CN106067167A - Image processing method and device - Google Patents

Abstract

The present invention discloses an image processing method and device, wherein the image processing method comprises: obtaining an image to be processed; identifying a face region in the image; determining a position to be processed in the face region, wherein the position to be processed is the position where a facial foreign body is located; taking the facial central axis of the face region as the axis of symmetry, determining the symmetrical position of the position to be processed; replacing the image block of the position to be processed with the image block of the symmetrical position to obtain a processed image; and outputting the processed image. The technical solution provided by the present invention can effectively improve the effect of eliminating facial foreign bodies in an image.

Description

Image processing method and device

technical field

The present invention relates to the technical field of image processing, in particular to an image processing method and device.

Background technique

With the rapid development of smart terminals (such as smart phones, tablet computers, etc.), basically all smart terminals have a camera function, and the pixels of smart terminals are getting higher and higher, and the camera effect of some smart terminals is even as good as For card cameras, compared with professional camera equipment such as card cameras and SLR cameras, smart terminals with camera functions are more convenient to carry and use. Therefore, the public is more willing to use the camera function of smart terminals to take pictures.

At present, after a user uses a smart terminal to take a picture of a person, he usually performs a beautification process on the person in the captured photo, so that the photo after the beautification process is sent to a social network platform to share with friends and family members. In the existing beauty treatment process, foreign bodies (such as spots, acne or moles) on the face of the character can only be treated by means of dermabrasion, because the dermabrasion cannot be excessive (excessive dermabrasion will cause the details of the character's face to be blurred). cannot be seen clearly), therefore, the foreign matter on the face of the character can only be lightened by means of skin resurfacing, but the foreign matter on the face of the character cannot be completely eliminated.

Contents of the invention

The invention provides an image processing method and device, which are used to improve the effect of eliminating facial foreign objects in images.

The first aspect of the present invention relates to an image processing method, comprising:

Get the image to be processed;

Identify the face area in the above image;

Determining the position to be processed in the above-mentioned human face area, wherein the above-mentioned position to be processed is the position where the foreign body on the face is located;

Determining the symmetrical position of the above-mentioned position to be processed by taking the central axis of the face of the above-mentioned human face area as the axis of symmetry;

replacing the image block at the position to be processed with the image block at the symmetrical position above to obtain a processed image;

Output the above processed image.

Based on the first aspect of the present invention, in a first possible implementation manner, the determination of the position to be processed in the above-mentioned face area includes:

Receive a position selection operation input in the above-mentioned face area;

The position selected by the above position selection operation is determined as the position to be processed in the above human face area.

Based on the first aspect of the present invention, in a second possible implementation manner, the above-mentioned determination of the position to be processed in the above-mentioned face area includes:

Determining the non-facial features area in the above-mentioned face area;

Determining the location of the image region that satisfies the foreign object condition in the above-mentioned non-facial features region as the location to be processed in the above-mentioned face region;

Wherein, the above-mentioned foreign matter condition is: the average value of pixels in the image area is within a preset threshold range.

Based on the first aspect of the present invention, or the first possible implementation of the first aspect of the present invention, or the second possible implementation of the first aspect of the present invention, in the third possible implementation, the above-mentioned The image block at the position to be processed is replaced with the image block at the symmetrical position above, and the processed image is obtained, including:

Copy the image block at the symmetrical position above;

Paste the image blocks at the above-mentioned symmetrical positions to the above-mentioned to-be-processed positions and then synthesize the image to obtain a processed image.

Based on the first aspect of the present invention, or the first possible implementation of the first aspect of the present invention, or the second possible implementation of the first aspect of the present invention, in the fourth possible implementation, the above-mentioned identification The face area in the image, specifically:

When an input facial foreign object removal instruction is received, the human face area in the above image is identified.

A second aspect of the present invention relates to an image processing device, comprising:

An image acquisition unit, configured to acquire an image to be processed;

An identification unit, configured to identify the human face area in the image acquired by the above image acquisition unit;

The first determining unit is configured to determine the position to be processed in the above-mentioned human face area, wherein the above-mentioned position to be processed is the position where the foreign object on the face is located;

The second determination unit is used to determine the symmetrical position of the position to be processed determined by the first determination unit with the central axis of the face area as the axis of symmetry;

An image block replacement unit, configured to replace the image block at the position to be processed determined by the first determination unit with the image block at the symmetrical position determined by the second determination unit, to obtain a processed image;

An image output unit, configured to output the above-mentioned processed image.

Based on the second aspect of the present invention, in a first possible implementation manner, the above-mentioned first determination unit includes:

A sub-receiving unit, configured to receive a position selection operation input in the above-mentioned face area;

The first sub-determining unit is configured to determine the position selected by the position selection operation as the position to be processed in the human face area.

Based on the second aspect of the present invention, in a second possible implementation manner, the above-mentioned first determination unit includes:

The second sub-determining unit is used to determine the non-facial sense area in the above-mentioned human face area;

The third sub-determining unit is configured to determine the position of the image area that satisfies the foreign object condition in the non-features area determined by the second sub-determining unit as the position to be processed in the above-mentioned human face area;

Wherein, the above-mentioned foreign matter condition is: the average value of pixels in the image area is within a preset threshold range.

Based on the second aspect of the present invention, or the first possible implementation of the second aspect of the present invention, or the second possible implementation of the second aspect of the present invention, in the third possible implementation, the above image block Replacement units include:

A copying unit, configured to copy the image block at the symmetrical position determined by the second determining unit;

The pasting and combining unit is used to paste the image block at the symmetrical position copied by the copying unit to the position to be processed determined by the first determining unit, and then synthesize the image to obtain a processed image.

Based on the second aspect of the present invention, or the first possible implementation of the second aspect of the present invention, or the second possible implementation of the second aspect of the present invention, in a fourth possible implementation, the above image processing The device also includes: a beautification instruction receiving unit, configured to receive an input instruction for removing foreign objects on the face;

The recognition unit is specifically configured to: when the beautification instruction receiving unit receives the facial foreign object removal instruction, recognize the face area in the image acquired by the image acquisition unit.

It can be seen from the above that in the embodiment of the present invention, by identifying the face area in the image to be processed, and after determining the position to be processed (that is, the position of the foreign body on the face), the central axis of the face area is used as the axis of symmetry , determine the symmetrical position of the position to be processed, and replace the image block at the position to be processed with the image block at the symmetrical position, so as to eliminate the facial foreign body at the position to be processed. There is a certain degree of similarity between the block and the image block at the position to be processed. Therefore, replacing the image block at the position to be processed with an image block at a symmetrical position can improve the fit of the image. The method of processing the facial foreign objects at the position to be processed can effectively eliminate the facial foreign objects and improve the elimination effect of the facial foreign objects in the image.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is a schematic flow chart of an embodiment of the image processing method provided by the present invention;

FIG. 2 is a schematic structural diagram of an embodiment of an image processing device provided by the present invention.

detailed description

In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The embodiment of the present invention provides an image processing method, please refer to FIG. 1, the image processing method in the embodiment of the present invention includes:

Step 101, acquiring an image to be processed;

In the embodiment of the present invention, the image to be processed may be obtained from a photo library, or an image captured in real time may also be obtained as the image to be processed, which is not limited herein.

Step 102, identifying the face area in the above image;

In the embodiment of the present invention, face recognition is performed on the image acquired in step 101 to identify the face area in the above image. Specifically, the process of performing face recognition on an image and identifying a face area in the image can be implemented with reference to existing technologies, and will not be repeated here.

Optionally, after acquiring the image to be processed in step 101, wait for the user to input an instruction, and then process the image acquired in step 101 according to the instruction input by the user after receiving the instruction input by the user. Step 102 is specifically: when an input facial foreign body removal instruction is received, identify the face area in the image acquired in step 101 . Specifically, a face foreign object removal control may be provided, so that the user inputs the above-mentioned face foreign object removal instruction by triggering the face foreign object removal control. Of course, step 102 may also be executed after the image to be processed is acquired in step 101, which is not limited here.

Step 103, determining the position to be processed in the above-mentioned face area;

Wherein, the above-mentioned position to be processed is the position where the foreign body on the face is located.

In the embodiment of the present invention, foreign bodies on the face include but are not limited to: spots, acne and moles.

In an application scenario, a position selection operation input in the human face area is received; and the position selected by the position selection operation is determined as a position to be processed in the human face area. Optionally, the above position selection operation is specifically a click operation, that is, the user can select the position to be processed by clicking the position of the foreign body in the face area above, so that in step 103, the position clicked by the user is determined as The position to be processed in the above face region. Of course, the above-mentioned position selection operation can also be input in other ways, for example, the selection box can be moved by triggering a physical button, and the selection box can be moved to the position of the facial foreign object in the above-mentioned face area, and then input the "OK" command, and this At this time, the position selected by the selection box is determined as the position to be processed in the above-mentioned face area.

In another application scenario, since in the face area of the above image, the brightness of foreign objects on the face will be darker than the brightness of foreign objects on the face, therefore, in this application scenario, automatic face recognition can be adopted based on this principle. The way of foreign objects determines the position to be processed in the above-mentioned face area. Specifically, step 103 includes: determining the non-featured sense area in the above-mentioned human face area; determining the position of the image area satisfying the foreign object condition in the above-mentioned non-five sense area area as the position to be processed in the human face area; wherein, the above-mentioned foreign object The condition is: the average value of pixels in the image area is within a preset threshold range. It should be noted that the non-featured sense area in the above-mentioned face area refers to the area other than the eyes, ears, nose, tongue, and mouth in the above-mentioned face area. The facial features area of the above-mentioned human face area, and then the areas other than the aforementioned facial features area in the aforementioned human face area may be determined as non-facial features areas of the aforementioned human face area. The foregoing threshold range can be obtained through statistics of a large amount of experimental data, and the embodiment of the present invention does not specifically limit the foregoing threshold range.

Step 104, taking the central axis of the face of the above-mentioned face area as the axis of symmetry, determining the symmetrical position of the above-mentioned position to be processed;

In the embodiment of the present invention, the central axis of the face refers to the straight line that divides the human face area into the left half area and the second half area on average. The nose and mouth of the human face are located on the central axis of the face, and the left eye and The right eyes are located on both sides of the central axis of the face.

In step 104, the symmetric position of the position to be processed determined in step 103 is determined by taking the central axis of the face of the above-mentioned human face region as the axis of symmetry. It should be understood that the distance from the central point of the position to be treated to the central axis of the face is equal to the distance from the central point of the symmetrical position to the central axis of the face, and the shape and size of the position to be treated are equal to the shape and size of the symmetrical position unanimous.

Step 105, replacing the image block at the position to be processed with the image block at the symmetrical position above to obtain a processed image;

Optionally, in step 105, copy the above-mentioned image block at the symmetrical position, paste the above-mentioned image block at the above-mentioned symmetrical position on the above-mentioned position to be processed, and then synthesize an image to obtain a processed image. Alternatively, it is also possible to traverse the pixel values of each pixel point in the above-mentioned symmetrical position, and modify the pixel value of each pixel point in the above-mentioned to-be-processed position to the pixel value of the corresponding pixel point in the above-mentioned symmetrical position, so as to realize the processing of the above-mentioned to-be-processed The image block at the position is replaced by the image block at the above-mentioned symmetrical position. Of course, in the embodiment of the present invention, the image block at the position to be processed may also be replaced with the image block at the symmetrical position in other ways, which is not limited here.

Step 106, outputting the above-mentioned processed image;

In the embodiment of the present invention, the processed image obtained in step 105 is output.

Specifically, step 106 includes but is not limited to: outputting and displaying the above-mentioned processed image and outputting and storing the above-mentioned processed image.

It should be noted that the image processing method in the embodiment of the present invention may be specifically implemented by an image processing device, and the image processing device may be integrated in a smart terminal. The above-mentioned smart terminal is specifically a smart phone, a tablet computer or other terminals with image processing capability, which is not limited here.

It can be seen from the above that in the embodiment of the present invention, by identifying the face area in the image to be processed, and after determining the position to be processed (that is, the position of the foreign body on the face), the central axis of the face area is used as the axis of symmetry , determine the symmetrical position of the position to be processed, and replace the image block at the position to be processed with the image block at the symmetrical position, so as to eliminate the facial foreign body at the position to be processed. There is a certain degree of similarity between the block and the image block at the position to be processed. Therefore, replacing the image block at the position to be processed with an image block at a symmetrical position can improve the fit of the image. The method of processing the facial foreign objects at the position to be processed can effectively eliminate the facial foreign objects and improve the elimination effect of the facial foreign objects in the image.

Embodiment two

The embodiment of the present invention also provides an image processing device, please refer to FIG. 2, the image processing device 200 in the embodiment of the present invention includes:

An image acquisition unit 201, configured to acquire an image to be processed;

An identification unit 202, configured to identify the face area in the image acquired by the image acquisition unit 201;

The first determining unit 203 is configured to determine a position to be processed in the face area, wherein the position to be processed is a position where a foreign object on the face is located;

The second determination unit 204 is configured to determine the symmetric position of the position to be processed determined by the first determination unit, taking the central axis of the face region as the axis of symmetry;

An image block replacement unit 205, configured to replace the image block at the position to be processed determined by the first determining unit 203 with the image block at the symmetrical position determined by the second determining unit 204, to obtain a processed image;

An image output unit 206, configured to output the processed image.

Optionally, the first determining unit 203 includes: a sub-receiving unit, configured to receive a position selection operation input in the face area; a first sub-determining unit, configured to determine the position selected by the position selection operation is the position to be processed in the face area.

Optionally, the first determining unit 203 includes: a second sub-determining unit, configured to determine the non-facial features area in the face area; a third sub-determining unit, configured to determine the non-facial features determined by the second sub-determining unit The position of the image area satisfying the foreign matter condition in the facial features area is determined as the position to be processed in the face area; wherein, the foreign matter condition is: the average value of pixels in the image area is within a preset threshold range.

Optionally, the image block replacing unit in the embodiment of the present invention includes: a copying unit, configured to copy the image block at the symmetrical position determined by the second determining unit 204; Paste the image block at the symmetrical position to the position to be processed determined by the first determination unit 203 and then synthesize the image to obtain a processed image.

Optionally, the image processing device in the embodiment of the present invention further includes: a beautification instruction receiving unit, configured to receive an input facial foreign body removal instruction; the identification unit is specifically configured to: when the beautification instruction receiving unit receives When the face foreign object removal instruction is reached, the face area in the image acquired by the image acquisition unit 201 is recognized.

It should be noted that the image processing apparatus in the embodiment of the present invention may be integrated in a smart terminal. The above-mentioned smart terminal is specifically a smart phone, a tablet computer or other terminals with image processing capability, which is not limited here.

It should be understood that the functions of each functional module of the image processing method and device in the embodiment of the present invention can be specifically implemented according to the method in the above method embodiment, and the specific implementation process can refer to the relevant description in the above method embodiment, which is not described here. Let me repeat.

As can be seen from the above, the image processing device in the embodiment of the present invention recognizes the face area in the image to be processed, and after determining the position to be processed (that is, the position where the foreign object on the face is located), uses the facial center of the face area The axis is the axis of symmetry, determine the symmetrical position of the position to be processed, and replace the image block at the position to be processed with the image block at the symmetrical position, so as to eliminate the foreign body on the face at the position to be processed. On the one hand, due to the The image block at the symmetrical position has a certain degree of similarity with the image block at the position to be processed. Therefore, replacing the image block at the position to be processed with the image block at the symmetrical position can improve the fit of the image. On the other hand, using the replaced It can effectively eliminate facial foreign objects and improve the effect of removing facial foreign objects in images by using the method of processing instead of lightening.

In the several embodiments provided in this application, it should be understood that the disclosed system and method can be implemented in other ways.

It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence. Because of the present invention, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

The above is a description of an image processing method and device provided by the present invention. For those of ordinary skill in the art, according to the idea of the embodiment of the present invention, there will be changes in the specific implementation and application range. In summary , the contents of this specification should not be construed as limiting the present invention.

Claims (10)

1. an image processing method, it is characterised in that including:

Obtain pending image；

Identify the human face region in described image；

Determining the pending position in described human face region, wherein, described pending position is the position at face's foreign body place；

With the face axis of described human face region as axis of symmetry, determine the symmetric position of described pending position；

The image block of described pending position is replaced with the image block of described symmetric position, the image after being processed；

Export the image after described process.

Image processing method the most according to claim 1, it is characterised in that described determine in described human face region wait locate Reason position, including:

Receive the position of input in described human face region and select operation；

Described position is selected the pending position that the position selected by operation is defined as in described human face region.

Image processing method the most according to claim 1, it is characterised in that described determine in described human face region wait locate Reason position, including:

Determine the non-face region in described human face region；

The position at the image-region place meeting foreign body condition in described non-face region is defined as in described human face region Pending position；

Wherein, described foreign body condition is: the pixel average of image-region is in default threshold range.

4. according to the image processing method described in any one of claims 1 to 3, it is characterised in that described by described pending position The image block put replaces with the image block of described symmetric position, the image after being processed, including:

Copy the image block of described symmetric position；

The image block of described symmetric position is affixed to composograph after on described pending position, the image after being processed.

5. according to the image processing method described in any one of claims 1 to 3, it is characterised in that in the described image of described identification Human face region, particularly as follows:

When the face's foreign body receiving input eliminates instruction, identify the human face region in described image.

6. an image processing apparatus, it is characterised in that including:

Image acquisition unit, for obtaining pending image；

Recognition unit, for identifying the human face region in the image that described image acquisition unit obtains；

First determines unit, and for determining the pending position in described human face region, wherein, described pending position is face The position at foreign body place；

Second determines unit, for the face axis of described human face region as axis of symmetry, determining that described first determines unit Determined by the symmetric position of pending position；

Image block replacement unit, described for determining that by described first the image block of pending position determined by unit replaces with Second image block determining symmetric position determined by unit, the image after being processed；

Image output unit, the image after exporting described process.

Image processing apparatus the most according to claim 6, it is characterised in that described first determines that unit includes:

Son receives unit, selects operation for receiving the position of input in described human face region；

First son determines unit, for described position selects the position selected by operation be defined as treating in described human face region Processing position.

Image processing apparatus the most according to claim 6, it is characterised in that described first determines that unit includes:

Second son determines unit, for determining the non-face region in described human face region；

3rd son determines unit, for described second son determines the figure meeting foreign body condition in the non-face region that unit determines The pending position being defined as in described human face region as the position at place, region；

Wherein, described foreign body condition is: the pixel average of image-region is in default threshold range.

9. according to the image processing apparatus described in any one of claim 6 to 8, it is characterised in that described image block replacement unit Including:

Copy cell, for copying the described second image block determining symmetric position determined by unit；

Pasting synthesis unit, the image block of described symmetric position for described copy cell being copied affixes to described first true Composograph after on pending position determined by cell, the image after being processed.

10. according to the image processing apparatus described in any one of claim 6 to 8, it is characterised in that described image processing apparatus is also Including: U.S. face instruction reception unit, eliminate instruction for receiving face's foreign body of input；

Described recognition unit specifically for: when described U.S. face instruction reception unit receive described face foreign body eliminate instruction time, Identify the human face region in the image that described image acquisition unit obtains.