Imaging quality detection method of intelligent mobile phone imaging module

Abstract

The invention relates to the technical field of smart phone quality detection, and provides an imaging quality detection method of a smart phone imaging module. The method comprises the following steps: segmenting an initial image collected by a smart phone imaging module to obtain a plurality of subimages, configuring a coding value for each subimage, combining the subimage to obtain a plurality of subimage combinations, and selecting a correlation coefficient target subimage combination from the subimage combinations; performing quality detection on a first sub-image in the target sub-image combination to obtain a first quality detection result; performing quality detection on a second sub-image in the target sub-image combination to obtain a second quality detection result; and determining a target quality detection result according to the first quality detection result and the second quality detection result. According to the method, the initial image area is selected, and the quality of the two sub-images is detected, so that the imaging quality condition of the smart phone imaging module can be evaluated by detecting the local features of the multi-feature initial image.

Description

Technical Field

[0001] The present application relates to the technical field of smartphone quality detection, and in particular to an imaging quality detection method for a smartphone imaging module. Background Art

[0002] The imaging module of a smartphone refers to the entire camera system, including lenses, sensors, image processing chips, and related components. Through the imaging module of a smartphone, images or videos taken by the phone can be captured, processed, and generated.

[0003] As the core component of the mobile phone camera system, the quality inspection of the smartphone imaging module is crucial to ensure the shooting performance and image quality of the mobile phone. In recent years, with the continuous development of computer vision technology, automated image processing technology has been widely used in the field of imaging quality inspection of smartphone imaging modules. Through efficient algorithms, feature extraction and quality assessment of collected images are performed, which significantly improves the inspection efficiency.

[0004] However, existing detection technologies rely too much on global quality assessment and neglect the detailed detection of local areas of the image. When there are multiple areas with different characteristics in the image, this global evaluation method often cannot accurately identify the specific quality of each area, and cannot evaluate the imaging quality of the smartphone imaging module based on each local feature of the multi-characteristic image, resulting in misjudgment of the imaging quality. Summary of the invention

[0005] In view of this, the present application provides an imaging quality detection method for a smartphone imaging module, which is used to solve the technical problem in the prior art that the imaging quality of a smartphone imaging module cannot be evaluated based on each local feature of a multi-characteristic image.

[0006] In the first aspect, the present application provides an imaging quality detection method for a smartphone imaging module, which adopts the following technical solution: Segmenting an initial image of a target object captured by an imaging module of a smart phone to obtain a plurality of sub-images; According to the position of each sub-image in the initial image, a coding value is configured for the corresponding sub-image to obtain a coding value set; Selecting any two coding values ​​from the coding value set to obtain a plurality of coding value combinations, each coding value combination corresponding to a sub-image combination; Selecting a target sub-image combination from the plurality of sub-image combinations; Performing a quality inspection on a first sub-image in the target sub-image combination to obtain a first quality inspection result; Performing a quality inspection on a second sub-image in the target sub-image combination to obtain a second quality inspection result; A target quality detection result is obtained according to the first quality detection result and the second quality detection result.

[0007] In an optional implementation, the selecting a target sub-image combination from the plurality of sub-image combinations comprises: Calculating a correlation coefficient between two sub-images in each of the sub-image combinations; Select the smallest correlation coefficient from multiple correlation coefficients as the target correlation coefficient; The sub-image combination corresponding to the target correlation coefficient is used as the target sub-image combination.

[0008] In an optional implementation, the performing quality detection on the first sub-image to obtain a first quality detection result includes: Performing a clarity test on the first sub-image to obtain a clarity test result; Performing a color test on the first sub-image to obtain a color test result; Performing a tone test on the first sub-image to obtain a tone test result; Performing a geometric deformation test on the first sub-image to obtain a deformation test result; A first quality inspection result is obtained based on the clarity test result, the color test result, the tone test result, and the deformation test result.

[0009] In an optional implementation, performing a clarity test on the first sub-image to obtain a clarity test result includes: Performing Fourier transform on the first sub-image to obtain frequency domain data of the first sub-image; generating a modal transfer function curve according to the frequency domain data; The clarity test result is obtained according to the curve area of ​​the modal transfer function curve.

[0010] In an optional implementation, performing a color test on the first sub-image to obtain a color test result includes: Performing spatial transformation on the first sub-image to obtain a first processed image; Performing saturation correction on the first processed image to obtain a second processed image; The color difference between the second processed image and the preset standard color image is calculated to obtain a color test result.

[0011] In an optional implementation, performing a tone test on the first sub-image to obtain a tone test result includes: Acquire input brightness data of the first sub-image; Obtaining a saturated exposure density of the first sub-image according to the input brightness data; Calculating grayscale noise data according to the saturated exposure density; A tone test result is obtained according to the grayscale noise data and preset standard noise data.

[0012] In an optional implementation, performing a geometric deformation test on the first sub-image to obtain a deformation test result includes: Performing area dot division on the first sub-image to obtain a central dot and an actual edge dot set of the initial image; Obtain a standard edge point set according to the central point; The difference mean of the actual edge point set and the standard edge point set is calculated to obtain a deformation test result.

[0013] In an optional implementation, obtaining the first quality inspection result based on the clarity test result, the color test result, the tone test result, and the deformation test result includes: Acquire multiple performance parameters corresponding to the smartphone imaging module; According to the parameter weight ratio corresponding to each of the performance parameters, the target parameter weight ratio is obtained; The clarity test result, the color test result, the tone test result and the deformation test result are weighted and calculated based on the target parameter weight ratio to obtain a target detection parameter; According to the target detection parameters, a match is performed in a preset database to obtain a quality detection result.

[0014] In a second aspect, the present application provides an imaging quality detection device for an imaging module of a smart phone, the device comprising: A processing module, used for segmenting an initial image of a target object acquired by an imaging module of a smart phone to obtain a plurality of sub-images; A coding module, configured to configure a coding value for each sub-image according to a position of the sub-image in the initial image, to obtain a coding value set; A combination module, used for selecting any two coding values ​​from the coding value set to obtain a plurality of coding value combinations, each coding value combination corresponding to a sub-image combination; A selection module, used for selecting a target sub-image combination from a plurality of sub-image combinations; A detection module, used for performing a quality detection on a first sub-image in the target sub-image combination to obtain a first quality detection result; The detection module is further used to perform quality detection on the second sub-image in the target sub-image combination to obtain a second quality detection result; A generating module is used to obtain a target quality detection result according to the first quality detection result and the second quality detection result.

[0015] The third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the imaging quality detection method of the imaging module of the smartphone when executing the computer program.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the imaging quality detection method of the smartphone imaging module.

[0017] This application obtains multiple sub-images by segmenting the initial image collected by the smartphone imaging module, and configures a coding value for each sub-image and combines them to obtain multiple sub-image combinations, and selects a target sub-image combination with a correlation coefficient from the multiple sub-image combinations; performs a quality test on the first sub-image in the target sub-image combination to obtain a first quality test result; performs a quality test on the second sub-image in the target sub-image combination to obtain a second quality test result; and then determines the target quality test result based on the first quality test result and the second quality test result. This application divides the initial image into regions, selects the one with the lowest correlation coefficient and performs quality tests on the two sub-images, and detects the local region with the lowest correlation of the initial image, which more accurately reflects the quality of imaging, and can detect each local feature of the multi-characteristic initial image to evaluate the imaging quality of the smartphone imaging module, thereby accurately obtaining the imaging quality level of the smartphone imaging module. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of an imaging quality detection method for an imaging module of a smart phone shown in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of an imaging quality detection device for an imaging module of a smart phone shown in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a smart phone shown in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0020] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0021] See also Figure 1 As shown, the imaging quality detection method of the smartphone imaging module shown in the embodiment of the present application includes the following steps.

[0022] S11, segmenting an initial image of the target object captured by the imaging module of the smart phone to obtain a plurality of sub-images.

[0023] The smartphone imaging module refers to the entire camera system of the smartphone, which may include lenses, sensors, image processing chips, and related components; the target object may be any colorful subject. Through the smartphone imaging module, the initial image of the target object may be obtained, and the initial image may be segmented into multiple sub-images of the same size. The initial image may be segmented using different segmentation methods, such as nine-square segmentation, grid segmentation, or other segmentation methods.

[0024] In the above embodiment, the initial image is obtained by the smartphone imaging module, and image analysis can be performed based on the initial image to detect the imaging quality of the smartphone imaging module, and the quality of the smartphone imaging module can be further determined based on the imaging quality. In addition, by uniformly dividing the initial image to obtain multiple sub-images, when facing images with multiple characteristics, each sub-image can be tested to obtain more accurate test data, which more accurately reflects the imaging quality level of the smartphone imaging module.

[0025] S12: According to the position of each sub-image in the initial image, configure a coding value for the corresponding sub-image to obtain a coding value set.

[0026] In the initial image, the initial image is divided, for example, into 9 sub-images of the same size by dividing it into a nine-square grid, and the position of each sub-image is determined. A coding value is configured based on the corresponding position of each sub-image in the initial image, wherein the coding value is used to identify the value of each sub-image. The coding values ​​of the 9 sub-images can be configured as 1 to 9, corresponding to the positions of the nine sub-images respectively. After the coding values ​​are configured, a coding value set is formed based on the coding values ​​of 1 to 9.

[0027] In the above embodiment, dividing the initial image into multiple sub-images and assigning a unique set of coding values ​​to each sub-image helps to improve the efficiency and accuracy of image processing and analysis. By identifying the position of each sub-image in the initial image and assigning a coding value to it, it is convenient to identify and track a specific sub-image in subsequent processing.

[0028] S13, arbitrarily selecting two coding values ​​from the coding value set to obtain a plurality of coding value combinations, each of the coding value combinations corresponding to a sub-image combination.

[0029] After configuring a unique coding value for each sub-image, all coding values ​​in the coding value set are arranged and combined to form multiple coding value combinations. For example, when the coding values ​​in the coding value set are 1 to 9, 36 different coding value combinations can be obtained, where each coding value combination represents the positional relationship between two sub-images in the initial image, and the 36 coding value combinations correspond to 36 sub-image combinations.

[0030] In the above embodiment, by combining the coding values ​​of different coding values, an association between different sub-images can be established to form a sub-image combination. When processing the initial image, different sub-image combinations in the initial image can be processed to achieve local characteristic detection of the initial image.

[0031] S14: Select a target sub-image combination from the plurality of sub-image combinations.

[0032] The target sub-image combination refers to the combination of two images with the largest difference in characteristics among multiple sub-image combinations, where the characteristics of the image may include clarity characteristics, color characteristics, grayscale characteristics, and geometric characteristics. After obtaining multiple sub-image combinations, a correlation coefficient test is performed on each sub-image combination, and the sub-image combination with the lowest correlation in image characteristics is determined as the target sub-image combination.

[0033] In the above embodiment, by selecting the sub-image combination with the lowest correlation of image characteristics as the target sub-image combination, the target sub-image combination can be detected to obtain the overall imaging quality level of the initial image.

[0034] In an optional implementation, the selecting a target sub-image combination from the plurality of sub-image combinations comprises: Calculating a correlation coefficient between two sub-images in each of the sub-image combinations; Select the smallest correlation coefficient from multiple correlation coefficients as the target correlation coefficient; The sub-image combination corresponding to the target correlation coefficient is used as the target sub-image combination.

[0035] For each sub-image combination, the correlation coefficient between two sub-images is calculated. The correlation coefficient is a statistic that measures the quality correlation and characteristic correlation of image characteristics between two sub-images. The correlation coefficient can be used to measure the correlation between the characteristics of two sub-images, which may include the correlation between clarity, color, grayscale or geometric characteristics.

[0036] By calculating multiple sub-images through the existing correlation coefficient method, the correlation coefficients in the multiple sub-images can be obtained, and the smallest one is selected from all the calculated correlation coefficients as the target correlation coefficient, that is, the sub-image combination with the lowest correlation between two image characteristics is selected as the target sub-image combination, where the smallest correlation coefficient indicates that the correlation between the two image characteristics is the weakest, that is, their difference is the largest, and the imaging quality is in the most unstable area.

[0037] In the above embodiment, the sub-image combination with the largest difference in two image characteristics is selected as the target sub-image combination through the correlation coefficient, which can reflect the minimum imaging quality level of the imaging module of the smartphone for the initial image during the detection process, thereby determining the imaging quality level of the imaging module of the smartphone.

[0038] S15, performing a quality inspection on the first sub-image in the target sub-image combination to obtain a first quality inspection result.

[0039] After obtaining the target sub-image, obtain the first sub-image in the target sub-image combination for quality inspection, where the quality inspection includes clarity inspection, color inspection, tone inspection and geometric deformation test. The clarity test evaluates the details and edge clarity of the image, the color test checks the color accuracy and saturation, the tone test evaluates the brightness and contrast, and the geometric deformation test detects whether the image is deformed or distorted. By inspecting the first sub-image from the four aspects of clarity, color, tone and geometric deformation, the imaging quality score of the first sub-image, that is, the first quality inspection result, can be obtained.

[0040] In the above embodiment, by testing the four aspects of clarity, color, gradation and geometric deformation, the imaging quality of the first sub-image can be comprehensively evaluated, thereby obtaining the imaging quality of a local area in the initial image, which further reflects the overall imaging quality level of the intelligent imaging module.

[0041] In an optional implementation, the performing quality detection on the first sub-image to obtain a first quality detection result includes: Performing a clarity test on the first sub-image to obtain a clarity test result; Performing a color test on the first sub-image to obtain a color test result; Performing a tone test on the first sub-image to obtain a tone test result; Performing a geometric deformation test on the first sub-image to obtain a deformation test result; A first quality inspection result is obtained based on the clarity test result, the color test result, the tone test result, and the deformation test result.

[0042] Among them, clarity detection refers to the evaluation of the clarity of the image. By performing a clarity test on the first sub-image, the clarity value of the first sub-image can be obtained, that is, the clarity test result; the color test result includes a comprehensive value of color accuracy and saturation, that is, the color test result, where color accuracy can be evaluated by comparing the color in the image with the standard color, and saturation can be evaluated by measuring the saturation of the color. An image close to the standard color and with moderate saturation is considered to have better color performance. The tone test result may include the brightness and contrast values ​​of the image, that is, the tone test result, where the brightness can be represented by the average brightness of the pixels, and the contrast can be measured by the brightness difference of the pixels in the image. Higher brightness and contrast values ​​indicate that the image is clearer and has higher clarity. The deformation test result usually indicates the distortion or deformation in the image. The corresponding difference is calculated by comparing the difference between the actual shape of the object in the image and its expected shape, that is, the deformation test result.

[0043] Based on certain weighted calculations of the clarity test results, color test results, tone test results and deformation test results, a comprehensive quality detection score of the first sub-image, that is, a first quality detection result, can be obtained, wherein the higher the comprehensive quality detection score, the better the first quality detection result.

[0044] In the above embodiment, a comprehensive quality evaluation is performed on the first sub-image based on clarity, color, gradation and deformation, so that the imaging quality of the first sub-image can be accurately obtained.

[0045] In an optional implementation, performing a clarity test on the first sub-image to obtain a clarity test result includes: Performing Fourier transform on the first sub-image to obtain frequency domain data of the first sub-image; generating a modal transfer function curve according to the frequency domain data; The clarity test result is obtained according to the curve area of ​​the modal transfer function curve.

[0046] When performing clarity detection on the first sub-image, the first sub-image is first subjected to Fourier transform to convert the spatial domain data of the first sub-image into frequency domain data. The spatial domain data refers to the position distribution and brightness distribution of each pixel in the first sub-image. The frequency domain data is the amplitude data and phase data of a series of frequency components obtained by converting the position distribution and brightness distribution of each pixel through Fourier transform. That is, the spatial domain data is the first sub-image presented in the form of pixels in space, and the frequency domain data is the first sub-image presented in the form of frequencies in the frequency domain.

[0047] After obtaining the frequency domain data of the first sub-image, the frequency domain data is divided into different frequency ranges, and the low-frequency amplitude is obtained. In the divided frequency ranges, the amplitude of each frequency domain data is divided by the low-frequency amplitude to obtain the contrast of each frequency domain data. Based on each frequency domain data and the corresponding contrast, a modal transfer function curve is constructed with frequency as the X-axis and contrast as the Y-axis. The modal transfer function curve is used to describe the presentation of each frequency detail in the first sub-image. The higher the peak value, the higher the clarity of the corresponding pixel point.

[0048] After obtaining the modal transfer function curve, the clarity test result can be obtained by calculating the area under the modal transfer function curve, wherein the larger the area, the higher the quantity and quality of the high-frequency details in the first sub-image, reflecting the higher overall clarity of the first sub-image.

[0049] In the above embodiment, by converting the image from the spatial domain to the frequency domain through Fourier transform, the frequency components and structural characteristics of the first sub-image can be obtained, and by constructing the modal transfer function curve, the presentation of different frequency details in the first sub-image can be intuitively understood, and by calculating the area under the modal transfer function curve, the clarity of the first sub-image can be quantitatively evaluated, reflecting the quantity and quality of high-frequency details in the first sub-image, thereby directly reflecting the clarity level of the first sub-image, providing data support for imaging clarity quality detection of smartphone imaging modules.

[0050] In an optional implementation, performing a color test on the first sub-image to obtain a color test result includes: Performing spatial transformation on the first sub-image to obtain a first processed image; Performing saturation correction on the first processed image to obtain a second processed image; The color difference between the second processed image and the preset standard color image is calculated to obtain a color test result.

[0051] Space conversion refers to converting the RGB color space of the first sub-image into the Lab color space. The RGB color space refers to an additive color space composed of red, green, and blue. It is the default color space output by smartphone cameras. Various colors can be produced by mixing different degrees of the three primary colors of red, green, and blue. The Lab color space is a color space with uniform color perception. It includes brightness and two chromaticity adjustment channels a and b. The Lab color space can more accurately describe the difference between colors and can cover all colors that the human visual system can perceive. Converting the RGB color space to the Lab color space can more accurately process and evaluate the color quality of the first sub-image.

[0052] Saturation refers to the purity and intensity of the color in the first sub-image, and saturation correction refers to restoring and adjusting the color saturation in the first sub-image to eliminate the chromaticity deviation caused by saturation processing. Saturation processing refers to enhancing or reducing the color saturation of the first sub-image after shooting by the smartphone camera to improve the color vividness or softness of the image. By performing saturation correction, the initial saturation of the first sub-image captured by the smartphone imaging module can be obtained.

[0053] When performing color detection on the first sub-image, the three-channel values ​​of RGB of the first sub-image are converted to the XYZ color space, and then converted from the XYZ color space to the Lab color space to obtain a first processed image in the Lab color space. Saturation correction is performed according to the saturation deviation of different areas in the first sub-image. For areas with reduced saturation in the first sub-image, the saturation of the corresponding color is increased by increasing the values ​​of the a channel and the b channel in the Lab color space. For areas with increased saturation in the first sub-image, the saturation of the corresponding color is reduced by reducing the values ​​of the a channel and the b channel in the Lab color space, thereby restoring the saturation of the first processed image and obtaining the initial image saturation acquired by the smartphone imaging module, that is, the second color image.

[0054] Obtain the color value of the standard color of each pixel value in the second image, and for each pixel, calculate the color difference between the color value of each pixel point in the second processed image and the corresponding color value in the standard color image, The color difference of all pixels is summed or averaged to obtain the color difference value of the entire image, that is, the color test result.

[0055] In the above embodiment, by converting the RGB color space into the Lab color space, the color quality of the first sub-image can be more accurately processed and evaluated. The saturation correction can effectively eliminate the chromaticity deviation caused by the saturation processing, and the original color saturation of the first sub-image acquired by the smartphone imaging module is obtained, thereby ensuring the authenticity and accuracy of the color imaging quality detection of the smartphone module. By calculating the color difference between the first sub-image and the standard color image, the color accuracy of the image can be quantitatively evaluated, thereby providing color imaging data support for the imaging quality detection of the smartphone imaging module.

[0056] In an optional implementation, performing a tone test on the first sub-image to obtain a tone test result includes: Acquire input brightness data of the first sub-image; Obtaining a saturated exposure density of the first sub-image according to the input brightness data; Calculating grayscale noise data according to the saturated exposure density; A tone test result is obtained according to the grayscale noise data and preset standard noise data.

[0057] Among them, the input brightness data refers to the brightness value of each pixel in the first sub-image, which is used to represent the grayscale level of the first sub-image. The higher the input brightness data, the lower the corresponding grayscale level; the saturated exposure density refers to the measure of saturation and exposure in the first sub-image, which is used to evaluate the color and exposure of the first image; the grayscale noise data refers to the noise data existing in the first sub-image, which reflects the degree of noise in the first sub-image; the preset standard noise data refers to the image noise level under a predefined or ideal state, which is used to evaluate the difference between the noise level of the first sub-image and the noise level under the ideal state.

[0058] When performing a tone test on the first sub-image, the first sub-image is converted into a grayscale image, and the RGB value of each pixel therein is converted into a single brightness value, thereby obtaining input brightness data of the first sub-image. Saturation calculation is performed on the brightness data of each pixel in the input brightness data, and the saturation exposure density value is obtained by calculating the standard deviation of the brightness value of each pixel and obtaining the average of all standard deviations. The grayscale noise data is then determined based on the standard deviation of the saturation density value, and the grayscale noise data of the first sub-image is calculated differentially from the preset standard noise data, and the average of all differences is calculated to obtain a tone test result.

[0059] In the above embodiment, by converting the first sub-image into a grayscale image and calculating the brightness value of each pixel, the grayscale level of the image can be effectively represented; by calculating the standard deviation of the brightness value of each pixel, the saturated exposure density of the first sub-image can be obtained, and the saturation and exposure degree of the first sub-image can be acquired; by comparing the grayscale noise data of the first sub-image with the preset standard noise data, the noise level of the first sub-image can be quantitatively evaluated; by calculating the difference between the grayscale noise data of the first sub-image and the preset standard noise data, the gradation degree of the first sub-image can be quantitatively evaluated, thereby providing gradation data support for imaging quality detection of smartphone imaging modules.

[0060] In an optional implementation, performing a geometric deformation test on the first sub-image to obtain a deformation test result includes: Performing area dot division on the first sub-image to obtain a central dot and an actual edge dot set of the initial image; Obtain a standard edge point set according to the central point; The difference mean of the actual edge dot set and the standard edge dot set is calculated to obtain the deformation test result. When the first sub-image is subjected to geometric deformation detection, the region dot division is performed according to the distribution of each pixel point in the first sub-image, and the entire first sub-image is divided into different dot regions. Among them, the central pixel point is defined as the central dot, and the other pixel points are defined as the actual edge dot, and the actual edge dot set is composed of the actual edge dot points corresponding to all other pixel points.

[0061] Taking the center dot as the benchmark, the neural network model is trained according to the target object corresponding to the first sub-image, and the standard pixel distribution of other pixels corresponding to the center dot is predicted. The standard edge point set based on the center dot can be obtained, and the deviation between the actual edge point set and the standard edge point set is calculated. The difference calculation is performed on each pixel point and then the mean calculation is performed to obtain the deformation test result.

[0062] In the above embodiment, by dividing the first sub-image into regions and calculating the difference between the actual edge point set and the standard edge point set, the geometric deformation test result of the first sub-image is obtained, thereby providing deformation data support for the imaging quality detection of the smartphone imaging module.

[0063] In an optional implementation, obtaining the first quality inspection result based on the clarity test result, the color test result, the tone test result, and the deformation test result includes: Acquire multiple performance parameters corresponding to the smartphone imaging module; According to the parameter weight ratio corresponding to each of the performance parameters, the target parameter weight ratio is obtained; The clarity test result, the color test result, the tone test result and the deformation test result are weighted and calculated based on the target parameter weight ratio to obtain a target detection parameter; According to the target detection parameters, a match is performed in a preset database to obtain a quality detection result.

[0064] Before conducting image quality testing, various performance parameters of the smartphone imaging module will be obtained, which may include resolution, contrast, saturation performance parameters, etc., and based on the importance of each performance parameter in the overall quality assessment, its corresponding parameter weight ratio will be determined to reflect the degree of influence of each parameter on the final image quality.

[0065] Using the obtained parameter weight ratio, the test results of clarity, color, gradation and deformation are weighted and calculated to obtain the target detection parameters, ensuring that the final quality assessment can fully and accurately reflect the true quality status of the image. And the obtained target detection parameters are used to match in a pre-established database. Among them, the database may contain a large number of image samples and their corresponding quality assessment results. By comparing and matching with the samples in the database, the quality test results of the current image can be quickly and accurately obtained to determine the quality level of the image.

[0066] In the above embodiment, by matching the target detection parameters in the preset database, the quality detection result of the first sub-image can be accurately obtained.

[0067] S16, performing a quality inspection on the second sub-image in the target sub-image combination to obtain a second quality inspection result.

[0068] While performing quality inspection on the first sub-image, the second sub-image will also be subjected to quality inspection. By performing a clarity test on the second sub-image, a clarity test result of the second sub-image can be obtained. By performing a color test on the second sub-image, a color test result of the second sub-image can be obtained. By performing a gradation test on the second sub-image, a gradation test result of the second sub-image can be obtained. By performing a geometric deformation test on the second sub-image, a deformation test result of the second sub-image can be obtained. As with the technical solution described in S15, the clarity test result, color test result, gradation test result and deformation test result of the second sub-image are calculated to obtain a second quality inspection result for the second sub-image.

[0069] In the above embodiment, by performing quality detection on the second sub-image to obtain the quality detection result of the second sub-image, the quality detection results of the two images in the target sub-image combination are achieved, which more accurately reflects the imaging quality level in the initial image.

[0070] S17, obtaining a target quality detection result according to the first quality detection result and the second quality detection result.

[0071] After obtaining the first quality test result and the second quality test result, if the quality of the two sub-images is similar or there is no obvious difference, then any one of them can be selected as the target quality test result. If the quality of one sub-image is obviously better than the other, the quality test result with lower quality is selected to reflect the target quality test result. In addition, the first quality test result and the second quality test result and the corresponding test data will be output to generate a test report of the target quality test result.

[0072] In the above embodiment, by selecting a sub-image with lower quality to reflect the target quality detection result, it is ensured that even if there are sub-images with large differences, the overall quality assessment will not be affected by the poor image, thus ensuring the quality bottom line. At the same time, by performing quality detection on the two sub-images, it is prevented that one of the quality detection reports is abnormal, resulting in inaccurate quality detection results, which affects the accuracy of the quality assessment of the smartphone imaging module.

[0073] This application obtains multiple sub-images by segmenting the initial image collected by the smartphone imaging module, and configures a coding value for each sub-image and combines them to obtain multiple sub-image combinations, and selects a target sub-image combination with a correlation coefficient from the multiple sub-image combinations; performs a quality test on the first sub-image in the target sub-image combination to obtain a first quality test result; performs a quality test on the second sub-image in the target sub-image combination to obtain a second quality test result; and then determines the target quality test result based on the first quality test result and the second quality test result. This application divides the initial image into regions, selects the one with the lowest correlation coefficient and performs quality tests on the two sub-images, and detects the local region with the lowest correlation of the initial image, which more accurately reflects the quality of imaging, and can detect each local feature of the multi-characteristic initial image to evaluate the imaging quality of the smartphone imaging module, thereby accurately obtaining the imaging quality level of the smartphone imaging module.

[0074] See also Figure 2 The above is a functional module diagram of the imaging quality detection device of the smartphone imaging module provided in the embodiment of the present application.

[0075] In some embodiments, the imaging quality detection device 20 of the smartphone imaging module may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the imaging quality detection device 20 of the smartphone imaging module may be stored in the memory of the smartphone and executed by at least one processor to perform (see Figure 1 (Description) Functions of an imaging quality detection method for a smartphone imaging module.

[0076] In this embodiment, the imaging quality detection device 20 of the smartphone imaging module can be divided into multiple functional modules according to the functions it performs. The functional modules can include: a processing module 201, an encoding module 202, a combining module 203, a selecting module 204, a detecting module 205 and a generating module 206.

[0077] The processing module 201 is used to segment the initial image of the target object captured by the imaging module of the smart phone to obtain multiple sub-images.

[0078] The encoding module 202 is used to configure an encoding value for each sub-image according to the position of the sub-image in the initial image to obtain an encoding value set.

[0079] The combination module 203 is used to select any two coding values ​​from the coding value set to obtain multiple coding value combinations, each of which corresponds to a sub-image combination.

[0080] The selection module 204 is used to select a target sub-image combination from the plurality of sub-image combinations.

[0081] The detection module 205 is used to perform quality detection on the first sub-image in the target sub-image combination to obtain a first quality detection result.

[0082] The detection module 205 is further used to perform quality detection on the second sub-image in the target sub-image combination to obtain a second quality detection result; The generating module 206 is configured to obtain a target quality detection result according to the first quality detection result and the second quality detection result.

[0083] By adopting the above technical solution, by dividing the initial image into regions, selecting the region with the lowest correlation coefficient and performing quality detection on the two sub-images, it is possible to detect the local region with the lowest correlation degree of the initial image, which can more accurately reflect the quality of imaging. It is possible to detect each local feature of the initial image with multiple characteristics to evaluate the imaging quality of the smartphone imaging module, thereby accurately obtaining the imaging quality level of the smartphone imaging module.

[0084] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, all or part of the steps of the imaging quality detection method of the imaging module of the smartphone are implemented. Figure 1 and its related description.

[0085] See also Figure 3 FIG. 2 is a schematic diagram of the structure of a smart phone according to an embodiment of the present application. In a preferred embodiment of the present application, the smart phone 3 includes a memory 31 , at least one processor 32 , and at least one communication bus 33 .

[0086] Those skilled in the art should understand that Figure 3 The structure of the smartphone shown does not constitute a limitation of the embodiments of the present application, and may be either a bus structure or a star structure. The smartphone 3 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0087] In some embodiments, the smart phone 3 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The smart phone 3 may also include client devices, which include but are not limited to any electronic product that can interact with the client through a keyboard, mouse, remote control, touchpad, or voice control device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0088] It should be noted that the smartphone 3 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0089] In some embodiments, the memory 31 stores a computer program, and when the computer program is executed by the at least one processor 32, all or part of the steps in the imaging quality detection method of the imaging module of the smartphone are implemented. The memory 31 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data. Further, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store applications required to operate the smartphone, at least one function, etc.

[0090] In some embodiments, the at least one processor 32 is the control core (Control Unit) of the smartphone 3, and uses various interfaces and lines to connect various components of the entire smartphone 3, and executes various functions and processes data of the smartphone 3 by running or executing programs or modules stored in the memory 31, and calling data stored in the memory 31. For example, when the at least one processor 32 executes the computer program stored in the memory, it implements all or part of the steps of the imaging quality detection method of the smartphone imaging module described in the embodiment of the present application; or implements all or part of the functions of the imaging quality detection device of the smartphone imaging module. The at least one processor 32 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips.

[0091] In some embodiments, the at least one communication bus 33 is configured to realize connection and communication between the memory 31 and the at least one processor 32, etc. Although not shown, the smart phone 3 may also include a power supply (such as a battery) for powering each component. Preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so that the power management device can realize functions such as management of charging, discharging, and power consumption management. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The smart phone 3 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0092] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including several instructions for enabling a smart phone or a processor to execute parts of the methods described in various embodiments of the present application.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0094] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for detecting imaging quality of an imaging module of a smart phone, characterized in that: The method comprises: Segmenting an initial image of a target object captured by an imaging module of a smart phone to obtain a plurality of sub-images; According to the position of each sub-image in the initial image, a coding value is configured for the corresponding sub-image to obtain a coding value set; Selecting any two coding values ​​from the coding value set to obtain a plurality of coding value combinations, each coding value combination corresponding to a sub-image combination; Selecting a target sub-image combination from the plurality of sub-image combinations; Performing a quality inspection on a first sub-image in the target sub-image combination to obtain a first quality inspection result; Performing a quality inspection on a second sub-image in the target sub-image combination to obtain a second quality inspection result; A target quality detection result is obtained according to the first quality detection result and the second quality detection result.

2. The imaging quality detection method of the smart phone imaging module according to claim 1, characterized in that: The selecting a target sub-image combination from the plurality of sub-image combinations comprises: Calculating a correlation coefficient between two sub-images in each of the sub-image combinations; Select the smallest correlation coefficient from multiple correlation coefficients as the target correlation coefficient; The sub-image combination corresponding to the target correlation coefficient is used as the target sub-image combination.

3. The imaging quality detection method of the smart phone imaging module according to claim 1, characterized in that: The performing quality detection on the first sub-image to obtain a first quality detection result includes: Performing a clarity test on the first sub-image to obtain a clarity test result; Performing a color test on the first sub-image to obtain a color test result; Performing a tone test on the first sub-image to obtain a tone test result; Performing a geometric deformation test on the first sub-image to obtain a deformation test result; A first quality inspection result is obtained based on the clarity test result, the color test result, the tone test result, and the deformation test result.

4. The imaging quality detection method of the smart phone imaging module according to claim 3, characterized in that: The performing a clarity test on the first sub-image to obtain a clarity test result includes: Performing Fourier transform on the first sub-image to obtain frequency domain data of the first sub-image; generating a modal transfer function curve according to the frequency domain data; The clarity test result is obtained according to the curve area of ​​the modal transfer function curve.

5. The imaging quality detection method of the smart phone imaging module according to claim 3, characterized in that: The performing a color test on the first sub-image to obtain a color test result includes: Performing spatial transformation on the first sub-image to obtain a first processed image; Performing saturation correction on the first processed image to obtain a second processed image; The color difference between the second processed image and the preset standard color image is calculated to obtain a color test result.

6. The imaging quality detection method of a smart phone imaging module according to claim 3, characterized in that: The performing a tone test on the first sub-image to obtain a tone test result includes: Acquire input brightness data of the first sub-image; Obtaining a saturated exposure density of the first sub-image according to the input brightness data; Calculating grayscale noise data according to the saturated exposure density; A tone test result is obtained according to the grayscale noise data and preset standard noise data.

7. The imaging quality detection method of a smart phone imaging module according to claim 3, characterized in that: The performing a geometric deformation test on the first sub-image to obtain a deformation test result includes: Performing area dot division on the first sub-image to obtain a central dot and an actual edge dot set of the initial image; Obtain a standard edge point set according to the central point; The difference mean of the actual edge point set and the standard edge point set is calculated to obtain a deformation test result.

8. The imaging quality detection method of a smart phone imaging module according to claim 3, characterized in that: The obtaining of the first quality inspection result based on the clarity test result, the color test result, the tone test result and the deformation test result comprises: Acquire multiple performance parameters corresponding to the smartphone imaging module; According to the parameter weight ratio corresponding to each of the performance parameters, the target parameter weight ratio is obtained; The clarity test result, the color test result, the tone test result and the deformation test result are weighted and calculated based on the target parameter weight ratio to obtain a target detection parameter; According to the target detection parameters, a match is performed in a preset database to obtain a quality detection result.

9. A smart phone, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the imaging quality detection method for a smart phone imaging module as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the steps of the imaging quality detection method of an imaging module of a smart phone as described in any one of claims 1 to 8.

Images