CN106503606A - face image adjusting system and face image adjusting method - Google Patents

Abstract

A face image adjusting system and a face image adjusting method are disclosed. The face image adjustment system comprises: an image acquisition module, a storage module and a processing module. The image acquisition module is used for acquiring an image file. The storage module is coupled to the image capturing module and used for storing at least one known face image and at least one blending parameter group corresponding to the at least one known face image. The processing module is coupled to the image capturing module and the storage module and is used for adjusting according to at least one blending parameter group to output a post-made face image. By the stored user's picture correction preference, the effect of directly applying the user's picture correction preference to the corresponding known face image can be achieved.

Description

Face image adjustment system and face image adjustment method

technical field

The invention relates to a human face image adjustment system and a human face image adjustment method. Specifically, the present invention relates to a face image adjustment system and a face image adjustment method that apply face recognition and record user behavior.

Background technique

At present, photo editing software and Meitu beauty application programs are very popular in the market. Users can easily specify the photo special effects they want to choose according to their facial images. For example, users apply photo editing software to apply thin face to their facial images. , whitening, skin smoothing, speckle removal, acne removal and other effects, and output the retouched face image.

However, even if there are multiple photos corresponding to the same user, it still needs to edit the photos or click on special effects one by one to achieve the desired effect of the user. In this way, this repetitive operation often causes the user to be frustrated. Trouble when retouching.

Contents of the invention

In order to solve the above problems, one aspect of the present invention provides a human face image adjustment system. The face image adjustment system includes: an image capture module, a storage module and a processing module. The image capturing module is used for obtaining an image file. The storage module is coupled to the image capture module, and is used for storing at least one known face image and at least one configuration parameter set corresponding to the at least one known face image. The processing module is coupled to the image capturing module and the storage module, and is used for identifying a first initial human face image corresponding to at least one known human face image in the image file, according to at least one corresponding to the at least one known human face image. The allocation parameter set adjusts the first initial face image conforming to at least one known face image to output a post-production face image.

Another aspect of the present invention is to provide a face image adjustment method. The face image adjustment method includes the following steps: obtaining an image file; storing at least one known face image and at least one allocation parameter corresponding to at least one known face image set; and when it is recognized that there is a first initial face image matching at least one known face image in the image file, adjust the at least one matching parameter set corresponding to at least one known face image according to at least one known face image The first initial face image to output a post-production face image.

By applying the above-mentioned face image adjustment system and face image adjustment method, the user can identify whether the face image is known in the image file, and use the recorded user image retouching preference to directly apply the image retouching preference to the In the corresponding known face images, the trouble of re-editing pictures for multiple photos of the same user is reduced.

Description of drawings

FIG. 1 is a block diagram of a face image adjustment system 100 according to an embodiment of the present invention;

FIG. 2 is a flowchart of a face image adjustment method 200 according to an embodiment of the present invention;

3A-3B are flowcharts of a face image adjustment method 300 according to an embodiment of the present invention;

4A-4C are schematic diagrams of the user interface of the face image adjustment method 300 according to an embodiment of the present invention;

FIG. 5 is a flowchart of a face image adjustment method 500 according to an embodiment of the present invention.

detailed description

Please refer to FIG. 1 , which is a block diagram of an image management system 100 according to an embodiment of the present invention. As shown in FIG. 1 , the image management system 100 includes an image capture module 110 , a storage system 120 and a processing module 130 . In various embodiments of the present invention, the image capturing module 110 is used to capture images, and may be a Charge Coupled Device (CCD) or a Complementary Metal-Oxide Semiconductor (CMOS). The storage module 120 is used for storing data, and may be, for example, a memory, a hard disk, a flash memory card, and the like. The processing module 130 is used to process various calculations, and can be implemented as an integrated circuit such as a microcontroller, a microprocessor, a digital signal processor, or an application specific integrated circuit, ASIC) or a logic circuit. Below, the image management system 100 in FIG. 1 will be combined with the face image adjustment method 200 in FIG. 2 to provide more specific details of the present invention.

FIG. 2 is a flowchart of a face image adjustment method 200 according to an embodiment of the present invention. The face image adjustment method 200 can be applied to the face image adjustment system 100 with the same or similar structure as shown in FIG. 1 . To simplify the description, the method will be described below by taking the face image adjustment system 100 in FIG. 1 as an example according to an embodiment of the present invention, but the present invention is not limited to this application.

It should be noted that the face image adjustment method 200 can be implemented through the face image adjustment system 100 in the aforementioned embodiments, and can also be implemented as a computer program and stored in a non-volatile computer-readable recording medium, And make the mobile device, computer or electronic device read the face image adjustment method 200 of the recording medium. The non-volatile computer-readable recording medium can be read-only memory, flash memory, floppy disk, hard disk, optical disk, pen drive, magnetic tape, database accessible by the network, or those skilled in the art can easily conceive of having the same function A non-volatile computer readable recording medium.

In addition, it should be understood that the steps of the method mentioned in this embodiment can be adjusted in sequence according to actual needs, and can even be executed simultaneously or partially simultaneously, unless the order is specifically stated.

As used herein, "first", "second", ... etc. do not specifically refer to the order or order, nor are they used to limit the present invention, but are only used to distinguish elements or components described with the same technical terms. Operation only.

In this embodiment, the face image adjustment method 200 includes the following steps.

In step S210, the image capture module 110 is used to obtain an image file. For example, the image capture module 110 located in the mobile device uses the front camera to take a picture of the user's own face, or uses the rear camera to take pictures of other people's faces.

In step S220, the storage module 120 is used for storing at least one known face image and at least one configuration parameter set corresponding to the at least one known face image. In one embodiment, the storage module 120 is coupled to the image capture module 110, and the step S220 can be performed before or after the step S210.

For example, the storage module 120 may store at least one face image in the storage module 120 in advance before acquiring the face image, and record the allocation parameter set corresponding to each face image. In one embodiment, the adjustment parameter set may include the brightness parameter value for adjusting the skin color, the smoothing parameter value for adjusting the smoothness of the face, the toning parameter value for adjusting the complexion of the face, the eye enlargement parameter value, Face acne parameter values, face speckle removal parameter values, face shape parameter values, etc. The effects corresponding to these parameter values can be achieved by various known image processing algorithms, such as: image filtering algorithm, smoothing image algorithm ... and so on, so I won't repeat them here. By applying the face image or making adjustments with these adjusted parameter values, the face image can be beautified. In one embodiment, the facial image adjustment system 100 can generate a configuration parameter set by recording multiple configuration parameter values selected by each user during each operation, or by manually setting and storing multiple configuration parameters. tuning parameter values to generate a tuning parameter set.

In step S230, the processing module 130 is used to identify whether there is a first initial face image matching at least one known face image in the image file. When the processing module 130 recognizes that there is a first initial face image matching at least one known face image in the image file, proceed to step S240; if the processing module 130 recognizes that there is no first initial face image matching at least one known face image in the image file When an initial face image is obtained, the process ends.

Since the same facial image usually has fixed facial features, the processing module 130 can obtain at least one facial feature of the first initial facial image by identifying facial features, and determine whether the image file has the first initial facial features. Face image. In one embodiment, the face feature may be a distance between the inner corners of the eyes, a distance between the left and right sides of the nose, a spot location, or a distance between the corners of the mouth. For example, the processing module 130 judges that the spot position and the distance between the left and right sides of the nose in the first initial face image conform to the data of a certain face image in the storage module 120, and then judges that the current first initial face image is a known person. face image.

In this way, the processing module 130 can identify whether the first initial human face image matches at least one known human face image stored in the storage module 120 according to at least one facial feature of the first initial human face image.

In another embodiment, if there are multiple face images in the image file, and some of them are known face images, while the other part is not, the user can choose to modify the image through the user interface Then in step S330, it is judged whether the selected face image is a known face image.

In step S240 , the processing module 130 adjusts the first initial face image matching the at least one known face image according to at least one configuration parameter set corresponding to the at least one known face image.

In one embodiment, the processing module 130 is coupled to the image capture module 110 and the storage module 120, and when the processing module 130 recognizes that the initial face image is a known face image, it indicates that there is a corresponding face image in the storage module 120 At least one tuning parameter set for . Therefore, the processing module 130 can automatically adjust the current user's face photo according to the pre-stored configuration parameter set corresponding to the face image, or suggest the user's preferred configuration parameter set for image modification settings, allowing users to The editor's editing steps are more concise.

Generally speaking, each user's photo editing habit is relatively fixed. For example, a certain user has a photo editing habit that prefers to enlarge eyes, while another user has a photo editing habit that prefers to remove freckles. For example, there is an allocation parameter set corresponding to a face image in the storage module 120, and the allocation parameter set is to set the smoothing parameter value to 50%, and set the eye enlargement parameter value to 20%, then the processing module 130 Based on these adjustment parameter values, the face image adjustment can be automatically performed or the user is recommended to use these adjustment parameter values to adjust the smoothing effect and the eye enlargement effect of the adjustment parameter set corresponding to the face image.

Next, in step S250, the processing module 130 outputs a post-production face image. In one embodiment, the processing module 130 displays on the display module 150 the face image after applying the configuration parameter set.

Through the above steps, a known face can be identified through the face image adjustment system 100 and the face image adjustment method 200, allowing the user to conveniently apply the pre-stored allocation parameter set to achieve the purpose of image retouching. By recording the user's image editing habits, when the processing module 130 recognizes a known user, it can automatically apply the stored adjustment parameter set to directly perform image editing, or recommend the user's preferred adjustment parameter value to generate Post-production facial images. Therefore, in the case that the user is the same person, it is not necessary to manually adjust various allocation parameter values for each image file.

Next, please refer to FIGS. 3A-3B and FIGS. 4A-4C together. FIGS. 3A-3B are flowcharts of a face image adjustment method 300 according to an embodiment of the present invention. 4A-4C are schematic diagrams of user interfaces of a face image adjustment method 300 according to an embodiment of the present invention. For the convenience of description, the user interface diagrams shown in FIGS. 4A-4C will be described together with the face image adjustment method 300 in FIGS. 3A-3B .

In this embodiment, the configuration parameter set can be an automatic configuration parameter value or a user configuration parameter value, or both an automatic configuration parameter value and a user configuration parameter value, and both the automatic configuration parameter value or the user configuration parameter value have at least one Adjust parameter values.

Wherein, steps S310-S330 and S350 in FIG. 3A-FIG. 3B are the same as steps S210-S230 and S250 in FIG. 2 respectively, so they will not be described in detail below.

In step S330, after the processing module 130 determines that there is a first initial face image (such as shown in FIG. 4A ) matching at least one known face image in the recognized image file, it proceeds to step S341. In one embodiment, when the processing module 130 determines that there is no first initial face image matching at least one known face image in the recognized image file, it enters step S361 of FIG. 3B , and step S361 will be described in subsequent paragraphs of the specification.

In step S341, the processing module 130 reads the automatic allocation parameter value of the known face image corresponding to the first initial human face image from the storage module 120, and loads the automatic allocation parameter value corresponding to the known face image. In one embodiment, the automatic configuration parameter value is at least one configuration parameter value preferred or commonly used by the user corresponding to the known face image, and the at least one configuration parameter value is stored in the storage module 120 in advance, for example, A face speckle removal parameter value.

In step S343, the processing module 130 determines whether the parameter value configured by the user is received. If the processing module 130 determines that the user-adjusted parameter value has been received, then enter step S345; if the processing module 130 determines that the user-adjusted parameter value has not been received, then enter step S347. In one embodiment, the processing module 130 can receive the user-configured parameter value currently input by the user for the face image through a user interface, for example, the user inputs a face shape parameter value and One-eye enlargement parameter value, so that the user can flexibly fine-tune the image retouching effect manually for the current face image.

In step S345 , when the processing module 130 determines that the user-adjusted parameter value is received, the first initial face image is adjusted by loading the automatically-adjusted parameter value and the user-adjusted parameter value. In one embodiment, as shown in FIG. 4A , the processing module 130 adjusts the first initial human face image F1 by loading the automatically adjusted parameter values, such as facial speckle removal parameter values, so that the adjusted human face The image F2 achieves the speckle removal effect (as shown in FIG. 4B ). In addition, the processing module 130 further loads user-configured parameter values, such as face shape parameter values and eye enlargement parameter values, to adjust the face image F2, so that the adjustment The final face image F3 achieves the beautification effect of freckle removal, face thinning and eye enlargement (as shown in FIG. 4C ).

On the other hand, in step S347, when the processing module 130 judges that the parameter value assigned by the user has not been received, the first initial facial image is directly adjusted by automatically adjusting the parameter value, for example, as shown in FIG. 4A, the processing module 130 passes Load the automatically adjusted parameter value, for example, the face speckle removal parameter value, to adjust the first initial face image F1, and the adjusted face image F2 can achieve the speckle removal effect (as shown in FIG. 4B ). In this way, in the case of not receiving the parameter value adjusted by the user, the processing module 130 can still automatically adjust the face image according to the automatically adjusted parameter value stored in the storage module 120 in advance, so that the face image corresponding to the same user can be adjusted. Multiple face images are automatically retouched according to the user's preference or a pre-set method to reduce repetitive retouching operations.

Next, in step S350, the processing module 130 outputs the post-production face image.

As can be seen from the above, through the application of automatic allocation parameter values, the face image adjustment system 100 can automatically recommend the user's preferred or appropriate beautification effect according to the known user behavior and the pre-stored allocation parameter set, so that Users can complete image retouching in simple steps. On the other hand, users can also input user-adjusted parameters through the user interface to adjust the current face image, thereby making the image retouching operation more efficient. elasticity.

On the other hand, in an embodiment, the unknown face image in the image file can be further processed. In step S330 of FIG. 3A , if the processing module 130 determines that there is no first initial face image matching at least one known face image in the recognized image file, then enter step S361 of FIG. 3B .

In step S361 , the processing module 130 identifies whether there is another original face image in the image file that does not match at least one known face image. In other words, in step S361 , the processing module 130 further determines whether there is another human face image in the image file, and the other human face image is not a known human face image.

In step S363 , the processing module 130 receives the user configuration parameter value for adjusting the other initial face image, and stores the other initial face image and the user configuration parameter value in the storage module 120 . In one embodiment, the processing module 130 can record the preferences of the other user in the current picture editing, for example, the face shape parameter values for thinning the face or chin, the parameter values for removing bags under the eyes, and the parameter values for Parameter values for scar removal, etc.

Therefore, when the processing module 130 judges that there is an unknown face image in the image file, it can store the unknown face image and its user-configured parameter values, so that when the face image is captured again, the processing The module 130 can recognize the face image, and recommend the user to adjust parameter values.

Through this method, the face image adjustment system 100 can establish a large number of user face databases, and automatically recommend appropriate image retouching effects according to the configuration parameter sets corresponding to each face in the facial database.

Please refer to FIG. 5 , which is a flowchart of a method 500 for adjusting a face image according to an embodiment of the present invention. In this embodiment, steps S510 - S540 may be further included after step S350 in FIG. 1 , and these steps will be described in detail below.

In step S510, the processing module 130 is also used to determine whether the post-production face image is selected. In one embodiment, the user can choose whether to use the post-production face image through a user interface. If the processing module 130 judges that the post-production face image is selected, go to step S520; if the processing module 130 judges that the post-production face image is not selected, go to step S540.

In step S540 , the first initial face image is displayed through the display module 150 coupled to the processing module 130 .

On the other hand, in step S520 , the processing module 130 stores the post-production face image in the storage module 120 .

In addition, in one embodiment, step S530 can be optionally performed to transmit the post-production face image stored in the storage module 120 to an Internet through the transmission module 140 coupled to the processing module 130 . In this way, the post-production face image can be sent to other applications or web pages through the Internet, such as Facebook (Face Book), Line, WeChat, etc., so that the post-production face image can be shared with multiple applications program.

Thereby, by applying the face image adjustment system and the face image adjustment method of the present invention, after the face image adjustment system recognizes a known user, it is more convenient to use the stored deployment parameter group to directly modify the image Or recommend the user's preferred adjustment parameter value to generate a post-production face image, reduce the trouble of repeatedly selecting the adjustment parameter value one by one for multiple face images corresponding to the same user, and meet the user's more convenient image editing needs .

Although the present invention has been disclosed above with the embodiments, it is not intended to limit the present invention. Any skilled person can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of protection should be based on the scope defined by the appended claims.

Claims (18)

1. a kind of face image adjusts system, it is characterised in that include：

One image acquisition module, in order to obtain an image file；

One storage module, is coupled to the image acquisition module, in order to store at least known to one face image and To should at least known to one face image at least one allotment parameter group；And

One processing module, is coupled to the image acquisition module and the storage module, picks out the image in order to work as Have in file and meet this at least known to one during one first Initial Face image of face image, according to this at least The corresponding at least one allotment parameter group adjustment of face image known to meets the face image at least known to The first Initial Face image, with face image processed after exporting.

2. face image according to claim 1 adjusts system, it is characterised in that at least one tune With parameter group be an automatic governing parameter value and a user allotment parameter value, and the automatic governing parameter value or The user allotment parameter value has at least one allotment parameter value.

3. face image according to claim 2 adjusts system, it is characterised in that the processing module Also in order to when pick out in the image file do not have meet this at least known to one face image one second at the beginning of During beginning face image, receive and parameter value is allocated in order to adjust the user of the second Initial Face image, and Second face image is just made to be stored in the storage module with user allotment parameter value this.

4. face image according to claim 2 adjusts system, it is characterised in that at least one tune It is a brightness parameter value, a smoothing parameter value or a toning parameter value with parameter value.

5. face image according to claim 2 adjusts system, it is characterised in that when the process mould When block judges to receive the user allotment parameter value, by being loaded into the automatic governing parameter value and the user Allotment parameter value adjusts the first Initial Face image.

6. face image according to claim 1 adjusts system, it is characterised in that the processing module Recognize to judge whether there is in the image file the first Initial Face image and take through a face characteristic An at least face characteristic of the first Initial Face image is obtained, an at least face characteristic is between an inner side canthus Away from, a wing of nose left and right sides spacing, a speckle displacement or a corners of the mouth spacing.

7. face image according to claim 6 adjusts system, it is characterised in that the processing module Further according to an at least face characteristic for the first Initial Face image recognizing first Initial Face Whether image accords with the face image at least known to of storage module storage.

8. face image according to claim 1 adjusts system, it is characterised in that the processing module Also in order to judging whether the rear face image processed is chosen；If the processing module judges the rear face image quilt processed During selection, the rear face image processed is stored in the storage module.

9. face image according to claim 7 adjusts system, it is characterised in that also include：

One transport module, is coupled to the processing module, in order to by the rear face processed stored by the storage module Image is transmitted in a world-wide web；

One display module, is coupled to the processing module, judges the rear face image processed in order to work as the processing module When not selected, show the first Initial Face image.

10. a kind of face image method of adjustment, it is characterised in that include：

Obtain an image file；

Storage at least known to one face image and to should at least known to one face image at least one allotment Parameter group；And

There is in the image file the one first initial people for meeting the face image at least known to when picking out During face image, this is met according to the corresponding at least one allotment parameter group adjustment of the face image known at least The first Initial Face image of face image at least known to one, with face image processed after exporting.

11. face image methods of adjustment according to claim 10, it is characterised in that this at least one Allotment parameter group is that an automatic governing parameter value and a user allocate parameter value, and the automatic governing parameter value Or the user allotment parameter value has at least one allotment parameter value.

12. face image methods of adjustment according to claim 11, it is characterised in that also include：

When pick out in the image file do not have meet this at least known to one face image one second initial During face image, receive and parameter value is allocated in order to adjust the user of the second Initial Face image；And

Storing this second just makes face image with user allotment parameter value.

13. face image methods of adjustment according to claim 11, it is characterised in that this at least one Allotment parameter value is a brightness parameter value, a smoothing parameter value or a toning parameter value.

14. face image methods of adjustment according to claim 11, it is characterised in that also include：

When judging to receive the user allotment parameter value, made with this by being loaded into the automatic governing parameter value User's allotment parameter value adjusts the first Initial Face image.

15. face image methods of adjustment according to claim 10, it is characterised in that also include：

Recognize to judge whether there is the first Initial Face image in the image file through a face characteristic And at least face characteristic of the first Initial Face image is obtained, an at least face characteristic is branch hole in Angular separation, a wing of nose left and right sides spacing, a speckle displacement or a corners of the mouth spacing.

16. face image methods of adjustment according to claim 15, it is characterised in that also include：

According to an at least face characteristic for the first Initial Face image recognizing the first Initial Face shadow It seem no face image at least known to for according with storage module storage.

17. face image methods of adjustment according to claim 16, it is characterised in that also include：

Judge whether the rear face image processed is chosen；If the processing module judges that the rear face image processed is selected When selecting, the rear face image processed is stored in the storage module.

18. face image methods of adjustment according to claim 16, it is characterised in that also include：

The rear face image processed is transmitted in a world-wide web；

When the processing module judges that the rear face image processed is not selected, show the first Initial Face shadow Picture.