The content of the invention
In order to solve the above problems, the invention provides a kind of application program management platform based on image recognition, first
Determined whether to enter Jing Yin management mode according to the sleep state of terminal user, secondly, under Jing Yin management mode still just
The message sound of various application programs is often received, unlike, according to the volume of ambient sound, by various application programs
The size of message sound and the volume of ambient sound are adapted, and avoid bringing acoustically excessively dry to the people of rest
Disturb.
According to an aspect of the present invention, there is provided a kind of application program management platform based on image recognition, the platform
Including:
Prestore equipment, for prestoring default volume threshold and volume control table, the volume control table with
Live volume stores the broadcast sound volume of terminal device corresponding with each live volume value for index;
Live volume detection device, for the volume around detection terminal equipment to be exported as live volume value;
Sleep degree detection device, for the sleep state of the personnel detected and around outlet terminal equipment;
Threshold value compares equipment, and the sleep state for the personnel around terminal device for deep sleep or shallow sleeps state
When, by live volume value compared with default volume threshold;
Management and control equipment, for the comparative result based on live volume value Yu default volume threshold, determine terminal device
Application program volume management strategy.
More specifically, in the application program management platform based on image recognition, in addition to:
Image capture device, for obtaining and exporting high-definition image to carrying out high-definition data shooting around terminal device;
User input equipment, for the operation based on user, receive the default volume threshold of user's input and the volume control of adjustment
Table;
Wherein, user input equipment is connected with prestoring equipment, prestores what is prestored in equipment for updating
Default volume threshold and volume control table.
More specifically, in the application program management platform based on image recognition, in addition to:
Noise spot analytical equipment, for receiving high-definition image, scene is carried out to high-definition image and judged to determine high-definition image
The distribution situation of interior pixel pixel value, pixel value point is carried out to each pixel in high-definition image based on the distribution situation
Analyse to determine whether for noise spot;
Noise region analytical equipment, it is connected with noise spot analytical equipment, for receiving point of the noise spot analytical equipment
Result is analysed, each noise spot in high-definition image is formed into multiple noise regions, determines the area and shape of each noise region,
And by the Area summing of each noise region to obtain the noise region gross area;
Starting device is filtered, is connected respectively with noise region analytical equipment and adaptive-filtering equipment, in noise range
When the domain gross area is more than or equal to preset area threshold value, start adaptive-filtering equipment, be less than default face in the noise region gross area
During product threshold value, adaptive-filtering equipment is closed, high-definition image is input into sleep degree detection directly as pending image sets
It is standby;
Adaptive-filtering equipment, it is connected respectively with filtering starting device and sleep degree detection device, for being filtered
After starting device starts, adaptive-filtering processing is carried out to high-definition image to obtain pending image, and pending image is defeated
Enter to sleep degree detection device;
The adaptive-filtering equipment includes region split cells, module selecting unit, filtering execution unit and image sets
Close unit, region split cells is used to receiving the shape of each noise region, the shape based on each noise region it is several
What feature, splits into multiple benchmark subregions, being shaped as each benchmark subregion is square, circular by each noise region
Or it is linear, when being shaped as square, the size of each benchmark subregion is 3 × 3,5 × 5 or 7 × 7, when being shaped as circle,
The radius of each benchmark subregion is 3 pixels, 5 pixels or 7 pixels, and when being shaped as linear, each benchmark subregion is
One one-dimensional pixel set;
The sleep degree detection device is connected with adaptive-filtering equipment and filtering starting device respectively, for based on connecing
The pending image detection that receives simultaneously exports the sleep state of wherein human body target using sleeping as the personnel around terminal device
Dormancy state output;
Wherein, the module selecting unit is connected with the region split cells, for each noise region, for
Its each benchmark subregion after being split, medium filtering template corresponding to selection, the filtering execution unit and the module
Selecting unit connects, for each noise region, each benchmark subregion after being split for it, taking in selection
Value filtering template performs medium filtering, to obtain each sub-regions filter pattern, and each sub-regions filter pattern is combined into
Filtered noise region subgraph;
Described image assembled unit is connected with the filtering execution unit, for receiving each noise region subgraph, and
Non-noise region is combined to obtain pending image with each noise region subgraph;Wherein, it is multiple to make an uproar in high-definition image
Region outside the domain of sound area is non-noise region;
Wherein, the distribution situation of pixel pixel value is included for each pixel in high-definition image in high-definition image
Region determine the pixel value range that the pixel pixel value should belong to.
More specifically, in the application program management platform based on image recognition:
Comparative result of the management and control equipment based on live volume value Yu default volume threshold, determines terminal device
The volume management strategy of application program includes:When the live volume value is less than or equal to the default volume threshold, enter in meditation
Sound management mode, when the live volume value is more than the default volume threshold, exit Jing Yin management mode;
Wherein, the management and control equipment performs following operation in Jing Yin management mode:Based on the volume control table
It is determined that the broadcast sound volume of terminal device corresponding with the live volume value is to be used as target broadcast sound volume to export;
Wherein, comparative result of the management and control equipment based on live volume value Yu default volume threshold, determines terminal device
The volume management strategy of application program include:The target broadcast sound volume is sent to terminal device so that the target to be played
Broadcast sound volume of the volume as the application program of terminal device.
More specifically, in the application program management platform based on image recognition:The threshold value compares equipment and also used
When the sleep state of the personnel around terminal device is waking state, stop entering live volume value and default volume threshold
Row compares.
Embodiment
The embodiment of the application program management platform based on image recognition of the present invention is carried out below with reference to accompanying drawings
Describe in detail.
Currently, used with increasing and mobile network the popularization of the application program on the mobile terminals such as mobile phone,
People increasingly be unable to do without mobile phone, or even have mobile phone in arms before sleeping and be unwilling to rest.
Each application program on the mobile terminals such as mobile phone is when carrying out message, in order to remind user, can all send larger
Sound, if under user's sleep state, these sound can disturb the rest of people.Meanwhile the sound of application program is not
It can be adjusted, can not be adapted using its sound sent with external sound according to external sound so that once sound is sent,
Otherwise do not hear, otherwise especially wake up ear, disturb the life of people.
In order to overcome above-mentioned deficiency, the present invention has built a kind of application program management platform based on image recognition, has been used for
The sleep state of personnel around terminal device is deep sleep or shallow when sleeping state, by live volume value and default volume threshold
Value is compared, the comparative result based on live volume value Yu default volume threshold, determines the sound of the application program of terminal device
Measure management strategy so that message sound is adapted with live volume value.
Fig. 1 is the structure square frame of the application program management platform based on image recognition according to embodiment of the present invention
Figure, the platform include:
Prestore equipment, for prestoring default volume threshold and volume control table, the volume control table with
Live volume stores the broadcast sound volume of terminal device corresponding with each live volume value for index;
Live volume detection device, for the volume around detection terminal equipment to be exported as live volume value;
Sleep degree detection device, for the sleep state of the personnel detected and around outlet terminal equipment;
Threshold value compares equipment, and the sleep state for the personnel around terminal device for deep sleep or shallow sleeps state
When, by live volume value compared with default volume threshold;
Management and control equipment, for the comparative result based on live volume value Yu default volume threshold, determine terminal device
Application program volume management strategy.
Then, continue to carry out further the concrete structure of the application program management platform based on image recognition of the present invention
Explanation.
In the application program management platform based on image recognition, in addition to:
Image capture device, for obtaining and exporting high-definition image to carrying out high-definition data shooting around terminal device;
User input equipment, for the operation based on user, receive the default volume threshold of user's input and the volume control of adjustment
Table;
Wherein, user input equipment is connected with prestoring equipment, prestores what is prestored in equipment for updating
Default volume threshold and volume control table.
In the application program management platform based on image recognition, in addition to:
Noise spot analytical equipment, for receiving high-definition image, scene is carried out to high-definition image and judged to determine high-definition image
The distribution situation of interior pixel pixel value, pixel value point is carried out to each pixel in high-definition image based on the distribution situation
Analyse to determine whether for noise spot;
Noise region analytical equipment, it is connected with noise spot analytical equipment, for receiving point of the noise spot analytical equipment
Result is analysed, each noise spot in high-definition image is formed into multiple noise regions, determines the area and shape of each noise region,
And by the Area summing of each noise region to obtain the noise region gross area;
Starting device is filtered, is connected respectively with noise region analytical equipment and adaptive-filtering equipment, in noise range
When the domain gross area is more than or equal to preset area threshold value, start adaptive-filtering equipment, be less than default face in the noise region gross area
During product threshold value, adaptive-filtering equipment is closed, high-definition image is input into sleep degree detection directly as pending image sets
It is standby;
Adaptive-filtering equipment, it is connected respectively with filtering starting device and sleep degree detection device, for being filtered
After starting device starts, adaptive-filtering processing is carried out to high-definition image to obtain pending image, and pending image is defeated
Enter to sleep degree detection device;
The adaptive-filtering equipment includes region split cells, module selecting unit, filtering execution unit and image sets
Close unit, region split cells is used to receiving the shape of each noise region, the shape based on each noise region it is several
What feature, splits into multiple benchmark subregions, being shaped as each benchmark subregion is square, circular by each noise region
Or it is linear, when being shaped as square, the size of each benchmark subregion is 3 × 3,5 × 5 or 7 × 7, when being shaped as circle,
The radius of each benchmark subregion is 3 pixels, 5 pixels or 7 pixels, and when being shaped as linear, each benchmark subregion is
One one-dimensional pixel set;
The sleep degree detection device is connected with adaptive-filtering equipment and filtering starting device respectively, for based on connecing
The pending image detection that receives simultaneously exports the sleep state of wherein human body target using sleeping as the personnel around terminal device
Dormancy state output;
Wherein, the module selecting unit is connected with the region split cells, for each noise region, for
Its each benchmark subregion after being split, medium filtering template corresponding to selection, the filtering execution unit and the module
Selecting unit connects, for each noise region, each benchmark subregion after being split for it, taking in selection
Value filtering template performs medium filtering, to obtain each sub-regions filter pattern, and each sub-regions filter pattern is combined into
Filtered noise region subgraph;
Described image assembled unit is connected with the filtering execution unit, for receiving each noise region subgraph, and
Non-noise region is combined to obtain pending image with each noise region subgraph;Wherein, it is multiple to make an uproar in high-definition image
Region outside the domain of sound area is non-noise region;
Wherein, the distribution situation of pixel pixel value is included for each pixel in high-definition image in high-definition image
Region determine the pixel value range that the pixel pixel value should belong to.
In the application program management platform based on image recognition:
Comparative result of the management and control equipment based on live volume value Yu default volume threshold, determines terminal device
The volume management strategy of application program includes:When the live volume value is less than or equal to the default volume threshold, enter in meditation
Sound management mode, when the live volume value is more than the default volume threshold, exit Jing Yin management mode;
Wherein, the management and control equipment performs following operation in Jing Yin management mode:Based on the volume control table
It is determined that the broadcast sound volume of terminal device corresponding with the live volume value is to be used as target broadcast sound volume to export;
Wherein, comparative result of the management and control equipment based on live volume value Yu default volume threshold, determines terminal device
The volume management strategy of application program include:The target broadcast sound volume is sent to terminal device so that the target to be played
Broadcast sound volume of the volume as the application program of terminal device.
In the application program management platform based on image recognition:The threshold value compares equipment and is additionally operable to set in terminal
When the sleep state of the personnel of standby surrounding is waking state, stop live volume value compared with default volume threshold.
Fig. 2 is the step flow of the application management method based on image recognition according to embodiment of the present invention
Figure, methods described include:
Default volume threshold and volume control table is prestored, the volume control table stores by index of live volume
The broadcast sound volume of terminal device corresponding with each live volume value;
Volume around detection terminal equipment as live volume value to export;
Detect the sleep state of the simultaneously personnel around outlet terminal equipment;
The sleep state of personnel around terminal device is deep sleep or shallow when sleeping state, by live volume value with it is pre-
If volume threshold is compared;
Comparative result based on live volume value Yu default volume threshold, determine the volume pipe of the application program of terminal device
Reason strategy.
In the application management method based on image recognition, in addition to:
Shot to carrying out high-definition data around terminal device to obtain and export high-definition image;
Operation based on user, receive the default volume threshold of user's input and the volume control table of adjustment;Renewal is pre-
Default volume threshold and the volume control table first stored.
In the application management method based on image recognition, in addition to:
Using noise spot analytical equipment, for receiving high-definition image, scene is carried out to high-definition image and judged to determine high definition
The distribution situation of pixel pixel value in image, pixel is carried out to each pixel in high-definition image based on the distribution situation
Value is analyzed to determine whether as noise spot;
Using noise region analytical equipment, it is connected with noise spot analytical equipment, for receiving the noise spot analytical equipment
Analysis result, each noise spot in high-definition image is formed into multiple noise regions, determine each noise region area and
Shape, and by the Area summing of each noise region to obtain the noise region gross area;
Using filtering starting device, it is connected respectively with noise region analytical equipment and adaptive-filtering equipment, for making an uproar
When the sound area domain gross area is more than or equal to preset area threshold value, start adaptive-filtering equipment, be less than in the noise region gross area pre-
If during area threshold, closing adaptive-filtering equipment, high-definition image is input to sleep degree inspection directly as pending image
Measurement equipment;
Using adaptive-filtering equipment, it is connected respectively with filtering starting device and sleep degree detection device, in quilt
Filter after starting device starts, adaptive-filtering processing is carried out to high-definition image to obtain pending image, and by pending figure
As being input to sleep degree detection device;
The adaptive-filtering equipment includes region split cells, module selecting unit, filtering execution unit and image sets
Close unit, region split cells is used to receiving the shape of each noise region, the shape based on each noise region it is several
What feature, splits into multiple benchmark subregions, being shaped as each benchmark subregion is square, circular by each noise region
Or it is linear, when being shaped as square, the size of each benchmark subregion is 3 × 3,5 × 5 or 7 × 7, when being shaped as circle,
The radius of each benchmark subregion is 3 pixels, 5 pixels or 7 pixels, and when being shaped as linear, each benchmark subregion is
One one-dimensional pixel set;
The sleep state of personnel around the detection and outlet terminal equipment includes:Based on the pending image received
The sleep state for detecting and exporting wherein human body target is exported using the sleep state as the personnel around terminal device;
Wherein, the module selecting unit is connected with the region split cells, for each noise region, for
Its each benchmark subregion after being split, medium filtering template corresponding to selection, the filtering execution unit and the module
Selecting unit connects, for each noise region, each benchmark subregion after being split for it, taking in selection
Value filtering template performs medium filtering, to obtain each sub-regions filter pattern, and each sub-regions filter pattern is combined into
Filtered noise region subgraph;
Described image assembled unit is connected with the filtering execution unit, for receiving each noise region subgraph, and
Non-noise region is combined to obtain pending image with each noise region subgraph;In high-definition image, multiple noise ranges
Region outside domain is non-noise region;
The distribution situation of pixel pixel value includes being directed to institute of each pixel in high-definition image in high-definition image
The pixel value range that the pixel pixel value should belong to is determined in region.
In the application management method based on image recognition:
The comparative result based on live volume value Yu default volume threshold, determine the sound of the application program of terminal device
Amount management strategy includes:When the live volume value is less than or equal to the default volume threshold, into Jing Yin management mode, when
When the live volume value is more than the default volume threshold, Jing Yin management mode is exited;
Wherein, following operate is performed in Jing Yin management mode:Determined and the live sound based on the volume control table
The broadcast sound volume of terminal device corresponding to value as target broadcast sound volume to export;
The comparative result based on live volume value Yu default volume threshold, determine the sound of the application program of terminal device
Amount management strategy includes:The target broadcast sound volume is sent to terminal device so that the target broadcast sound volume to be set as terminal
The broadcast sound volume of standby application program.
In the application management method based on image recognition, the personnel around detection and outlet terminal equipment
Sleep state after, in addition to:
When the sleep state of personnel around terminal device is waking state, stop live volume value and default volume
Threshold value is compared.
In addition, image filtering, i.e., press down under conditions of image detail feature is retained as far as possible to the noise of target image
System, is indispensable operation in image preprocessing, and the quality of its treatment effect will directly influence successive image processing and divide
The validity and reliability of analysis.
Due to the imperfection of imaging system, transmission medium and recording equipment etc., digital picture is in its formation, transmission log mistake
Often polluted in journey by a variety of noises.In addition, some links in image procossing when the picture object inputted and are not so good as pre-
Also noise can be introduced when thinking in result images.These noises often show as one on image and cause the isolated of stronger visual effect
Pixel or block of pixels.Typically, noise signal it is uncorrelated to the object to be studied it occur with useless message form, upset figure
The observable information of picture.For data image signal, psophometer is either large or small extreme value, and these extreme values are acted on by plus-minus
On the true gray value of image pixel, the interference of bright, dim spot is caused to image, greatly reduces picture quality, influence image restoration,
The progress of the follow-up work such as segmentation, feature extraction, image recognition.A kind of wave filter for effectively suppressing noise is constructed to must take into consideration
Two basic problems:The noise in target and background can effectively be removed;Meanwhile can protect well image object shape,
Size and specific geometry and topological features.
One kind in conventional image filtering pattern is nonlinear filter, it is, in general, that when signal spectrum and noise frequency
Such as the noise as caused by mission nonlinear or non-gaussian be present and make an uproar when composing aliasing or when containing nonadditivity noise in signal
Sound etc.), traditional linear filter technology, such as Fourier conversion, while noise is filtered out, always blurred picture is thin in some way
Section (such as edge) and then the extraction property reduction for causing the positioning precision and feature as linear character.And nonlinear filter is
Based on a kind of Nonlinear Mapping relation to input signal, often a certain specific noise approx can be mapped as zero and retained
Signal wants feature, thus it can overcome the weak point of linear filter to a certain extent.
Using the application program management platform based on image recognition of the present invention, for nothing under sleep state in the prior art
The technical problem that terminal device sound and ambient sound are adapted by method, when the live volume value is less than or equal to the default sound
When measuring threshold value, into Jing Yin management mode, when the live volume value is more than the default volume threshold, Jing Yin management is exited
Pattern;The management and control equipment performs following operation in Jing Yin management mode:Based on volume control table determination and institute
The broadcast sound volume of terminal device corresponding to live volume value is stated to be exported as target broadcast sound volume;Wherein, management and control equipment
Comparative result based on live volume value Yu default volume threshold, determine the volume management strategy bag of the application program of terminal device
Include:The target broadcast sound volume is sent to terminal device using the application program by the target broadcast sound volume as terminal device
Broadcast sound volume so that the terminal device volume under user's sleep state is adapted with live volume value, solve above-mentioned
Technical problem.
It is understood that although the present invention is disclosed as above with preferred embodiment, but above-described embodiment and it is not used to
Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of change.Therefore, every content without departing from technical solution of the present invention, the technical spirit pair according to the present invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection
It is interior.