待处理图像为例，所得到的关键词包括“张三”、“代言人”和“某宝”，将这些关键词作为标签对待处理图像进行标记；参见图9，其示出了本申请实施例提供的一种标记待处理图像的结构示意图；如图9所示，901部分表示标记信息，902部分表示待处理图像，903部分表示“重拍”按钮，904部分表示“保存”按钮；其中，901部分的标记信息浏览为横滑动方式，所标记的每一个标签内容不超过200字，而且901部分的标记信息除了移动终端自动将关键词作为标签进行添加之外，用户也可以手动添加标签；当用户对902部分所示的待处理图像不满意时，用户可以点击903部分所示的“重拍”按钮来重新获取待处理图像；最终用户点击904部分所示的“保存”按钮，可以使得移动终端将这些标记和待处理图像作为拍照速记信息进行记录，基于这些标签，有利于用户对待处理图像进行查看和分类。
对于图3所示的技术方案，在一种可能的实现方式中，所述将所述搜索结果记录于所述待处理图像对应的拍照速记信息中，包括：
将所述搜索结果以附件形式记录于所述拍照速记信息中。
举例来说，仍以图8所示的搜索结果显示界面为例，在上述显示页面中除了包含搜索信息标题(如801部分)和搜索信息内容(如802部分)之外，还包括803部分所示的“添加为附件”的功能按钮，根据用户对该按钮的操作，可以将搜索结果以附件形式记录于拍照速记信息中；搜索结果作为对速记内容的辅助记录，提高了拍照速记信息的全面性以及智能性。
本实施例提供了一种图像处理方法，应用于具有速记功能的移动终端，所述方法包括：基于速记应用程序，获取待处理图像；对所述待处理图像进行图像识别，得到一个或多个被识别对象；根据所述得到的所述被识别对象，获取所述待处理图像的关键词；根据所述关键词，获取与所述关键词相匹配的搜索结果；将所述搜索结果记录于所述待处理图像对应的拍照速记信息中；从而不仅完善了拍照速记信息的全面性，而且还解决了信息 搜索结果冗余且无意义的问题，进一步提高了信息搜集的准确性和智能性。
基于前述技术方案相同的发明构思，参见图10，其示出了本申请实施例提供的一种图像处理装置100的组成，所述图像处理装置100可以包括：第一获取部分1001、识别部分1002、第二获取部分1003、第三获取部分1004和记录部分1005；其中，
所述第一获取部分1001，配置为基于速记应用程序，获取待处理图像；
所述识别部分1002，配置为对所述待处理图像进行图像识别，得到一个或多个被识别对象；
所述第二获取部分1003，配置为根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
所述第三获取部分1004，配置为根据所述关键词，获取与所述关键词相匹配的搜索结果；
所述记录部分1005，配置为将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
在上述方案中，所述第一获取部分1001，配置为：
接收速记开启指令，所述速记开启指令用于指示打开速记应用程序；
接收选择指令，所述选择指令用于指示选择拍照速记模式；
接收拍照指令，根据所述拍照指令获取所述待处理图像。
在上述方案中，参见图11，所述图像处理装置100还包括预处理部分1006，配置为：
对所述待处理图像按照预设的处理策略进行预处理。
在上述方案中，所述识别部分1002，配置为：
对所述待处理图像进行图像识别，根据所述识别的结果得到所述被识别对象包括下述各项中的至少一项：物体信息、风景信息、人物信息、电影信息、品牌信息和文字信息。
在上述方案中，所述第三获取部分1004，配置为：
将所述关键词与预设信息库中第一搜索信息进行匹配；
基于所述匹配结果，获取匹配成功的所述关键词对应的第二搜索信息；其中，所述第二搜索信息为与所述关键词的匹配度不小于预设匹配阈值的第一搜索信息；
根据所述匹配度对所述第二搜索信息进行排序，获取所述第二搜索信息的排序结果；
根据所述排序结果，将排序靠前预定数量的第二搜索信息确定为所述关键词的搜索结果。
在上述方案中，参见图12，所述图像处理装置100还包括建立部分1007，配置为：
接收包含所述关键词的搜索指令，根据所述搜索指令生成搜索请求；
将所述搜索请求发送给服务器；
基于所述服务器对所述搜索请求的响应，接收所述服务器返回的第一搜索信息；
基于所述第一搜索信息，建立所述预设信息库。
在上述方案中，参见图13，所述图像处理装置100还包括调整部分1008，配置为：
基于用户日志信息，获取用户的历史搜索记录；其中，所述历史搜索记录包含有搜索关键词、搜索结果和对应的搜索次数；
对所述历史搜索记录进行深度学习，获得辅助搜索模型；
基于所述辅助搜索模型，调整所述第二搜索信息的排序结果。
在上述方案中，参见图14，所述图像处理装置100还包括显示部分1009，配置为：
基于所述速记应用程序的当前显示界面，将所述搜索结果进行显示。
在上述方案中，参见图15，所述图像处理装置100还包括标记部分1010，配置为：
根据所述关键词，对所述待处理图像进行标记。
在上述方案中，所述记录部分1005，配置为：
将所述搜索结果以附件形式记录于所述速记信息中。
可以理解地，在本实施例中，“部分”可以是部分电路、部分处理器、部分程序或软件等等，当然也可以是单元，还可以是模块也可以是非模块化的。
另外，在本实施例中的各组成部分可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
所述集成的单元如果以软件功能模块的形式实现并非作为独立的产品进行销售或使用时，可以存储在一个计算机可读取存储介质中，基于这样的理解，本实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或processor(处理器)执行本实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
因此，本实施例提供了一种计算机存储介质，该计算机存储介质存储有图像处理程序，所述图像处理程序被至少一个处理器执行时实现上述图3所示的技术方案中所述图像处理的方法的步骤。
基于上述图像处理装置100的组成以及计算机存储介质，参见图16， 其示出了本申请实施例提供的图像处理装置100的具体硬件结构，可以包括：网络接口1601、存储器1602和处理器1603；各个组件通过总线系统1604耦合在一起。可理解，总线系统1604用于实现这些组件之间的连接通信。总线系统1604除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图16中将各种总线都标为总线系统1604。其中，网络接口1601，用于在与其他外部网元之间进行收发信息过程中，信号的接收和发送；
存储器1602，用于存储能够在处理器1603上运行的计算机程序；
处理器1603，用于在运行所述计算机程序时，执行：
基于速记应用程序，获取待处理图像；
对所述待处理图像进行图像识别，得到一个或多个被识别对象；
根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
根据所述关键词，获取与所述关键词相匹配的搜索结果；
将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
可以理解，本申请实施例中的存储器1602可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本文描述的系统和方法的存储器1602旨在包括但不限于这些和任意其它适合类型的存储器。
而处理器1603可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器1603中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1603可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为 硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1602，处理器1603读取存储器1602中的信息，结合其硬件完成上述方法的步骤。
可以理解的是，本文描述的这些实施例可以用硬件、软件、固件、中间件、微码或其组合来实现。对于硬件实现，处理单元可以实现在一个或多个专用集成电路(Application Specific Integrated Circuits，ASIC)、数字信号处理器(Digital Signal Processing，DSP)、数字信号处理设备(DSP Device，DSPD)、可编程逻辑设备(Programmable Logic Device，PLD)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)、通用处理器、控制器、微控制器、微处理器、用于执行本申请所述功能的其它电子单元或其组合中。
对于软件实现，可通过执行本文所述功能的模块(例如过程、函数等)来实现本文所述的技术。软件代码可存储在存储器中并通过处理器执行。存储器可以在处理器中或在处理器外部实现。
可选地，作为另一个实施例，处理器1603还配置为在运行所述计算机程序时，执行上述图3所示的技术方案中所述图像处理的方法的步骤。
可选地，本申请实施例还提供了一种移动终端，其中，所述移动终安装有速记应用程序，所述移动终端至少包括如前述的图像处理装置100。
需要说明的是：本申请实施例所记载的技术方案之间，在不冲突的情况下，可以任意组合。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。
工业实用性
本申请实施例中，基于速记应用程序，获取待处理图像；对所述待处理图像进行图像识别，得到一个或多个被识别对象；根据所述得到的所述被识别对象，获取所述待处理图像的关键词；根据所述关键词，获取与所述关键词相匹配的搜索结果；将所述搜索结果记录于所述待处理图像对应的拍照速记信息中；从而不仅完善了拍照速记信息的全面性，而且还解决了信息搜索结果冗余且无意义的问题，进一步提高了信息搜集的准确性和智能性。

Claims (14)

  1. 一种图像处理方法，所述方法包括：
    基于速记应用程序，获取待处理图像；
    对所述待处理图像进行图像识别，得到一个或多个被识别对象；
    根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
    根据所述关键词，获取与所述关键词相匹配的搜索结果；
    将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
  2. 根据权利要求1所述的方法，其中，所述基于速记应用程序，获取待处理图像，包括：
    接收速记开启指令，所述速记开启指令用于指示打开速记应用程序；
    接收选择指令，所述选择指令用于指示选择拍照速记模式；
    接收拍照指令，根据所述拍照指令获取所述待处理图像。
  3. 根据权利要求1所述的方法，其中，在所述对所述待处理图像进行图像识别，得到一个或多个被识别对象之前，所述方法还包括：
    对所述待处理图像按照预设的处理策略进行预处理。
  4. 根据权利要求1所述的方法，其中，所述对所述待处理图像进行图像识别，得到一个或多个被识别对象，包括：
    对所述待处理图像进行图像识别，根据所述识别的结果得到所述被识别对象包括下述各项中的至少一项：物体信息、风景信息、人物信息、电影信息、品牌信息和文字信息。
  5. 根据权利要求1所述的方法，其中，所述根据所述关键词，获取与所述关键词相匹配的搜索结果，包括：
    将所述关键词与预设信息库中第一搜索信息进行匹配；
    基于所述匹配结果，获取匹配成功的所述关键词对应的第二搜索信息；其中，所述第二搜索信息为与所述关键词的匹配度不小于预设匹配阈值的第一搜索信息；
    根据所述匹配度对所述第二搜索信息进行排序，获取所述第二搜索信息的排序结果；
    根据所述排序结果，将排序靠前预定数量的第二搜索信息确定为所述关键词的搜索结果。
  6. 根据权利要求5所述的方法，其中，在所述将所述关键词与预设信息库中第一搜索信息进行匹配之前，所述方法还包括：
    接收包含所述关键词的搜索指令，根据所述搜索指令生成搜索请求；
    将所述搜索请求发送给服务器；
    基于所述服务器对所述搜索请求的响应，接收所述服务器返回的第一搜索信息；
    基于所述第一搜索信息，建立所述预设信息库。
  7. 根据权利要求5或6所述的方法，其中，在所述根据所述排序结果，将排序靠前预定数量的第二搜索信息确定为所述关键词的搜索结果之前，所述方法还包括：
    基于用户日志信息，获取用户的历史搜索记录；其中，所述历史搜索记录包含有搜索关键词、搜索结果和对应的搜索次数；
    对所述历史搜索记录进行深度学习，获得辅助搜索模型；
    基于所述辅助搜索模型，调整所述第二搜索信息的排序结果。
  8. 根据权利要求1所述的方法，其中，在所述根据所述关键词，获取与所述关键词相匹配的搜索结果之后，所述方法还包括：
    基于所述速记应用程序的当前显示界面，将所述搜索结果进行显示。
  9. 根据权利要求1至8任一项所述的方法，其中，在所述根据所述得到的所述被识别对象，获取所述待处理图像的关键词之后，所述方法还包括：
    根据所述关键词，对所述待处理图像进行标记。
  10. 根据权利要求1至9任一项所述的方法，其中，所述将所述搜索结果记录于所述待处理图像对应的拍照速记信息中，包括：
    将所述搜索结果以附件形式记录于所述拍照速记信息中。
  11. 一种图像处理装置，其中，所述图像处理装置包括：第一获取部分、识别部分、第二获取部分、第三获取部分和记录部分；
    所述第一获取部分，配置为基于速记应用程序，获取待处理图像；
    所述识别部分，配置为对所述待处理图像进行图像识别，得到一个或多个被识别对象；
    所述第二获取部分，配置为根据所述得到的所述被识别对象，获取所述待处理图像的关键词；
    所述第三获取部分，配置为根据所述关键词，获取与所述关键词相匹配的搜索结果；
    所述记录部分，配置为将所述搜索结果记录于所述待处理图像对应的拍照速记信息中。
  12. 一种图像处理装置，其中，所述图像处理装置包括：存储器和处理器；
    所述存储器，用于存储能够在所述处理器上运行的计算机程序；
    所述处理器，用于在运行所述计算机程序时，执行权利要求1至10任一项所述的方法的步骤。
  13. 一种计算机存储介质，其中，所述计算机存储介质存储有图像处理程序，所述图像处理程序被至少一个处理器执行时实现权利要求1至10任一项所述的方法的步骤。
  14. 一种移动终端，其中，所述移动终端安装有速记应用程序，所 述移动终端至少包括如权利要求11至12任一项所述的图像处理装置。
PCT/CN2018/101695 2018-08-22 2018-08-22 一种图像处理方法、装置以及计算机存储介质 WO2020037534A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880096298.7A CN112534422A (zh) 2018-08-22 2018-08-22 一种图像处理方法、装置以及计算机存储介质
PCT/CN2018/101695 WO2020037534A1 (zh) 2018-08-22 2018-08-22 一种图像处理方法、装置以及计算机存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/101695 WO2020037534A1 (zh) 2018-08-22 2018-08-22 一种图像处理方法、装置以及计算机存储介质

Publications (1)

Publication Number Publication Date
WO2020037534A1 true WO2020037534A1 (zh) 2020-02-27

Family

ID=69592367

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/101695 WO2020037534A1 (zh) 2018-08-22 2018-08-22 一种图像处理方法、装置以及计算机存储介质

Country Status (2)

Country Link
CN (1) CN112534422A (zh)
WO (1) WO2020037534A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537341A (zh) * 2014-12-23 2015-04-22 北京奇虎科技有限公司 人脸图片信息获取方法和装置
CN104615640A (zh) * 2014-11-28 2015-05-13 百度在线网络技术（北京）有限公司 一种用于提供搜索关键词及进行搜索的方法与装置
CN105874454A (zh) * 2013-12-31 2016-08-17 谷歌公司 用于基于场境信息生成搜索结果的方法、系统和介质
CN107577790A (zh) * 2017-09-18 2018-01-12 北京金山安全软件有限公司 一种图像搜索方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104778176A (zh) * 2014-01-13 2015-07-15 阿里巴巴集团控股有限公司 一种数据搜索处理方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105874454A (zh) * 2013-12-31 2016-08-17 谷歌公司 用于基于场境信息生成搜索结果的方法、系统和介质
CN104615640A (zh) * 2014-11-28 2015-05-13 百度在线网络技术（北京）有限公司 一种用于提供搜索关键词及进行搜索的方法与装置
CN104537341A (zh) * 2014-12-23 2015-04-22 北京奇虎科技有限公司 人脸图片信息获取方法和装置
CN107577790A (zh) * 2017-09-18 2018-01-12 北京金山安全软件有限公司 一种图像搜索方法及装置

Also Published As

Publication number Publication date
CN112534422A (zh) 2021-03-19

Similar Documents

Publication Publication Date Title
WO2021135601A1 (zh) 辅助拍照方法、装置、终端设备及存储介质
WO2019233219A1 (zh) 对话状态确定方法及装置、对话系统、计算机设备、存储介质
TWI544350B (zh) Input method and system for searching by way of circle
US11249620B2 (en) Electronic device for playing-playing contents and method thereof
US7694214B2 (en) Multimodal note taking, annotation, and gaming
EP2457183B1 (en) System and method for tagging multiple digital images
US11442983B2 (en) Contextually disambiguating queries
CN111465918B (zh) 在预览界面中显示业务信息的方法及电子设备
US9049540B2 (en) Wireless attached reader screen for cell phones
US8364680B2 (en) Computer systems and methods for collecting, associating, and/or retrieving data
US20140240603A1 (en) Object detection metadata
WO2018171047A1 (zh) 一种拍摄引导方法、设备及系统
WO2021258797A1 (zh) 图像信息输入方法、电子设备及计算机可读存储介质
WO2022057435A1 (zh) 基于搜索的问答方法及存储介质
US20230195780A1 (en) Image Query Analysis
WO2018184260A1 (zh) 文档图像的校正方法及装置
WO2019137259A1 (zh) 图像处理方法、装置、存储介质及电子设备
CN111708943A (zh) 一种搜索结果展示方法、装置和用于搜索结果展示的装置
CN107643923B (zh) 复制信息的处理方法及移动终端
US20060082664A1 (en) Moving image processing unit, moving image processing method, and moving image processing program
WO2021073434A1 (zh) 对象行为的识别方法、装置及终端设备
WO2020047721A1 (zh) 一种搜索响应方法、装置以及计算机存储介质
KR20210120203A (ko) 웹 페이지에 기반한 메타데이터 생성방법
WO2020037534A1 (zh) 一种图像处理方法、装置以及计算机存储介质
CN113779285A (zh) 一种图库图片动态处理方法、设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18930562

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24.06.2021

122 Ep: pct application non-entry in european phase

Ref document number: 18930562

Country of ref document: EP

Kind code of ref document: A1