CN105933613A - Image processing method, device and mobile terminal - Google Patents

Abstract

The invention discloses an image processing method and device and a mobile terminal. The method comprises the following steps: after the mobile terminal is in a shooting mode, determining a preselected object based on a live-action picture frame in a camera preview interface; determining an object type of the preselected object based on a depth value of the preselected object in the live-action picture frame; if the object type of the preselected object is in accordance with a preset type, determining the preselected object as a target object to be processed; and performing effect enhancement processing on the target object based on augmented reality. By using the method, the target object meeting the preset conditions can be selected in the shot image, and the augmented reality technology is fused into the shooting function of the mobile terminal, so that the aim of enhancing the effect of the selected target object in real time based on the augmented reality technology is fulfilled, the image processing process is simplified, the shot image achieves the expected effect of a user, and the user experience is improved.

Description

Image processing method, device and mobile terminal

technical field

Embodiments of the present invention relate to the technical field of image processing, and in particular, to an image processing method, device, and mobile terminal.

Background technique

With the development and innovation of electronic technology, more and more electronic products appear in people's lives, and mobile terminals have become one of the most popular electronic products. With the wide application of mobile terminals, functional applications integrated on mobile terminals There are also more and more functions, such as shooting functions, navigation functions, and multimedia playback functions of mobile terminals.

Generally, when shooting images based on the shooting function of a mobile terminal, in many cases, the actual captured images cannot meet the user's expected effect, and it is often necessary to beautify the image, resulting in the ability to beautify the image. Image beautification method.

However, based on the existing image beautification methods, it is often only possible to perform post-beautification processing on the captured images, and cannot perform image beautification in real time during the image capture process. Some images are enhanced.

Contents of the invention

The purpose of the present invention is to provide an image processing method, device and mobile terminal to achieve the purpose of enhancing the effect of the target object to be processed in the captured image in real time when the image is captured.

On the one hand, an embodiment of the present invention provides a method for image processing, including:

After the mobile terminal is in the shooting mode, the preselected object is determined based on the real scene frame in the camera preview interface;

determining an object type of the preselected object based on a depth value of the preselected object in the real scene frame;

If the object type of the preselected object conforms to the preset type, then determining the preselected object as the target object to be processed;

Perform effect enhancement processing on the target object based on augmented reality.

On the other hand, an embodiment of the present invention provides an image processing device, including:

The preselected object determination module is used to determine the preselected object based on the real scene frame in the camera preview interface after the mobile terminal is in the shooting mode;

An object type determination module, configured to determine the object type of the preselected object based on the depth value of the preselected object in the real scene frame;

a target object determining module, configured to determine the pre-selected object as the target object to be processed when the object type of the pre-selected object conforms to a preset type;

The augmented reality processing module is configured to perform effect enhancement processing on the target object based on augmented reality.

In yet another aspect, an embodiment of the present invention further provides a mobile terminal, where the mobile terminal integrates the image processing apparatus provided in the embodiment of the present invention.

Embodiments of the present invention provide an image processing method, device, and mobile terminal. The method of the present invention can be summarized as follows: firstly, after the mobile terminal is in the shooting mode, the preselected object is determined based on the real scene frame displayed in the camera preview interface, Then the object type of the pre-selected object is determined based on the depth of field value, and the target object meeting the conditions is determined based on the object type of the pre-selected object, and finally the determined target object is enhanced based on augmented reality. Using this method, the target object that meets the preset conditions can be selected in the captured image, and the augmented reality technology is integrated into the shooting function of the mobile terminal, so as to realize the real-time monitoring of the selected target object based on the augmented reality technology. The purpose of enhancing the effect is to simplify the image processing process and make the captured image achieve the expected effect of the user, thereby improving the user experience.

Description of drawings

FIG. 1 is a schematic flowchart of an image processing method provided in Embodiment 1 of the present invention;

FIG. 2 is a schematic flowchart of an image processing method provided in Embodiment 2 of the present invention;

FIG. 3a is a schematic flowchart of an image processing method provided by Embodiment 3 of the present invention;

Fig. 3b is an example diagram of determining a target object in a real scene frame of a camera preview interface;

Fig. 3c is another example diagram of determining a target object in a real scene frame of a camera preview interface;

FIG. 4 is a structural block diagram of an image processing device provided by Embodiment 4 of the present invention.

detailed description

The technical solution of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

Embodiment one

FIG. 1 is a schematic flowchart of an image processing method provided by Embodiment 1 of the present invention. This method is applicable to the case where the effect enhancement processing is performed on the captured image when the user uses the mobile terminal to take pictures, and can be executed by an image processing device, wherein the device can be implemented by software and/or hardware, and is generally integrated in the mobile terminal .

As shown in FIG. 1, an image processing method provided by Embodiment 1 of the present invention specifically includes the following operations:

S101. After the mobile terminal is in a shooting mode, determine a preselected object based on a real-scene picture frame in a camera preview interface.

In this embodiment, the mobile terminal may specifically refer to smart electronic devices with a camera function, such as mobile phones, notebooks, and tablet computers. In this embodiment, the fact that the mobile terminal is in the shooting mode may specifically be understood as a mode in which the mobile terminal performs image shooting based on the camera after starting the shooting application. Specifically, the camera preview interface can be understood as an interface capable of displaying the real scene captured by the camera of the mobile terminal in real time. Generally, the captured real scene is displayed in the camera preview interface in the form of picture frames.

In this embodiment, the pre-selected object may specifically be understood as an image selected based on a set condition in a real-scene frame and can be used as a target object for effect enhancement. Wherein, the preselected objects may be one or more. The setting condition may be to pre-set image features of the target object to be enhanced (such as feature points such as color, shape, or size of the object to be enhanced), thereby determining a preselected object that can be used as the target object.

S102. Determine an object type of the preselected object based on a depth value of the preselected object in the real picture frame.

In this embodiment, the real-scene frame in the camera preview interface has a depth of field value. Specifically, the depth value that can clearly display the real scene in the picture frame based on the camera capturing the real scene can be determined as the depth value of the captured real picture frame, and when the depth value that can clearly show the scene is small, it can be considered that the captured real picture frame The depth of field value is small, and conversely, when the depth value that can clearly display the scene is large, it can be considered that the depth of field value of the captured real scene frame is large. Generally, the adjustment of the depth of field value can be realized by focusing adjustment during image shooting, or by synthesizing at least two captured frames of the same real scene.

In this embodiment, for a real-scene picture frame with a depth value, the depth of field value of the image displayed in the real-scene picture frame can also be determined. Generally, the depth of field value of the image displayed in the real-scene picture frame can be understood is the depth value of the image displayed in the real picture frame, when the depth value of the image displayed in the real picture frame exceeds the set value, the image can be considered as a stereoscopic image, and its object type is stereoscopic; When the depth value of the image displayed in the real scene frame does not exceed the set value, the image can be considered as a planar image, and the object type is planar. It should be noted that the higher the depth of field value of the real picture frame, the easier it is to determine the depth of field value of the image displayed in the real picture frame.

In addition, for an image in a real scene frame, if the image is a real object in reality, the image is generally displayed in a stereoscopic form in the real scene frame and the depth of field value is higher than a preset value. If the image exists in In the photo or poster, when the image existing in the photo or poster is captured again, the image is displayed in a plane form in the real picture frame and the depth of field value is lower than the preset value. Therefore, the object type of the image can be determined by determining the field depth value of the image in the real picture frame.

S103. If the object type of the preselected object conforms to the preset type, determine the preselected object as the target object to be processed.

In this embodiment, the target object to be processed needs to be preset. Specifically, the selection condition of the target object to be processed can be preset. The selection condition can be used to determine the pre-selected object, and then it can also be preset The object type of the target object to be processed is set, and subsequently whether the preselected image is the target object to be processed can be determined by determining the object type of the preselected object. Exemplarily, if the preset object type of the target object to be processed is stereotype, after determining whether the object type of the preselected object is stereotype, it may be determined whether the preselected object is the target object to be processed.

S104. Perform effect enhancement processing on the target object based on augmented reality.

It should be noted that augmented reality (Augmented Reality, referred to as AR) is a technology that calculates the position and angle of the camera image in real time and adds the corresponding image. The goal of this technology is to put the virtual world on the screen. world and interact with it. With the wide application of mobile terminals, augmented reality technology is gradually integrated into many functional applications of mobile electronic devices.

In this embodiment, the augmented reality can be integrated into the photographing function of the mobile terminal, so that the effect or scene can be enhanced in real time on the photographed image based on the augmented reality technology when photographing. In this embodiment, based on the augmented reality technology, effect enhancement is performed on the target object determined in the real-scene picture frame, so as to achieve the expected effect of image processing.

In the image processing method provided by Embodiment 1 of the present invention, firstly, after the mobile terminal is in the shooting mode, the preselected object is determined based on the real scene frame displayed in the camera preview interface, and then the object type of the preselected object is determined based on the depth of field value, and The qualified target object is determined based on the object type of the preselected object, and finally the determined target object is enhanced based on the augmented reality. Using this method, the target object that meets the preset conditions can be selected in the captured image, and the augmented reality technology is integrated into the shooting function of the mobile terminal, so as to realize the real-time monitoring of the selected target object based on the augmented reality technology. The purpose of enhancing the effect is to simplify the image processing process and make the captured image achieve the expected effect of the user, thereby improving the user experience.

Embodiment two

Fig. 2 is a schematic flowchart of an image processing method provided by Embodiment 2 of the present invention. Embodiment 2 of the present invention is optimized based on the above-mentioned embodiment. In this embodiment, a step is also optimized and added: acquire The current picture frames captured by at least two cameras on the Internet; image synthesis processing is performed on the at least two current picture frames captured respectively to synthesize real-world picture frames satisfying the preset depth of field range; and the real-world picture frames are displayed on the In the camera preview interface.

As shown in Figure 2, an image processing method provided by Embodiment 2 of the present invention specifically includes the following operations:

S201. After the mobile terminal is in a shooting mode, acquire current picture frames respectively captured by at least two cameras on the mobile terminal.

In this embodiment, at least two cameras are used to capture picture frames of the same picture. Exemplarily, the at least two cameras may be dual cameras arranged in parallel; generally, the lens settings of the at least two cameras used are often different, some are long-angle lenses, some are wide-angle lenses, so when based on the above-mentioned multiple cameras When capturing the same picture, each camera has different capture points when capturing the same picture. Some cameras focus on capturing the outline of the image to be shot, and only capture in black and white, so that the close-up can be clearly captured And the image of the distant view retains more details. Some cameras focus on capturing the color of the image to be captured, and only render the color to ensure the authenticity of the color.

S202. Perform image composition processing on at least two current picture frames captured respectively, so as to synthesize real scene picture frames satisfying a preset depth of field range.

In this embodiment, when at least two real-scene picture frames of the same picture are captured based on at least two cameras, since the focus of each captured real-scene picture frame is different, when performing image synthesis on these real-scene picture frames, the The new real-action picture frame not only retains a clear image, but also highlights more image details (clearly highlights the details of the distant view and the near view, and increases the depth of field value of the real-action picture frame).

In this embodiment, in order to more easily determine the depth of field value of the image in the real scene picture frame, it is necessary to ensure that the field depth value of the real scene picture frame can be within a preset depth of field range. Based on the above image synthesis processing, real-scene picture frames satisfying the preset depth-of-field range can be obtained.

S203. Display the real scene frame in the camera preview interface.

In this embodiment, after image composition processing is performed on at least two captured real-scene picture frames, the formed real-scene picture frames satisfying a preset depth of field range may be displayed in the camera preview interface.

It should be noted that the process of each camera capturing real-world image frames and at least two composite processing of real-life image frames is extremely short-lived. You can see the composited real-life picture frame in .

S204. Determine a pre-selected object based on the real scene image frame in the camera preview interface.

Exemplarily, the real-scene picture frame is a picture frame formed through image synthesis processing, and a preselected object that can be used as a target object can be determined based on a set image attribute in the picture frame.

S205. Determine an object type of the preselected object based on a depth value of the preselected object in the real scene picture frame.

Exemplarily, since the depth of field value of the real scene picture frame formed by the image synthesis process conforms to the preset depth of field range, when the depth of field value of the real scene picture frame is within the preset depth of field range, it is easy to determine Depth of field value for preselected objects.

Exemplarily, when the depth of field value of the image in the real picture frame is greater than the set value, the image may be considered as a stereoscopic image, and the corresponding object type may be stereoscopic.

S206. If the object type of the preselected object conforms to the preset type, determine the preselected object as the target object to be processed.

Exemplarily, after the object type of the pre-selected object is determined based on step S205, it can be determined whether the object type conforms to the preset type, assuming that the preset type is three-dimensional, then the pre-selected object whose object type is three-dimensional can be regarded as to be processed target audience.

S207. Perform effect enhancement processing on the target object based on augmented reality.

Exemplarily, the augmented reality technology may be integrated into the shooting function of the mobile terminal, so as to enhance the effect of the determined target object to be enhanced when shooting based on the mobile terminal.

An image processing method provided in Embodiment 2 of the present invention embodies the process of determining a real-scene picture frame conforming to a preset depth of field range, that is, captures a real-scene picture frame through at least two cameras, and combines the captured current picture frames To determine the live-action frame displayed in the camera preview interface that conforms to the preset depth-of-field range. Using this method, the depth of field value of the pre-selected object can be quickly determined and the corresponding object type can be determined based on the depth of field value of the pre-selected object, so that the target object to be enhanced can be accurately and quickly determined. In addition, the augmented reality technology is integrated into the mobile terminal In the shooting function of the camera, the purpose of enhancing the effect of the selected target object in real time based on augmented reality technology is achieved, which not only simplifies the image processing process, but also enables the captured image to achieve the desired effect of the user, improving the user experience. .

Embodiment three

Fig. 3a is a schematic flowchart of an image processing method provided by Embodiment 3 of the present invention. Embodiment 3 of the present invention is optimized on the basis of the above-mentioned embodiment. In this embodiment, the step "based on the real scene in the camera preview interface Determining the pre-selected object in the picture frame is optimized as: extracting image feature points that match preset image attributes in the real-scene picture frame; determining the image outline based on the image feature points, and determining the image formed by the image outline for the preselected object.

Further, the step of "determining the object type of the preselected object based on the depth value of the preselected object in the real picture frame" is optimized as follows: if the depth value of the preselected object in the real picture frame is greater than the set If the value is fixed, the object type of the preselected object is determined to be stereo; if the depth of field value of the preselected object in the real scene frame is less than or equal to the set value, then the object type of the preselected object is determined to be planar .

In addition, the step of "performing effect enhancement processing on the target object based on augmented reality" is optimized as: performing effect enhancement processing on the target object based on the virtual content in the augmented reality library that matches the target object.

As shown in Figure 3a, an image processing method provided by Embodiment 3 of the present invention specifically includes the following operations:

S301. After the mobile terminal is in a shooting mode, acquire current picture frames respectively captured by at least two cameras on the mobile terminal.

S302. Perform image synthesis processing on at least two currently captured image frames, so as to synthesize real-scene image frames satisfying a preset depth-of-field range.

S303. Display the real scene frame in the camera preview interface.

In this embodiment, steps S301 to S303 determine the real-scene frame that satisfies the preset depth-of-field range based on the image synthesis process, and display the real-scene frame on the camera preview interface.

S304. Extract image feature points matching preset image attributes from the image frame of the real scene.

In this embodiment, image feature points matching preset image attributes may be extracted from the real-scene picture frame. Wherein, the preset image attribute may specifically be set before shooting the real-scene picture, and may be considered as the image attribute of the target object to be enhanced. Exemplarily, if the preset image attribute is an attribute of a rose, the rose may be used as a preselected object to be enhanced.

In this embodiment, taking roses as the pre-selected object to be enhanced as an example, first, image feature points matching the attributes of the rose can be extracted from the real scene frame, and the image feature points can have shape features points, size feature points, and color feature points.

S305. Determine an image contour based on the image feature points, and determine an image formed by the image contour as a preselected object.

In this embodiment, after the image feature points matching the preset image attributes are determined based on step S304, a corresponding image outline can be formed in the region to be recognized based on the image feature points, and finally the The image whose outline is determined is used as a preselected object to be enhanced.

It should be noted that, in the real-scene picture frame, the number of preselected objects formed by image feature points matching preset image attributes may be one or multiple.

S306. If the depth of field value of the preselected object in the real scene frame is greater than a set value, determine that the object type of the preselected object is stereo.

In this embodiment, the depth of field value corresponding to the preselected object can be determined in the real-scene picture frame conforming to the preset depth of field range, and when the depth of field value is determined to be greater than the set value, the preselected object can be considered as a stereoscopic image , the object type corresponding to the preselected object is stereotype.

Exemplarily, the preselected object whose object type is stereo may be a real object image captured by a camera.

S307. If the depth of field value of the preselected object in the real picture frame is less than or equal to a set value, determine that the object type of the preselected object is a plane type.

In this embodiment, when it is determined that the depth of field value is less than or equal to a set value, it may be considered that the preselected object is a planar image, and the object type corresponding to the preselected object is a planar image.

Exemplarily, the preselected object whose object type is planar may be a planar face captured by a camera or a non-real image displayed on a poster.

S308. If the object type of the preselected object conforms to the preset type, determine the preselected object as the target object to be processed.

In this embodiment, before enhancing the effect of the target object, the type of the target object to be enhanced is usually preset to make the enhancement effect of the target object better. Generally, if the object type of the pre-selected object meets the preset object type to be enhanced type, it indicates that the preset object can be used as the target object for effect enhancement.

S309. Perform effect enhancement processing on the target object based on the virtual content matching the target object in the augmented reality library.

In this embodiment, when the effect or scene enhancement is performed based on augmented reality technology, it is mainly implemented based on the virtual content stored in the augmented reality library, as long as it is determined that the virtual content matching the target object exists in the augmented reality library, An enhancement operation can be performed on the target object based on the virtual content.

The image processing method provided by Embodiment 3 of the present invention embodies the process of determining the target object, so that the target object can be determined based on the object type of the pre-selected object in the real-scene picture frame. In addition, it also embodies the target object Steps of the enhancement operation, so that the target object can perform effect enhancement when there is corresponding virtual content in the augmented reality library. Using this method, the target object to be enhanced can be accurately and quickly determined. In addition, the augmented reality technology is integrated into the shooting function of the mobile terminal, so that the effect of the selected target object can be enhanced in real time based on the augmented reality technology. The purpose of this is to simplify the image processing process and make the captured image achieve the desired effect of the user, thereby improving the user experience.

On the basis of the above-mentioned embodiments, the third embodiment of the present invention provides two example diagrams in which the target object is determined based on the depth of field value in the real-scene frame in the camera preview interface, wherein, Fig. 3b and Fig. 3c are respectively the real-scene in the camera preview interface Illustration of an example of targeting an object in a picture frame.

Specifically, as shown in FIG. 3b, the real-scene picture frame 31 displayed in the camera preview interface is obtained based on at least two camera captures and image merging processing. It can be seen that there is a real-scene picture frame 31 that meets the set conditions. preselected image 311, and the depth of field value of the preselected image 311 can be determined in the real picture frame 31, since the determined depth of field value is greater than the set value, it can be considered that the preselected image 311 is a stereoscopic image, and the corresponding object type is stereoscopic type. At this time, if the preset object type of the target object to be enhanced is stereo, then the preselected image 311 can be easily determined as the target object to be enhanced in the real-scene frame 31 .

In addition, as shown in FIG. 3c, the real-scene picture frame 32 displayed in the camera preview interface is obtained based on at least two camera captures and image merging processing. It can be seen that there is a pre-selected frame 32 that meets the set conditions image 321, and the depth of field value of the preselected image 321 can be determined in the real picture frame 32, since the determined depth of field value is smaller than the set value, it can be considered that the preselected image 321 is a planar image, and the corresponding object type is planar . At this time, if the preset object type of the target object to be enhanced is stereo, it can be easily determined in the real scene frame 32 that the preselected image 321 cannot be the target object to be enhanced.

Embodiment Four

FIG. 4 is a structural block diagram of an image processing device according to Embodiment 4 of the present invention. The device is suitable for performing effect enhancement processing on captured images when a user uses a mobile terminal to capture images. The device can be implemented by software and/or hardware, and is generally integrated in a mobile terminal. As shown in FIG. 4 , the identification device includes: a preselected object determination module 41 , an object type determination module 42 , a target object determination module 43 and an augmented reality processing module 44 .

Wherein, the pre-selected object determination module 41 is used to determine the pre-selected object based on the real scene picture frame in the camera preview interface after the mobile terminal is in the shooting mode;

An object type determination module 42, configured to determine the object type of the preselected object based on the depth value of the preselected object in the real scene picture frame;

A target object determination module 43, configured to determine the pre-selected object as the target object to be processed when the object type of the pre-selected object conforms to a preset type;

The augmented reality processing module 44 is configured to perform effect enhancement processing on the target object based on augmented reality.

In this embodiment, the device first determines the preselected object based on the real scene picture frame in the camera preview interface through the preselected object determination module 41 after the mobile terminal is in the shooting mode; The depth of field value in the real-scene picture frame determines the object type of the pre-selected object; then, when the object type of the pre-selected object conforms to the preset type through the target object determination module 43, the pre-selected object is determined as the target object to be processed ; Finally, the augmented reality processing module 44 performs effect enhancement processing on the target object based on the augmented reality.

An image processing device provided in Embodiment 4 of the present invention can select a target object that meets preset conditions in the captured image, and integrate augmented reality technology into the shooting function of the mobile terminal, thereby achieving the goal based on augmented reality. The purpose of the technology is to enhance the effect of the selected target object in real time, which not only simplifies the image processing process but also enables the captured image to achieve the expected effect of the user, improving the user experience.

Further, it also includes:

An image capture module, configured to acquire current picture frames captured by at least two cameras on the mobile terminal;

An image synthesis module, configured to perform image synthesis processing on at least two current picture frames captured respectively, so as to synthesize real scene picture frames satisfying a preset depth-of-field range;

An image display module, configured to display the real scene frame in the camera preview interface.

Further, the preselected object determination module 41 is specifically used for:

Extracting image feature points matching preset image attributes in the image frame of the real scene;

An image contour is determined based on the image feature points, and an image formed by the image contour is determined as a preselected object.

Further, the object type determination module 42 is specifically used for:

When the depth of field value of the preselected object in the real scene frame is greater than a set value, it is determined that the object type of the preselected object is a three-dimensional type;

When the depth of field value of the pre-selected object in the real scene frame is less than or equal to a set value, it is determined that the object type of the pre-selected object is a planar type.

Further, the augmented reality processing module 44 specifically includes:

Perform effect enhancement processing on the target object based on the virtual content matching the target object in the augmented reality library.

Embodiment five

Embodiment 5 of the present invention provides a mobile terminal, which integrates the image processing apparatus provided in the foregoing embodiments. The processing of captured images can be performed in real time by performing image processing.

Exemplarily, the mobile terminal in this embodiment may specifically be an intelligent electronic device such as a mobile phone, a notebook, and a tablet computer. When the user uses the mobile terminal in this embodiment, the mobile terminal determines the preselected object based on the real scene picture frame in the camera preview interface after the mobile terminal is in the shooting mode based on the image processing device integrated in it, and then based on the preselected object The depth of field value in the real picture frame determines the object type of the pre-selected object, and then when the object type of the pre-selected object conforms to the preset type, the pre-selected object is determined as the target object to be processed, and finally based on Augmented reality performs effect enhancement processing on the target object.

The mobile terminal in this embodiment uses the image processing device provided by the present invention to select the target object that meets the preset conditions in the captured image, and integrates the augmented reality technology into the shooting function of the mobile terminal, thereby achieving Based on the augmented reality technology, the effect of the selected target object is enhanced in real time, thereby simplifying the image processing process and making the captured image achieve the expected effect of the user, thereby improving the user experience.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims (11)

1. the method for an image procossing, it is characterised in that including:

After mobile terminal is in screening-mode, determine preliminary election based on the outdoor scene image frame in camera preview interface Object；

The object of described preliminary election object is determined based on described preliminary election object depth of field value in described outdoor scene image frame Type；

If the object type of described preliminary election object meets preset kind, then it is defined as treating by described preliminary election object The destination object processed；

Based on augmented reality, described destination object is carried out effect enhancement process.

Method the most according to claim 1, it is characterised in that also include:

Obtain the current picture frame caught respectively by least two photographic head on mobile terminal；

At least two the current picture frames captured respectively are carried out image synthesis process, meets with synthesis and preset The outdoor scene image frame of field depth；

Described outdoor scene image frame is shown in described camera preview interface.

Method the most according to claim 1, it is characterised in that described based in camera preview interface Outdoor scene image frame determines preliminary election object, specifically includes:

The image characteristic point matched with pre-set image attribute is extracted in described outdoor scene picture photo frame；

Determine image outline based on described image characteristic point, and the image that described image outline is formed is defined as Preliminary election object.

Method the most according to claim 1, it is characterised in that described based on described preliminary election object in institute State the depth of field value in outdoor scene image frame and determine the object type of described preliminary election object, specifically include:

If the depth of field value that described preliminary election object is in described outdoor scene image frame is more than setting value, it is determined that described The object type of preliminary election object is solid type；

If the depth of field value that described preliminary election object is in described outdoor scene image frame is less than or equal to setting value, the most really The object type of fixed described preliminary election object is plane.

Method the most according to claim 1, it is characterised in that described based on augmented reality to described mesh Mark object carries out effect enhancement process, specifically includes:

Based on the virtual content mated with described destination object in augmented reality storehouse, described destination object is imitated Really enhancement process.

6. the device of an image procossing, it is characterised in that including:

Preliminary election object determines module, for after mobile terminal is in screening-mode, based on camera preview interface In outdoor scene image frame determine preliminary election object；

Object type determination module, for based on described preliminary election object depth of field value in described outdoor scene image frame Determine the object type of described preliminary election object；

Destination object determines module, is used for when the object type of described preliminary election object meets preset kind, then Described preliminary election object is defined as pending destination object；

Augmented reality processing module, for carrying out effect enhancement process based on augmented reality to described destination object.

Device the most according to claim 6, it is characterised in that also include:

Image capture module, for obtain by least two photographic head on mobile terminal catch respectively current Image frame；

Image synthesis unit, for carrying out at image synthesis at least two the current picture frames captured respectively Reason, meets the outdoor scene image frame presetting field depth with synthesis；

Image display, for showing described outdoor scene image frame in described camera preview interface.

Method the most according to claim 6, it is characterised in that described preliminary election object determines module, tool Body is used for:

The image characteristic point matched with pre-set image attribute is extracted in described outdoor scene picture photo frame；

Determine image outline based on described image characteristic point, and the image that described image outline is formed is defined as Preliminary election object.

Method the most according to claim 6, it is characterised in that described object type determination module, tool Body is used for:

When described preliminary election object depth of field value in described outdoor scene image frame is more than setting value, determine described pre- The object type selecting object is solid type；

When described preliminary election object depth of field value in described outdoor scene image frame is less than or equal to setting value, determine The object type of described preliminary election object is plane.

Method the most according to claim 6, it is characterised in that described augmented reality processing module, Specifically include:

Based on the virtual content mated with described destination object in augmented reality storehouse, described destination object is imitated Really enhancement process.

11. 1 kinds of mobile terminals, it is characterised in that this mobile terminal is integrated with as claim 6-10 is arbitrary The device of described image procossing.