CN104268150A - Method and device for playing music based on image content - Google Patents
Method and device for playing music based on image content Download PDFInfo
- Publication number
- CN104268150A CN104268150A CN201410432694.6A CN201410432694A CN104268150A CN 104268150 A CN104268150 A CN 104268150A CN 201410432694 A CN201410432694 A CN 201410432694A CN 104268150 A CN104268150 A CN 104268150A
- Authority
- CN
- China
- Prior art keywords
- picture
- scene
- target photo
- scene label
- picture group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
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)
- Television Signal Processing For Recording (AREA)
Abstract
The invention relates to a method and a device for playing music based on image content. The method includes: splitting target images in an image library into at least one image group according to preset conditions, and distributing one scene tag for each image group; determining a music file corresponding to the scene tag of the corresponding image group; playing the music file corresponding to the scene tag of the corresponding image group while the target images in the corresponding image group are displayed. According to the method, the target images in the image library are split into at least one image group according to the preset conditions; each image group has one scene tag which corresponds to one music file; while the target images in each image group are displayed, the scene tag corresponding to the corresponding image group is determined; accordingly, the music file according to the scene tag can be automatically played. Therefore, the method and the device according to the scheme have the advantages that the music files can be played according to the scene tags of the image groups, operating is easier for users, and time is saved for the users.
Description
Technical field
The present invention relates to communication technical field, in particular, relate to method and the device of playing music based on image content.
Background technology
During the picture of people in Album for glancing over pictures or picture library, usually can play some music.Sometimes, user, in order to better experience the atmosphere in picture, can select the music that some and the current picture checked match usually.Such as, user, when browsing the picture of oneself playing by the sea, can play the music that some are cheerful and light-hearted, makes oneself better to incorporate scene joyful in picture.And for example, user, when browsing the picture of friend's wedding, can play the music that some are relevant with wedding, as wedding march etc.For another example, user, when browsing terrified picture, can play the music that some are strange or terrible, to set off terrified atmosphere by contrast, makes user experience terrified atmosphere fully.
In research and practice process, inventor finds that above-mentioned correlation technique at least exists following problem:
Because user is when browsing pictures, the picture of multiple different contents may be checked within a period of time.Such as, user has checked the picture played in seashore, the picture of friend's wedding and terrified picture within 10 minutes, so user is when checking the picture of multiple different contents, what often needs were manual goes the music switching applicable photo current, with the scene making oneself better incorporate photo current.But the frequent music of going manual switchover and the current picture browsed to match, the operation complexity of meeting adding users; And user may be difficult to find the music matched with the current picture browsed at short notice, so user may waste a large amount of time when searching the music type matched with the current picture browsed.
Therefore, how to play according to image content the music be applicable to, become the problem needing solution at present badly.
Summary of the invention
For overcoming Problems existing in correlation technique, the disclosure provides a kind of method and the device of playing music based on image content, plays corresponding music file, thus reduces the operation complexity of user, and save the time of user according to the scene label of picture group.
According to the first aspect of disclosure embodiment, a kind of method playing music based on image content is provided, comprises:
According to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for described each picture component;
Determine the music file corresponding with the scene label of described picture group;
When showing the Target Photo of described picture group, play the music file corresponding with the scene label of described picture group.
Optionally, describedly according to pre-conditioned, Target Photo in picture library is split at least one picture group, and comprises for described each picture component joins a scene labelling step:
Obtain and often open Target Photo in picture library;
The scene label that the characteristics of image utilizing the scene decision model that generates in advance to determine often to open described Target Photo is corresponding;
The described Target Photo of corresponding same scene label is defined as a picture group, described scene label is defined as the scene label of described picture group.
Optionally, describedly according to pre-conditioned, Target Photo in picture library is split at least one picture group, and comprises for described each picture component joins a scene labelling step:
According to presetting a point set condition, the Target Photo in picture library is divided at least one picture group;
The scene decision model that generates in advance is utilized to determine scene label corresponding to the characteristics of image often opening Target Photo in described picture group;
For each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of Target Photo as described picture group.
Optionally, describedly Target Photo in picture library be divided at least one picture group step comprise according to presetting a point set condition:
Determine photographing data or the shooting places of each Target Photo in picture library;
The described Target Photo of same for correspondence described photographing data is defined as a picture group, or the described Target Photo of same for correspondence described shooting places is defined as a picture group.
Optionally, described method also comprises:
Create scene label;
Obtain the given scenario picture corresponding with each scene label;
Extract the characteristics of image of given scenario picture corresponding to described each scene label;
Utilize and preset the characteristics of image of machine learning method to given scenario picture corresponding to described each scene label and train, generate described scene decision model.
According to the second aspect of disclosure embodiment, a kind of device playing music based on image content is provided, comprises:
Grouping module, for Target Photo in picture library being split at least one picture group according to pre-conditioned, and joins a scene label for described each picture component;
Determination module, for determining the music file corresponding with the scene label of described picture group;
Playing module, for when showing the Target Photo of described picture group, plays the music file corresponding with the scene label of described picture group.
Optionally, described grouping module comprises:
Obtaining submodule, often opening Target Photo for obtaining in picture library;
First decision sub-module, the scene label that the characteristics of image for utilizing the scene decision model generated in advance to determine often to open described Target Photo is corresponding;
First determines submodule, for the described Target Photo of corresponding same scene label is defined as a picture group, described scene label is defined as the scene label of described picture group.
Optionally, described grouping module comprises:
Grouping submodule, for being divided at least one picture group according to presetting a point set condition by the Target Photo in picture library;
Second decision sub-module, determines scene label corresponding to the characteristics of image often opening Target Photo in described picture group for utilizing the scene decision model generated in advance;
Second determines submodule, for for each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of Target Photo as described picture group.
Optionally, described grouping submodule comprises:
3rd determines submodule, for determining photographing data or the shooting places of each Target Photo in picture library;
4th determines submodule, for the described Target Photo of same for correspondence described photographing data is defined as a picture group, or the described Target Photo of same for correspondence described shooting places is defined as a picture group.
Optionally, described device also comprises:
Creation module, for creating scene label;
Acquisition module, for obtaining the given scenario picture corresponding with each scene label;
Extraction module, for extracting the characteristics of image of given scenario picture corresponding to described each scene label;
Training module, for utilizing the characteristics of image of default machine learning device to given scenario picture corresponding to described each scene label to train, generates described scene decision model.
According to the third aspect of disclosure embodiment, a kind of device playing music based on image content is provided, comprises:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
According to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for described each picture component;
Determine the music file corresponding with the scene label of described picture group;
When showing the Target Photo of described picture group, play the music file corresponding with the scene label of described picture group.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the Target Photo in picture library can be split at least one picture group according to pre-conditioned by the scheme that the disclosure provides, each picture group is all to there being a scene label, and, there is corresponding relation in scene label and music file, so when Showing Picture the Target Photo in group, just can determine the scene label that this picture group is corresponding, thus music file corresponding to this scene label can be play automatically.Therefore, the scheme that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user.
Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows embodiment according to the invention, and is used from instructions one and explains principle of the present invention.
Fig. 1 is a kind of process flow diagram playing the method for music based on image content according to an exemplary embodiment.
Fig. 2 is the process flow diagram of the another kind according to an exemplary embodiment based on the method for image content broadcasting music.
Fig. 3 is another process flow diagram based on the method for image content broadcasting music according to an exemplary embodiment.
Fig. 4 is a kind of schematic diagram playing the device of music based on image content according to an exemplary embodiment.
Fig. 5 is the schematic diagram of the another kind according to an exemplary embodiment based on the device of image content broadcasting music.
Fig. 6 is another schematic diagram based on the device of image content broadcasting music according to an exemplary embodiment.
Fig. 7 is a kind of block diagram playing the device of music based on image content according to an exemplary embodiment.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the present invention.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present invention are consistent.
Embodiment one
Fig. 1 is a kind of process flow diagram playing the method for music based on image content according to an exemplary embodiment, and as shown in Figure 1, the method based on image content broadcasting music shown in Fig. 1 may be used in terminal.The method based on image content broadcasting music that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user, and then improves the Experience Degree of user.The method comprises the following steps.
In step s 11, according to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for each picture component;
Wherein, at least one Target Photo can be deposited in picture library.Target Photo can be the picture/mb-type of various form, and such as, Target Photo can be various types of pictures such as BMP or JPG.Picture group can comprise at least one Target Photo, and each picture group only distributes a scene label.
Wherein, scene label can be polytype label, and such as, scene label can comprise the types such as pet, landscape and portrait, and scene label can by user's sets itself in advance.
In addition, pre-conditioned expression generating pictures group and there is multiple implementation for picture group allocation scenarios label, these implementations are described in detail by embodiment below.
In step s 12, the music file corresponding with the scene label of picture group is determined;
Wherein, the corresponding relation of scene label and music file can be that user establishes in advance, such as, suppose that scene label comprises pet label, landscape label and portrait label, user sets up the corresponding relation of pet label and music file A, landscape label and the corresponding relation of music file B and the corresponding relation of portrait label and music file C respectively.Set up user in the process of the corresponding relation of scene label and music file, the music file that user can select some and scene label to match, such as, for pet label, the music file that music rhythm is comparatively cheerful and light-hearted, joyful can be selected; And for example, for landscape label, the music file of some allusions can be selected.
In step s 13, when Showing Picture the Target Photo of group, the music file corresponding with the scene label of picture group is play.
Wherein, corresponding with the scene label of picture group music file can be one or more.If a scene label is to there being a music file, so when Showing Picture the Target Photo of group, play a music file corresponding with the scene label of picture group; If a scene label is to there being multiple music file, so when Showing Picture the Target Photo of group, play the multiple music files corresponding with the scene label of picture group.
In the embodiment shown in fig. 1, Target Photo in picture library can be split at least one picture group according to pre-conditioned by the scheme that the disclosure provides, each picture group is all to there being a scene label, and, there is corresponding relation in scene label and music file, so when Showing Picture the Target Photo in group, just can determine the scene label that this picture group is corresponding, thus music file corresponding to this scene label can be play automatically.Therefore, the scheme that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user.
Embodiment two
Fig. 2 is the process flow diagram of the another kind according to an exemplary embodiment based on the method for image content broadcasting music, and as shown in Figure 2, the method based on image content broadcasting music shown in Fig. 2 may be used in terminal.Wherein, the present embodiment is the improvement carried out on the basis of embodiment one, so refer to embodiment one with the something in common of embodiment one in the present embodiment.The method based on image content broadcasting music that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user, and then improves the Experience Degree of user.The method comprises the following steps.
In the step s 21, obtain and often open Target Photo in picture library.
In step S22, the scene label that the characteristics of image utilizing the scene decision model that generates in advance to determine often to open Target Photo is corresponding.
Wherein, the characteristics of image of Target Photo can be HOG (Histogram of Oriented Gradient, the histograms of oriented gradients) feature of Target Photo, certainly, characteristics of image also can be the feature of other types, so characteristics of image is not limited to HOG feature.
In addition, scene decision model is a kind of decision model generated in advance, the characteristics of image corresponding any scene label of scene decision model for identifying Target Photo, such as, Target Photo is the picture of a kitten, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is pet.And for example, Target Photo is the picture of a middle-aged male, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is portrait.For another example, Target Photo is the picture of a Guilin Scenery with Hills and Waters, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is landscape.
In addition, scene decision model can be generated by following steps: the first step, creates scene label; Second step, obtains the given scenario picture corresponding with each scene label; 3rd step, extracts the characteristics of image of given scenario picture corresponding to each scene label; 4th step, utilizes and presets the characteristics of image of machine learning method to given scenario picture corresponding to each scene label and train, generate described scene decision model.
Illustrate the step of above-mentioned generating scene decision model below.First, create three scene labels, these three scene labels are respectively pet, landscape and portrait.Secondly, collect pet picture respectively, scenery picture and each 10,000 of portrait picture, wherein, 10,000 the pet pictures collected can comprise cat class, dog class, snake class, the picture that pet muroid is relevant to pet with fish etc., 10,000 scenery pictures collected can comprise high mountain, river, desert, seashore, trees, meadow, waterfall, rainbow, the picture that cloud is relevant to landscape with scenic spots and historical sites etc., 10,000 the portrait pictures collected can comprise children's face-image, old man's face-image, the picture that maiden's face-image is relevant to portrait with adult face's image etc.Again, 30,000 pictures collected are zoomed to unified size, such as, this 30,000 pictures is all zoomed to the size that resolution is 200 × 200.Then, extract the characteristics of image of 30,000 pictures after convergent-divergent respectively, such as, extract the HOG feature of 30,000 pictures after convergent-divergent respectively.Finally, utilize and preset the characteristics of image of machine learning method to corresponding respectively 10,000 the scene pictures of three scene labels and train with generating scene decision model, such as, default machine learning method can be SVM (Support Vector Machine, support vector machine) method, a scene decision model can be trained by SVM method, this scene decision model can identify picture akin with pet, landscape and portrait, and determines this picture and belong to which kind of scene label in above-mentioned three kinds of scene labels.
In step S23, the Target Photo of corresponding same scene label is defined as a picture group, scene label is defined as the scene label of picture group.
Wherein, because the scene label that the characteristics of image of a lot of Target Photo is corresponding is all identical, so the Target Photo of scene label identical for correspondence is defined as a picture group, again common for Target Photo in this picture group corresponding scene label is defined as the scene label of picture group, be equivalent to for this picture group determines a mark, to be different from other picture group.
In step s 24 which, the music file corresponding with the scene label of picture group is determined.
In step s 25, when Showing Picture the Target Photo of group, the music file corresponding with the scene label of picture group is play.
In the embodiment shown in Figure 2, Target Photo in picture library can be split at least one picture group according to pre-conditioned by the scheme that the disclosure provides, each picture group is all to there being a scene label, and, there is corresponding relation in scene label and music file, so when Showing Picture the Target Photo in group, just can determine the scene label that this picture group is corresponding, thus music file corresponding to this scene label can be play automatically.Therefore, the scheme that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user.
Embodiment three
Fig. 3 is another process flow diagram based on the method for image content broadcasting music according to an exemplary embodiment, and as shown in Figure 3, the method based on image content broadcasting music shown in Fig. 3 may be used in terminal.Wherein, the present embodiment is the improvement carried out on the basis of embodiment one, so refer to embodiment one with the something in common of embodiment one in the present embodiment.The method based on image content broadcasting music that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user, and then improves the Experience Degree of user.The method comprises the following steps.
In step S31, according to presetting a point set condition, the Target Photo in picture library is divided at least one picture group;
Wherein, preset a point set condition and there is various ways.
First kind of way, first can determine the photographing data of each Target Photo in picture library, then the Target Photo of same for correspondence photographing data is defined as a picture group.Such as, suppose in picture library, to there are 3 pictures, be respectively picture A, picture B and picture C, the photographing data of picture A is on January 1st, 2010, and the photographing data of picture B is on May 10th, 2010, and the photographing data of picture C is on January 1st, 2010, so after the photographing data determining three pictures, can determine that picture A and picture C is same photographing data, so picture A and picture C is defined as a picture group, picture B is defined as another picture group.
The second way, first can determine the shooting places of each Target Photo in picture library, then the Target Photo of same for correspondence shooting places is defined as a picture group.Such as, suppose in picture library, to there are 3 pictures, be respectively picture A, picture B and picture C, the shooting places of picture A is Beijing, and the shooting places of picture B is Beijing, and the shooting places of picture C is Guangzhou, so after the shooting places determining three pictures, can determine that picture A and picture B is same shooting places, so picture A and picture B is defined as a picture group, picture C is defined as another picture group.
In step s 32, the scene decision model that generates in advance is utilized to determine scene label corresponding to the characteristics of image often opening Target Photo in picture group;
Wherein, the characteristics of image of Target Photo can be HOG (Histogram of Oriented Gradient, the histograms of oriented gradients) feature of Target Photo, certainly, characteristics of image also can be the feature of other types, so characteristics of image is not limited to HOG feature.
In addition, scene decision model is a kind of decision model generated in advance, the characteristics of image corresponding any scene label of scene decision model for identifying Target Photo, such as, Target Photo is the picture of a kitten, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is pet.And for example, Target Photo is the picture of a middle-aged male, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is portrait.For another example, Target Photo is the picture of a Guilin Scenery with Hills and Waters, and the scene label that so scene decision model just can identify the characteristics of image of Target Photo corresponding is landscape.
In addition, scene decision model can be generated by following steps: the first step, creates scene label; Second step, obtains the given scenario picture corresponding with each scene label; 3rd step, extracts the characteristics of image of given scenario picture corresponding to each scene label; 4th step, utilizes and presets the characteristics of image of machine learning method to given scenario picture corresponding to each scene label and train, generate described scene decision model.
Illustrate the step of above-mentioned generating scene decision model below.First, create three scene labels, these three scene labels are respectively pet, landscape and portrait.Secondly, collect pet picture respectively, scenery picture and each 10,000 of portrait picture, wherein, 10,000 the pet pictures collected can comprise cat class, dog class, snake class, the picture that pet muroid is relevant to pet with fish etc., 10,000 scenery pictures collected can comprise high mountain, river, desert, seashore, trees, meadow, waterfall, rainbow, the picture that cloud is relevant to landscape with scenic spots and historical sites etc., 10,000 the portrait pictures collected can comprise children's face-image, old man's face-image, the picture that maiden's face-image is relevant to portrait with adult face's image etc.Again, 30,000 pictures collected are zoomed to unified size, such as, this 30,000 pictures is all zoomed to the size that resolution is 200 × 200.Then, extract the characteristics of image of 30,000 pictures after convergent-divergent respectively, such as, extract the HOG feature of 30,000 pictures after convergent-divergent respectively.Finally, utilize and preset the characteristics of image of machine learning method to corresponding respectively 10,000 the scene pictures of three scene labels and train with generating scene decision model, such as, default machine learning method can be SVM (Support Vector Machine, support vector machine) method, a scene decision model can be trained by SVM method, this scene decision model can identify picture akin with pet, landscape and portrait, and determines this picture and belong to which kind of scene label in above-mentioned three kinds of scene labels.
In step S33, for each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of the Target Photo determining picture group as picture group.
Wherein, after the scene label that the characteristics of image of the Target Photo determining a picture group is corresponding, the scene label that each Target Photo needing to determine this picture group is corresponding, and calculate the scene label that scene label occurrence number is maximum, and using the scene label of this scene label as picture group.Such as, picture group X comprises 3 pictures, be respectively picture A, picture B and picture C, the scene label that picture A is corresponding is pet, the scene label that picture B is corresponding is also pet, the scene label that picture C is corresponding is landscape, because scene label is that the occurrence number of pet is maximum, so using the scene label of pet as picture group X.
In step S34, determine the music file corresponding with the scene label of picture group.
In step s 35, when Showing Picture the Target Photo of group, the music file corresponding with the scene label of picture group is play.
In the embodiment shown in fig. 3, Target Photo in picture library can be split at least one picture group according to pre-conditioned by the scheme that the disclosure provides, each picture group is all to there being a scene label, and, there is corresponding relation in scene label and music file, so when Showing Picture the Target Photo in group, just can determine the scene label that this picture group is corresponding, thus music file corresponding to this scene label can be play automatically.Therefore, the scheme that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user.
Embodiment four
Fig. 4 is a kind of schematic diagram playing the device of music based on image content according to an exemplary embodiment.The device based on image content broadcasting music that the disclosure provides can play corresponding music file according to the scene label of picture group, thus reduces the operation complexity of user, and saves the time of user, and then improves the Experience Degree of user.With reference to Fig. 4, this device comprises grouping module 41, determination module 42 and playing module 43.Wherein:
Grouping module 41, for Target Photo in picture library being split at least one picture group according to pre-conditioned, and joins a scene label for each picture component;
Determination module 42, for determining the music file corresponding with the scene label of picture group;
Playing module 43, for when Showing Picture the Target Photo of group, plays the music file corresponding with the scene label of picture group.
Fig. 5 is the schematic diagram of the another kind according to an exemplary embodiment based on the device of image content broadcasting music.With reference to Fig. 5, this device comprises acquisition submodule 51, first decision sub-module 52, first and determines submodule 53, determination module 54 and playing module 55.Wherein:
Obtaining submodule 51, often opening Target Photo for obtaining in picture library;
First decision sub-module 52, the scene label that the characteristics of image for utilizing the scene decision model generated in advance to determine often to open Target Photo is corresponding;
First determines submodule 53, for the Target Photo of corresponding same scene label is defined as a picture group, scene label is defined as the scene label of picture group.
Determination module 54, for determining the music file corresponding with the scene label of picture group;
Playing module 55, for when Showing Picture the Target Photo of group, plays the music file corresponding with the scene label of picture group.
Fig. 6 is another schematic diagram based on the device of image content broadcasting music according to an exemplary embodiment.With reference to Fig. 6, this device comprises grouping submodule 61, second decision sub-module 62, second and determines submodule 63, determination module 64 and playing module 65.Wherein:
Grouping submodule 61, for being divided at least one picture group according to presetting a point set condition by the Target Photo in picture library;
Second decision sub-module 62, determines scene label corresponding to the characteristics of image often opening Target Photo in picture group for utilizing the scene decision model generated in advance;
Second determines submodule 63, for for each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of Target Photo as picture group.
Determination module 64, for determining the music file corresponding with the scene label of picture group;
Playing module 65, for when Showing Picture the Target Photo of group, plays the music file corresponding with the scene label of picture group.
In an optional embodiment of the present disclosure, grouping submodule 61 can comprise following submodule: the 3rd determines submodule, for determining photographing data or the shooting places of each Target Photo in picture library; 4th determines submodule, for the Target Photo of same for correspondence photographing data is defined as a picture group, or the described Target Photo of same for correspondence described shooting places is defined as a picture group.
In an optional embodiment of the present disclosure, the device that the disclosure provides can also comprise with lower module: creation module, for creating scene label; Acquisition module, for obtaining the given scenario picture corresponding with each scene label; Extraction module, for extracting the characteristics of image of given scenario picture corresponding to each scene label; Training module, for utilizing the characteristics of image of default machine learning device to given scenario picture corresponding to each scene label to train, generating scene decision model.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
Embodiment five
Fig. 7 is a kind of block diagram playing the device 800 of music based on image content according to an exemplary embodiment.Such as, device 800 can be mobile phone, computing machine, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Fig. 7, device 800 can comprise following one or more assembly: processing components 802, storer 804, power supply module 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of I/O (I/O), sensor module 814, and communications component 816.
The integrated operation of the usual control device 800 of processing components 802, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 802 can comprise one or more processor 820 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 802 can comprise one or more module, and what be convenient between processing components 802 and other assemblies is mutual.Such as, processing components 802 can comprise multi-media module, mutual with what facilitate between multimedia groupware 808 and processing components 802.
Storer 804 is configured to store various types of data to be supported in the operation of device 800.The example of these data comprises for any application program of operation on device 800 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 804 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
The various assemblies that power supply module 806 is device 800 provide electric power.Power supply module 806 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 800 and be associated.
Multimedia groupware 808 is included in the screen providing an output interface between device 800 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant with touch or slide and pressure.In certain embodiments, multimedia groupware 808 comprises a front-facing camera and/or post-positioned pick-up head.When device 800 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to export and/or input audio signal.Such as, audio-frequency assembly 810 comprises a microphone (MIC), and when device 800 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 804 further or be sent via communications component 816.In certain embodiments, audio-frequency assembly 810 also comprises a loudspeaker, for output audio signal.
I/O interface 812 is for providing interface between processing components 802 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 814 comprises one or more sensor, for providing the state estimation of various aspects for device 800.Such as, sensor module 814 can detect the opening/closing state of device 800, the relative positioning of assembly, such as assembly is display and the keypad of device 800, the position of all right pick-up unit 800 of sensor module 814 or device 800 1 assemblies changes, the presence or absence that user contacts with device 800, the temperature variation of device 800 orientation or acceleration/deceleration and device 800.Sensor module 814 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 814 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 814 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 816 is configured to the communication being convenient to wired or wireless mode between device 800 and other equipment.Device 800 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 816 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, communications component 816 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 800 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 804 of instruction, above-mentioned instruction can perform said method by the processor 820 of device 800.Such as, non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in storage medium is performed by the processor of mobile terminal, make mobile terminal can perform a kind of method playing music based on image content, method comprises: according to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for each picture component; Determine the music file corresponding with the scene label of picture group; When Showing Picture the Target Photo of group, play the music file corresponding with the scene label of picture group.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (11)
1. play a method for music based on image content, it is characterized in that, comprising:
According to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for described each picture component;
Determine the music file corresponding with the scene label of described picture group;
When showing the Target Photo of described picture group, play the music file corresponding with the scene label of described picture group.
2. according to claim 1ly play the method for music based on image content, it is characterized in that, describedly according to pre-conditioned, Target Photo in picture library is split at least one picture group, and comprise for described each picture component joins a scene labelling step:
Obtain and often open Target Photo in picture library;
The scene label that the characteristics of image utilizing the scene decision model that generates in advance to determine often to open described Target Photo is corresponding;
The described Target Photo of corresponding same scene label is defined as a picture group, described scene label is defined as the scene label of described picture group.
3. according to claim 1ly play the method for music based on image content, it is characterized in that, describedly according to pre-conditioned, Target Photo in picture library is split at least one picture group, and comprise for described each picture component joins a scene labelling step:
According to presetting a point set condition, the Target Photo in picture library is divided at least one picture group;
The scene decision model that generates in advance is utilized to determine scene label corresponding to the characteristics of image often opening Target Photo in described picture group;
For each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of Target Photo as described picture group.
4. that states according to claim 3 plays the method for music based on image content, it is characterized in that, describedly Target Photo in picture library is divided at least one picture group step comprises according to presetting a point set condition:
Determine photographing data or the shooting places of each Target Photo in picture library;
The described Target Photo of same for correspondence described photographing data is defined as a picture group, or the described Target Photo of same for correspondence described shooting places is defined as a picture group.
5. the method playing music based on image content according to claim 2 to 4 any one, it is characterized in that, described method also comprises:
Create scene label;
Obtain the given scenario picture corresponding with each scene label;
Extract the characteristics of image of given scenario picture corresponding to described each scene label;
Utilize and preset the characteristics of image of machine learning method to given scenario picture corresponding to described each scene label and train, generate described scene decision model.
6. play a device for music based on image content, it is characterized in that, comprising:
Grouping module, for Target Photo in picture library being split at least one picture group according to pre-conditioned, and joins a scene label for described each picture component;
Determination module, for determining the music file corresponding with the scene label of described picture group;
Playing module, for when showing the Target Photo of described picture group, plays the music file corresponding with the scene label of described picture group.
7. the device playing music based on image content according to claim 6, it is characterized in that, described grouping module comprises:
Obtaining submodule, often opening Target Photo for obtaining in picture library;
First decision sub-module, the scene label that the characteristics of image for utilizing the scene decision model generated in advance to determine often to open described Target Photo is corresponding;
First determines submodule, for the described Target Photo of corresponding same scene label is defined as a picture group, described scene label is defined as the scene label of described picture group.
8. the device playing music based on image content according to claim 6, it is characterized in that, described grouping module comprises:
Grouping submodule, for being divided at least one picture group according to presetting a point set condition by the Target Photo in picture library;
Second decision sub-module, determines scene label corresponding to the characteristics of image often opening Target Photo in described picture group for utilizing the scene decision model generated in advance;
Second determines submodule, for for each picture group, using the scene label of scene labels maximum for quantity corresponding for the characteristics of image of Target Photo as described picture group.
9., according to the device playing music based on image content that claim 8 is stated, it is characterized in that, described grouping submodule comprises:
3rd determines submodule, for determining photographing data or the shooting places of each Target Photo in picture library;
4th determines submodule, for the described Target Photo of same for correspondence described photographing data is defined as a picture group, or the described Target Photo of same for correspondence described shooting places is defined as a picture group.
10. the device playing music based on image content according to claim 7 to 9 any one, it is characterized in that, described device also comprises:
Creation module, for creating scene label;
Acquisition module, for obtaining the given scenario picture corresponding with each scene label;
Extraction module, for extracting the characteristics of image of given scenario picture corresponding to described each scene label;
Training module, for utilizing the characteristics of image of default machine learning device to given scenario picture corresponding to described each scene label to train, generates described scene decision model.
Play the device of music based on image content, it is characterized in that, comprising for 11. 1 kinds:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
According to pre-conditioned, Target Photo in picture library is split at least one picture group, and join a scene label for described each picture component;
Determine the music file corresponding with the scene label of described picture group;
When showing the Target Photo of described picture group, play the music file corresponding with the scene label of described picture group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410432694.6A CN104268150A (en) | 2014-08-28 | 2014-08-28 | Method and device for playing music based on image content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410432694.6A CN104268150A (en) | 2014-08-28 | 2014-08-28 | Method and device for playing music based on image content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268150A true CN104268150A (en) | 2015-01-07 |
Family
ID=52159672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410432694.6A Pending CN104268150A (en) | 2014-08-28 | 2014-08-28 | Method and device for playing music based on image content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268150A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881471A (en) * | 2015-05-28 | 2015-09-02 | 努比亚技术有限公司 | Information processing method and terminal equipment |
| CN105005595A (en) * | 2015-06-30 | 2015-10-28 | 广东欧珀移动通信有限公司 | Sound playing method, mobile terminal, server and system |
| CN105447150A (en) * | 2015-11-26 | 2016-03-30 | 小米科技有限责任公司 | Face album based music playing method and apparatus, and terminal device |
| CN105528428A (en) * | 2015-12-09 | 2016-04-27 | 深圳市金立通信设备有限公司 | Image display method and terminal |
| CN105631457A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and device for selecting picture |
| CN106297479A (en) * | 2016-08-31 | 2017-01-04 | 武汉木子弓数字科技有限公司 | A kind of song teaching method based on AR augmented reality scribble technology and system |
| CN108062522A (en) * | 2017-12-12 | 2018-05-22 | 广州德科投资咨询有限公司 | The performance pattern creating method and robot of a kind of robot |
| CN108920648A (en) * | 2018-07-03 | 2018-11-30 | 四川大学 | It is a kind of based on music-image, semantic relationship across mode matching method |
| CN109309862A (en) * | 2018-07-26 | 2019-02-05 | 浠诲嘲 | Multi-medium data editing system |
| CN109688426A (en) * | 2018-07-26 | 2019-04-26 | 浠诲嘲 | Multi-medium data edit methods |
| CN105631457B (en) * | 2015-12-17 | 2019-07-16 | 小米科技有限责任公司 | Select the method and device of picture |
| CN110489573A (en) * | 2019-07-30 | 2019-11-22 | 维沃移动通信有限公司 | Interface display method and electronic equipment |
| CN112199974A (en) * | 2019-07-08 | 2021-01-08 | Tcl集团股份有限公司 | Learning evaluation method, device and equipment |
| CN112825544A (en) * | 2019-11-21 | 2021-05-21 | 北京小米移动软件有限公司 | Picture processing method and device and storage medium |
| TWI774659B (en) * | 2016-03-25 | 2022-08-21 | 香港商阿里巴巴集團服務有限公司 | Image text recognition method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103700A (en) * | 2011-01-18 | 2011-06-22 | 南京邮电大学 | Land mobile distance-based image spam similarity-detection method |
| CN102932993A (en) * | 2012-10-26 | 2013-02-13 | 浙江大学 | Lamp under remote control of cell phone and control method of lamp |
| US8548249B2 (en) * | 2010-02-19 | 2013-10-01 | Sony Corporation | Information processing apparatus, information processing method, and program |
| CN103475789A (en) * | 2013-08-26 | 2013-12-25 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and control method thereof |
| CN103605992A (en) * | 2013-11-28 | 2014-02-26 | 国家电网公司 | Sensitive image recognizing method in interaction of inner and outer power networks |
| CN103824053A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Face image gender marking method and face gender detection method |
-
2014
- 2014-08-28 CN CN201410432694.6A patent/CN104268150A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8548249B2 (en) * | 2010-02-19 | 2013-10-01 | Sony Corporation | Information processing apparatus, information processing method, and program |
| CN102103700A (en) * | 2011-01-18 | 2011-06-22 | 南京邮电大学 | Land mobile distance-based image spam similarity-detection method |
| CN102932993A (en) * | 2012-10-26 | 2013-02-13 | 浙江大学 | Lamp under remote control of cell phone and control method of lamp |
| CN103475789A (en) * | 2013-08-26 | 2013-12-25 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and control method thereof |
| CN103605992A (en) * | 2013-11-28 | 2014-02-26 | 国家电网公司 | Sensitive image recognizing method in interaction of inner and outer power networks |
| CN103824053A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Face image gender marking method and face gender detection method |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881471A (en) * | 2015-05-28 | 2015-09-02 | 努比亚技术有限公司 | Information processing method and terminal equipment |
| CN105005595A (en) * | 2015-06-30 | 2015-10-28 | 广东欧珀移动通信有限公司 | Sound playing method, mobile terminal, server and system |
| EP3173969A1 (en) * | 2015-11-26 | 2017-05-31 | Xiaomi Inc. | Method, apparatus and terminal device for playing music based on a target face photo album |
| CN105447150A (en) * | 2015-11-26 | 2016-03-30 | 小米科技有限责任公司 | Face album based music playing method and apparatus, and terminal device |
| CN105447150B (en) * | 2015-11-26 | 2019-04-16 | 小米科技有限责任公司 | Method for playing music, device and terminal device based on face photograph album |
| US9953221B2 (en) | 2015-11-26 | 2018-04-24 | Xiaomi Inc. | Multimedia presentation method and apparatus |
| CN105528428A (en) * | 2015-12-09 | 2016-04-27 | 深圳市金立通信设备有限公司 | Image display method and terminal |
| CN105631457A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and device for selecting picture |
| CN105631457B (en) * | 2015-12-17 | 2019-07-16 | 小米科技有限责任公司 | Select the method and device of picture |
| TWI774659B (en) * | 2016-03-25 | 2022-08-21 | 香港商阿里巴巴集團服務有限公司 | Image text recognition method and device |
| CN106297479A (en) * | 2016-08-31 | 2017-01-04 | 武汉木子弓数字科技有限公司 | A kind of song teaching method based on AR augmented reality scribble technology and system |
| CN108062522A (en) * | 2017-12-12 | 2018-05-22 | 广州德科投资咨询有限公司 | The performance pattern creating method and robot of a kind of robot |
| CN108062522B (en) * | 2017-12-12 | 2020-03-06 | 广州德科投资咨询有限公司 | Robot performance mode generation method and robot |
| CN108920648A (en) * | 2018-07-03 | 2018-11-30 | 四川大学 | It is a kind of based on music-image, semantic relationship across mode matching method |
| CN108920648B (en) * | 2018-07-03 | 2021-06-22 | 四川大学 | Cross-modal matching method based on music-image semantic relation |
| CN109309862A (en) * | 2018-07-26 | 2019-02-05 | 浠诲嘲 | Multi-medium data editing system |
| CN109688426B (en) * | 2018-07-26 | 2020-02-07 | 深圳中琛源科技股份有限公司 | Multimedia data editing method |
| CN109688426A (en) * | 2018-07-26 | 2019-04-26 | 浠诲嘲 | Multi-medium data edit methods |
| CN112199974A (en) * | 2019-07-08 | 2021-01-08 | Tcl集团股份有限公司 | Learning evaluation method, device and equipment |
| CN110489573A (en) * | 2019-07-30 | 2019-11-22 | 维沃移动通信有限公司 | Interface display method and electronic equipment |
| CN112825544A (en) * | 2019-11-21 | 2021-05-21 | 北京小米移动软件有限公司 | Picture processing method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104268150A (en) | Method and device for playing music based on image content | |
| CN104268547A (en) | Method and device for playing music based on picture content | |
| CN105094760B (en) | A kind of picture indicia method and device | |
| CN105611413A (en) | Method and device for adding video clip class markers | |
| CN105095873A (en) | Picture sharing method and apparatus | |
| CN105302315A (en) | Image processing method and device | |
| CN105335712A (en) | Image recognition method, device and terminal | |
| CN112118395B (en) | Video processing method, terminal and computer readable storage medium | |
| CN104090741A (en) | Statistical method and device for electronic book reading | |
| CN105469056A (en) | Face image processing method and device | |
| CN104731880A (en) | Image ordering method and device | |
| CN105809174A (en) | Method and device for identifying image | |
| CN104112119A (en) | Face identification-based communication method and apparatus | |
| CN104754267A (en) | Video clip marking method, device and terminal | |
| CN105447150A (en) | Face album based music playing method and apparatus, and terminal device | |
| CN105045504A (en) | Image content extraction method and apparatus | |
| CN104991910A (en) | Album creation method and apparatus | |
| CN105335714A (en) | Photograph processing method, device and apparatus | |
| CN105512220A (en) | Image page output method and device | |
| CN104461348A (en) | Method and device for selecting information | |
| CN104216672A (en) | Display control method and display control device | |
| CN104809204A (en) | Picture processing method and picture processing device | |
| CN105205093B (en) | The method and device that picture is handled in picture library | |
| CN104715007A (en) | User identification method and device | |
| CN104702988A (en) | AV (Audio/Video) playing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150107 |