WO2017206444A1

WO2017206444A1 - Method and device for detecting imaging difference, and computer storage medium

Info

Publication number: WO2017206444A1
Application number: PCT/CN2016/105783
Authority: WO
Inventors: 董静怡
Original assignee: 中兴通讯股份有限公司
Priority date: 2016-06-03
Filing date: 2016-11-14
Publication date: 2017-12-07
Also published as: CN107465912A

Abstract

Disclosed in an embodiment of the invention is a method for detecting an imaging difference, comprising: respectively acquiring a first image and a second image captured by a first photographing device and a second photographing device; and comparing the first image and the second image to obtain a difference in imaging quality therebetween, and if the difference in imaging quality exceeds a preset threshold, generating and issuing a notification. Also disclosed in the embodiment of the invention are a device for detecting an imaging difference, and a computer storage medium.

Description

Imaging difference detecting method, device and computer storage medium

Technical field

The present invention relates to terminal imaging technologies, and in particular, to an imaging difference detection method and apparatus, and a computer storage medium.

Background technique

At present, more and more mobile terminals use dual camera solutions to achieve fast focus, background blur, panoramic deep camera and other functions.

Whether it is fast focus or large aperture function, it is required that the image quality of the two cameras of the mobile terminal should be as close as possible; the closer the image quality of the two cameras is, the closer the focus accuracy and the background blur The better. However, in actual use, based on the difference in the installation position of the dual camera, there is often one of the cameras in a position that is relatively easy to touch or occlude; if the camera is set to an auxiliary camera that is not visible, then if the camera is When occlusion or foreign object coverage on the lens, the difference in imaging quality between the two cameras will increase; the difference in imaging quality will directly affect the focus accuracy and blurring of the background blurred object contour, which will affect the user experience. Based on this, in the case of occlusion and foreign object coverage, it is particularly important to confirm whether the dual camera framing is successful, that is, whether the imaging quality of the two cameras is close enough.

It is relatively simple to identify large-area occlusions. Because large areas are occluded, there is a significant difference in exposure. It is easy to judge occlusion by exposure difference, and then prompt the user to check and avoid occlusion of the camera; however, there is currently no effective way to identify A small amount of occlusion and foreign object coverage on the camera.

Therefore, how to effectively identify the occlusion and foreign object coverage existing on the camera, remind the user to clean up, reduce the imaging difference between the two cameras, and improve the imaging quality of the dual camera is an urgent problem to be solved.

Summary of the invention

In view of this, embodiments of the present invention are directed to provide an imaging difference detecting method, apparatus, and computer storage medium, which can effectively identify the occlusion and foreign object coverage existing on the camera, remind the user to clean up, thereby reducing the imaging difference between the two cameras, and improving the double Camera image quality.

In order to achieve the above object, the technical solution of the present invention is achieved as follows:

An embodiment of the present invention provides an imaging difference detecting method, where the method includes:

Acquiring the first image and the second image captured by the first camera device and the second camera device respectively;

Comparing the difference in imaging quality between the first image and the second image, when the difference in imaging quality exceeds a preset threshold, a prompt is generated and issued.

In the above solution, comparing the difference in imaging quality between the first image and the second image includes:

The difference in image content, and/or image sharpness, and/or image contrast of the first and second images is compared.

In the above solution, the comparing the difference between the image content of the first image and the second image includes:

The first image and the second image are divided into more than one block, and the difference in image content of the corresponding position block of the first image and the second image is compared.

In the above solution, comparing the difference of the image content of the corresponding location block of the first image and the second image comprises: comparing image content of the same location block of the first image and the second image corner area difference.

In the above solution, the comparing the difference in image sharpness of the first image and the second image comprises: comparing a difference in edge definition of the subject in the first image and the second image.

In the above solution, the comparing the difference in edge definition of the object in the first image and the second image includes:

Detecting the first image and the second image using a Sobel edge detection algorithm The edge of the subject;

A difference in sharpness of a position corresponding to a position of the subject in the first image and the second image is compared.

In the above solution, comparing the difference in image contrast between the first image and the second image comprises: comparing a difference in contrast between the first image and the second image by using a histogram.

In the above solution, the acquiring the first image and the second image captured by the first camera device and the second camera device respectively includes: acquiring the image captured by the first camera device and the second camera device at a preset focal length And a first image and a second image, or the first image and the second image within a preset focal length difference range captured by the first camera and the second camera.

The embodiment of the present invention further provides an imaging difference detecting device, where the device includes: an acquiring module and a comparing module; wherein

The acquiring module is configured to acquire a first image captured by the first camera device and a second image captured by the second camera device;

The comparison module is configured to compare image quality differences between the first image and the second image, and generate and issue a prompt when the image quality difference exceeds a preset threshold.

In the above solution, the comparison module is specifically configured to:

In the above solution, the acquiring module is specifically configured to:

Acquiring the first image and the second image captured by the first camera device and the second camera device on a preset focal length, or acquiring a preset focal length difference captured by the first camera device and the second camera device The first image and the second image within range.

Embodiments of the present invention also provide a computer storage medium, the storage medium comprising a set of instructions that, when executed, cause at least one processor to perform operations including:

The imaging difference detecting method and device and the computer storage medium provided by the embodiments of the present invention respectively acquire the first image and the second image captured by the first camera device and the second camera device; and compare the first image and the second image The difference in imaging quality, when the difference in imaging quality exceeds a preset threshold, prompts the user. In this way, by detecting the difference between the imaging of the two camera devices, the occlusion and foreign object coverage existing on the camera can be effectively recognized, and the user is prompted to clear, thereby reducing the imaging difference between the two cameras and improving the imaging quality of the dual camera.

DRAWINGS

1 is a schematic flow chart of an imaging difference detecting method according to an embodiment of the present invention;

2 is a schematic diagram showing a comparison of histograms in different contrasts according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of an imaging difference detecting apparatus according to an embodiment of the present invention.

detailed description

In the embodiment of the present invention, the first image and the second image captured by the first camera device and the second camera device are respectively acquired; and the image quality difference between the first image and the second image is compared, when the image quality difference exceeds Prompt the user when the threshold is preset.

Wherein, the difference in imaging quality may be a difference in image content, or may be a difference in sharpness of a subject edge in the image, or may be a difference in image contrast.

The present invention will be further described in detail below with reference to the embodiments.

The imaging difference detecting method provided by the embodiment of the present invention is as shown in FIG. 1 , and the method includes:

Step 101: Acquire a first image and a second image captured by the first camera device and the second camera device, respectively;

Here, the first camera device and the second camera device may be two cameras on the same side of the dual camera terminal, such as a dual camera located at the back of the terminal; the first camera may be separately obtained. a first image and a second image captured by the image device and the second camera at the same time;

Further, since the dual camera is usually set to focus on a near focus and a focus on a distance, the images captured by the two cameras may have a large difference in depth of field, which is not conducive to comparison; therefore, a detection mode can be set in Synchronizing the focal lengths of the two cameras in the detection mode, so that the two cameras take the first image and the second image with a uniform focal length, ensuring that the focal lengths of the first image and the second image are consistent, so that it can be avoided in subsequent comparisons. The deviation of the comparison result should be caused by the difference of depth of field; this detection mode can be added to the stage before the user takes the photo according to the demand, to avoid affecting the normal shooting of the user; or in the normal shooting process, the focal length difference between the two cameras falls The first image and the second image captured when a preset focal length difference is within a range.

Step 102: Comparing the difference in imaging quality between the first image and the second image, generating and issuing a prompt when the difference in imaging quality exceeds a preset threshold;

Here, three methods may be used to detect whether the camera has occlusion or foreign object coverage, and one of them may be used or a combination thereof may be used to compare the difference in imaging quality between the first image and the second image to determine whether the lens exists. Occlusion or foreign object coverage; wherein the difference in imaging quality may be a difference in image content, a difference in sharpness of a subject edge in the image, or a difference in image contrast.

Method 1: Comparison of image content;

Generally, if a camera lens of a dual camera terminal is blocked by a finger or the like, the image content captured by the two cameras may be different, and therefore, the image content may be detected by comparing the image content; specifically, the image may be captured. The first image and the second image are respectively divided into more than one block, and the block contents corresponding to the positions of the two images are compared. Further, since the large-area occlusion can be detected by the difference in exposure, the comparison of the block contents can be mainly used for detecting the small-area occlusion; the small-area occlusion is usually mainly located at the corner position of the image, and can be from the corner area. The block starts to contrast, so you can minimize the amount of calculation. If the calculation finds that the difference of the block content exceeds the preset content difference threshold, the current first image and the second image are considered to be different. As a result, one of the cameras may have a shadow, which may prompt the user that the camera lens has a shadow.

In practical applications, some existing algorithms such as Structural Similarity (SIM) can be used to compare the image similarity of the image block content, and set a preset content difference threshold. When the difference value exceeds When the preset content difference threshold is used, the prompt is sent to the user; due to the difference between the dual camera position and the individual performance of the camera, the image content of the first image and the second image captured by the two cameras cannot be completely consistent, and statistics can be performed. The image content difference between the first image and the second image taken under ideal conditions may not be reached in actual shooting, so if the image content difference is 1% to 3% under ideal conditions, A difference value of 3% to 5% is selected as the preset content difference threshold.

Method 2: contrasting the edge definition of the image subject;

Generally, if there is a foreign object covering the lens, the sharpness of the subject in the captured image will be significantly reduced. Therefore, the sharpness of the same subject in the first image and the second image can be compared to detect whether there is a foreign object. Covering the lens; further, in the case where the lens has foreign matter coverage, the edge sharpness of the subject is most significantly reduced, and therefore, it is preferable to compare the edge sharpness of the same subject in the first image and the second image.

In practical applications, some existing image object edge detection algorithms such as Sobeel Sobel edge detection algorithm may be used to determine the edge of the object; and the edge sharpness evaluation method is used to compare the edges of the two images. In the resolution evaluation method, a Laplace image sharpness algorithm or the like in the edge gradient detection method may be employed. By setting a preset sharpness difference threshold, when the edge sharpness comparison difference between the first image and the second image exceeds the preset sharpness difference threshold, a prompt is sent to the user, prompting the user that there may be foreign object coverage on the lens; Due to the difference of the dual camera position, the individual performance of the camera, etc., the first image and the second image captured by the two cameras cannot achieve the same edge definition, and the first image and the second image taken under ideal conditions can be counted. The difference in edge definition of the image; this difference range may not be achieved in actual shooting, so if the difference in edge resolution is close to ideal conditions For the range of 1% to 3%, a difference value of 3% to 5% can be selected as the preset sharpness difference threshold.

Method 3: Image contrast contrast;

Generally, if there is foreign matter covering the lens, the contrast of the image will be significantly reduced due to the blocking effect of the foreign matter on the light. This change will be directly reflected on the histogram of the first image and the second image. Compare the histograms to determine if one of them has a foreign object and gives a user prompt.

Specifically, the grayscale histogram can be used to measure the image contrast. The histogram is a two-dimensional map. The abscissa indicates the gray level of each pixel in the image, which can be 0 to 255 levels; the ordinate is the gray level. The number or probability of occurrence of each pixel in the upper image; the peak of the histogram is concentrated at the low end, the image is darker, and the image is brighter; the peak of the histogram is concentrated in a certain area, the image is dim, and the object and background are different in the image. For large images, the histogram has a bimodal characteristic; the more uniform the histogram distribution, the better the image contrast; for the same image, if the contrast is reduced, the histogram distribution will be concentrated; the histogram shown in Figure 2(a) The picture shows a histogram of the original image. It can be seen that the pixel distribution on each gray scale is more uniform in the histogram. Figure 2(b) is the histogram of the image after the lens is covered by foreign objects. You can see the gray in the histogram. The pixel distribution is more concentrated, indicating that the contrast of Figure 2(b) is lower; by comparing the histograms of the first image and the second image, if the pixel distribution on each gray scale is found on one of the histograms If the concentration is relatively concentrated, it can be judged that the contrast of the image is low, and the corresponding image of the camera may have foreign object coverage; here, a contrast difference threshold may be set, when the difference between the histogram of the first image and the second image exceeds the contrast difference At the threshold, it is determined that there may be foreign matter coverage on the lens corresponding to one of the images, and the user is prompted; here, the contrast difference may be a difference in the uniformity of the distribution of the histogram; due to differences in the position of the dual camera and the individual performance of the camera, The image contrast of the first image and the second image captured by the two cameras cannot be completely consistent, and the difference between the first image and the second image captured under ideal conditions can be counted, such as 1% to 3 %; this difference range may not be achieved in actual shooting, so if the contrast is close to ideal conditions The difference is 1% to 3%, and a difference value of 3% to 5% can be selected as the preset contrast difference threshold.

Using one or more of the above three image quality comparison methods, it can be determined whether the image quality of one of the dual cameras is degraded, and if it is lowered, it indicates that the occlusion or foreign object coverage existing on the camera needs to be cleaned.

The imaging difference detecting device provided by the embodiment of the present invention, as shown in FIG. 3, the device includes: an obtaining module 31 and a comparing module 32;

The acquiring module 31 is configured to acquire a first image captured by the first camera device and a second image captured by the second camera device;

Here, the first camera device and the second camera device may be two cameras on the same side of the dual camera terminal, such as a dual camera located at the back of the terminal; the first camera device and the second camera device may be respectively acquired in the same a first image and a second image taken at time;

The comparison module 32 is configured to compare image quality differences between the first image and the second image, and generate and issue a prompt when the image quality difference exceeds a preset threshold;

Here, three methods may be used to detect whether the camera has occlusion or foreign object coverage, and one of them may be used or a combination thereof may be used to compare the difference in imaging quality between the first image and the second image to determine whether the lens exists. Occlusion or foreign object coverage; wherein the difference in imaging quality may be a difference in image content or a difference in sharpness of a subject edge in the image, It can also be the difference in image contrast.

Method 1: Comparison of image content;

Generally, if a camera lens of a dual camera terminal is blocked by a finger or the like, the image content captured by the two cameras may be different, and therefore, the image content may be detected by comparing the image content; specifically, the image may be captured. The first image and the second image are respectively divided into more than one block, and the block contents corresponding to the positions of the two images are compared. Further, since the large-area occlusion can be detected by the difference in exposure, the comparison of the block contents can be mainly used for detecting the small-area occlusion; the small-area occlusion is usually mainly located at the corner position of the image, and can be from the corner area. The block starts to contrast, so you can minimize the amount of calculation. If the calculation finds that the difference of the block content exceeds the preset content difference threshold, it is considered that the current first image and the second image are inconsistent, and one of the cameras may have a shadow, which may prompt the user that the camera lens has a shadow condition.

In practical applications, some existing algorithms, such as a SIM algorithm, may be used to compare the image similarity of the image block content, and set a preset content difference threshold, when the difference value exceeds the preset content difference threshold. Sending a prompt to the user; due to the difference in the position of the dual camera, the performance of the individual camera, etc., the image content of the first image and the second image captured by the two cameras cannot be completely consistent, and the statistically close to the ideal situation can be counted. The difference between the image content of the first image and the second image; this difference range may not be achieved in actual shooting. Therefore, if the image content difference is 1% to 3% under ideal conditions, 3% to 5% may be selected. The difference value is used as a preset content difference threshold.

Method 2: contrasting the edge definition of the image subject;

In practical applications, some existing image object edge detection algorithms such as Sobel edge detection algorithm and the like may be used to determine the edge of the object; and the edge definition of the two images is compared by the edge sharpness evaluation method; The resolution evaluation method may use a Laplace image sharpness algorithm in the edge gradient detection method or the like. By setting a preset sharpness difference threshold, when the edge sharpness comparison difference between the first image and the second image exceeds the preset sharpness difference threshold, a prompt is sent to the user, prompting the user that there may be foreign object coverage on the lens; Due to the difference of the dual camera position, the individual performance of the camera, etc., the first image and the second image captured by the two cameras cannot achieve the same edge definition, and the first image and the second image taken under ideal conditions can be counted. The difference in edge definition of the image; this difference range may not be achieved in actual shooting. Therefore, if the difference in edge sharpness is 1% to 3% under ideal conditions, a difference value of 3% to 5% can be selected. As a preset clarity difference threshold.

Method 3: Image contrast contrast;

Specifically, the gray histogram can be used to measure the image contrast; the histogram is a two-dimensional map, and the abscissa indicates the gray level of each pixel in the image, which can be 0 to 255 levels; the ordinate is the gray level. The number or probability of occurrence of each pixel of the upper image; the peak of the histogram is concentrated at the low end, the image is darker, and the image is brighter; the peak of the histogram is concentrated in a certain area, the image is dim; the difference between the object and the background in the image For large images, the histogram has a bimodal characteristic; the more uniform the histogram distribution, the better the image contrast; for the same image, if the contrast is reduced, the histogram distribution will be concentrated; the histogram shown in Figure 2(a) The picture shows a histogram of the original image. It can be seen that the pixel distribution on each gray scale is more uniform in the histogram. Figure 2(b) is the histogram of the image after the lens is covered by foreign objects. You can see the gray in the histogram. Pixel distribution Concentration, indicating that the contrast of Figure 2(b) is low; by comparing the histograms of the first image and the second image, if the pixel distribution on each gray scale on one of the histograms is found to be concentrated, it can be judged that the contrast of the image is relatively Low, the image corresponding to the camera may have foreign object coverage; here a contrast difference threshold may be set, and when the histogram difference between the first image and the second image exceeds the contrast difference threshold, determine one of the images corresponding to There may be foreign matter covering on the lens, and the user is prompted; here, the contrast difference may be a difference in the degree of uniformity of the histogram distribution; the first image taken by the two cameras due to the difference in the position of the dual camera, the individual performance of the camera, and the like The contrast of the image with the second image cannot be completely consistent, and the difference between the contrast of the first image and the second image taken under ideal conditions can be counted, such as 1% to 3%; this may not be achieved in actual shooting. The range of difference, therefore, if the difference in contrast under ideal conditions is 1% to 3%, then Set the difference value of 3% to 5% of a predetermined contrast difference threshold.

In an actual application, the acquiring module 31 can be implemented by a camera device of the terminal in combination with a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA). The comparison module 32 can be implemented by a CPU, an MPU, a DSP, an FPGA, or the like of the terminal.

The above is only the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included. Within the scope of protection of the present invention.

Comparing the difference in imaging quality between the first image and the second image, when the image quality is poor Generate and issue a prompt when the preset threshold is exceeded.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

The above is only the preferred embodiment of the present invention and is not intended to limit the scope of the present invention.

Industrial applicability

The embodiment of the invention discloses an imaging difference detecting method, a device and a computer storage medium, respectively acquiring a first image and a second image captured by the first camera device and the second camera device; The difference in imaging quality between the first image and the second image is issued to the user when the difference in imaging quality exceeds a preset threshold. In this way, by detecting the difference between the imaging of the two camera devices, the occlusion and foreign object coverage existing on the camera can be effectively recognized, and the user is prompted to clear, thereby reducing the imaging difference between the two cameras and improving the imaging quality of the dual camera.

Claims

An imaging difference detecting method, the method comprising:

Acquiring the first image and the second image captured by the first camera device and the second camera device respectively;

Comparing the difference in imaging quality between the first image and the second image, when the difference in imaging quality exceeds a preset threshold, a prompt is generated and issued.
The method of claim 1, wherein comparing the difference in imaging quality between the first image and the second image comprises:

The difference in image content, and/or image sharpness, and/or image contrast of the first and second images is compared.
The method of claim 2, wherein comparing the difference in image content of the first image and the second image comprises:

The first image and the second image are divided into more than one block, and the difference in image content of the corresponding position block of the first image and the second image is compared.
The method of claim 3, wherein comparing the difference in image content of the corresponding location block of the first image and the second image comprises:

Comparing the difference in image content of the same location block of the first image and the second image corner region.
The method of claim 2, wherein comparing the difference in image sharpness of the first image and the second image comprises comparing edge definition of a subject in the first image and the second image The difference.
The method according to claim 5, wherein said comparing a difference in edge definition of a subject in said first image and said second image comprises:

Detecting edges of the object in the first image and the second image by using a Sobel Sobel edge detection algorithm;

Comparing the difference in sharpness of the edge of the corresponding position of the object in the first image and the second image different.
The method of claim 2, wherein comparing the difference in image contrast of the first image and the second image comprises comparing a difference in contrast of the first image and the second image using a histogram.
The method according to any one of claims 1 to 7, wherein the acquiring the first image and the second image captured by the first camera device and the second camera device respectively comprises: acquiring the first camera device and The first image and the second image captured by the second camera device on a preset focal length, or the first image and the preset focal length difference range captured by the first camera device and the second camera device Second image.
An imaging difference detecting device, the device comprising: an acquiring module and a comparing module; wherein

The acquiring module is configured to acquire a first image captured by the first camera device and a second image captured by the second camera device;

The comparison module is configured to compare an imaging quality difference between the first image and the second image, and generate and issue a prompt when the imaging quality difference exceeds a preset threshold.
The apparatus of claim 9, wherein the contrast module is configured to compare image content of the first and second images, and/or image sharpness, and/or contrast of image contrast.
The apparatus according to claim 9 or 10, wherein the acquisition module is configured to acquire the first image and the second image captured by the first camera device and the second camera device at a preset focal length, or Acquiring the first image and the second image within a preset focal length difference range captured by the first camera device and the second camera device.
A computer storage medium comprising a set of instructions that, when executed, cause at least one processor to perform operations comprising:

Acquiring the first image and the second image captured by the first camera device and the second camera device respectively;

Comparing the difference in imaging quality between the first image and the second image, when the difference in imaging quality exceeds a preset threshold, a prompt is generated and issued.