WO2018035794A1 - System and method for measuring image resolution value - Google Patents

Abstract

A system and method for measuring an image resolution value. The method for measuring an image resolution value comprises: convoluting an image by using an image feature extractor, to extract a first feature image from a part of the image (240); down-sampling, by using the image feature extractor, the first feature image obtained by convolution to obtain a second feature image with low resolution (250); performing column transformation on the down-sampled second feature image by using the image feature extractor, to obtain a single-column feature vector (260); and performing resolution value calculation on the single-column feature vector by using a predicator, to obtain a resolution value of the image (270). The method can measure a resolution value of an image quickly, is easy in training, uses few parameters, and can measure the resolution value accurately in real time. The method is widely applicable to an optical imaging system and a medical imaging system.

Description

System and method for measuring image sharpness value Technical field

The invention belongs to the technical field of image processing, and in particular to a system for measuring image sharpness values.

Background technique

With the accelerated pace of life and the proliferation of wireless networks and mobile phones, images have become an important means of information acquisition and communication. Because the camera shakes, the relative motion of the target, the camera's own quality, etc., the sharpness of the image will be different, and the image sharpness is the most intuitive feeling of the user, and it is related to the user's information about the image. Acquisition and scene interpretation are a key factor in image quality. At present, there is no problem with the reference image sharpness measurement method: (1) the accuracy of the image sharpness measurement is not high; (2) a large amount of experimental data is needed for parameter selection, and the calculation amount thereof may not be applied to the real picture; 3) The test is performed on the LIVE database, and the scalability is poor; (4) The method of image sharpness measurement is complicated, and the measurement takes a long time.

Therefore, the prior art has yet to be improved and developed.

Summary of the invention

In order to solve the above problems in the prior art, an object of the present invention is to provide a system and method for measuring image sharpness values with less parameters, small amount of calculation, easy training, high precision, and high speed.

The present invention provides a method of measuring image sharpness values, the method comprising:

The image feature extractor is used to perform convolution processing on the image to obtain a first feature image in the local extraction of the image;

Performing down-sampling processing on the first feature image obtained by the convolution process by using the image feature extractor to obtain a second feature image with lower resolution;

Performing column transformation on the downsampled second feature image by using an image feature extractor to obtain a single column feature vector;

The single column feature vector is used to calculate a sharpness value using a predictor to obtain a sharpness value of the image.

Further, the image is convoluted by using multiple convolution kernels, and the calculation formula is as follows:

Where X _i is the received image to be tested, i represents the number of layers, k is the convolution kernel, M _j is the receptive field of the input layer, B is the bias term, and f is the activation function.

Further, the downsampling process is used to reduce the spatial resolution of the model and eliminate the offset and image distortion. The calculation formula of the downsampling process is:

W _j =f(β _j p(y _j )),

Where p is the sampling function and β is the weighting factor.

Further, the formula for the predictor to calculate the sharpness value of the image is:

Where X _i , Y are sample observations, σ is the smoothing factor, and n is the number of samples.

Further, before the image is subjected to convolution processing by using the image feature extractor, the method further includes:

The image feature extractor is trained to enable the image feature extractor to perform convolution and downsampling processing on the image to obtain a single column feature vector;

The predictor is trained to enable the predictor to perform an arithmetic process on the single-column feature vector to obtain a sharpness value of the image.

Further, after training the image feature extractor and the predictor, further comprising verifying the sharpness value measured by the image feature extractor and the predictor, and verifying that the image feature extractor cooperates with the predictor to measure The method of obtaining the sharpness value includes:

Inputting a reference image into the trained image feature extractor, the image feature extractor extracting features of the reference image and obtaining a single column reference feature vector;

The trained predictor inputs the single-column reference feature vector and performs an operation to obtain a sharpness reference value of the reference image;

Calculating a Pearson linear correlation parameter (LCC) and a Spearson sorting sequence related parameter (SROCC) according to the calculated sharpness reference value and the subjective sharpness value of the reference image;

Determining whether the value of the Pearson linear correlation parameter (LCC) is greater than or equal to a first threshold value, and whether the value of the Spearson Sorting Sequence Related Parameter (SROCC) is greater than or equal to a second threshold value; if yes, Then, the image feature extractor and the predictor are trained; if not, the image feature extractor and the predictor are not trained, and the image feature extractor and the predictor are continuously trained.

Further, the formula of the Pearson linear correlation parameter (LCC) and the Spearson sorting correlation parameter (SROCC) is:

Where n is the number of samples,

Are _{{x 1, x 2, ...} , x n} and _{{y 1, y 2, ...} , y n} is the mean, σ _x, σ _y, respectively, the difference to their standard, r _xi, r _yi are x The sorting position of _i and y _i in their respective data sequences.

Further, the method for training the image feature extractor includes:

Initialize, enter the training set;

Calculating the average squared error of the image feature extractor;

Determining whether the average squared error converges; if the average squared error converges, the training ends; if not, the residual is calculated;

Passing the residuals layer by layer in reverse to obtain the residual value of each layer;

Update the parameter values for weights and offsets.

Further, the formula for calculating the average squared error and residual of the image feature extractor model is:

Where m is the number of samples per batch, y is the sample label, nl is the output layer, y is the sample label, a is the output value, f is the activation function, and z is the upper layer neuron of the output layer.

Further, the formula for calculating the residual value of each layer is:

δ ^(l) = ((W ^(l) ) ^T δ ^(l+1) )·f'(z ^(l) ),

Where W ^(l) is the weight of the first layer.

Further, the calculation formula of the “update parameter value of the weighting value and the offset term” is:

among them,

Is the bias term of the first layer, and α is the learning rate.

Further, the method of training the predictor includes:

Inputting the training set into the trained image feature extractor to obtain a local single-column feature vector of the training set;

According to the single column feature vector and label of the training set, the regression value of the dependent variable to the independent variable is obtained.

The present invention also provides a system for measuring image sharpness values, the method of measuring image sharpness values as described above for measuring sharpness values of an image, the system comprising:

The image feature extractor is configured to: receive an image; extract a first feature image from the local image; and perform blur processing on the extracted first feature image to obtain a second feature image with a lower resolution; The processed second feature image is transformed into a single column feature vector;

The predictor is configured to perform a scoring calculation on the single-column feature vector to obtain a sharpness value of the image.

Further, the system further includes a trainer configured to train the image feature extractor to enable the image feature extractor to perform convolution and downsampling processing on the image to obtain a single column feature vector.

Further, the trainer is configured to:

Initialize, input the training set to the image feature extractor;

Calculating an average square error of the image feature extractor; determining whether the average squared error converges;

If the average squared error converges, the training ends; if not, the residual is calculated; the residual is inversely transmitted layer by layer to obtain the residual value of each layer; and the parameter values of the weight and the offset term are updated.

Further, the trainer is further configured to train the predictor to enable the predictor to perform an operation process on the single-column feature vector to obtain a sharpness value of the image.

Further, the trainer is configured to:

Inputting the training set into the trained image feature extractor to obtain a local single-column feature vector of the training set;

According to the single column feature vector and label of the training set, the regression value of the dependent variable to the independent variable is obtained.

Further, the system further includes a verifier configured to verify a sharpness value measured by the image feature extractor in conjunction with the predictor.

Further, the verifier is configured to:

Inputting the reference image into the trained image feature extractor, the image feature extractor performs feature extraction on the reference image and obtains a single column reference feature vector, and the trained predictor inputs the single column reference feature vector, and performs an operation to Obtaining a sharpness reference value of the reference image;

Calculating a sharpness reference value and a subjective sharpness value of the reference image, and calculating a Pearson linear correlation parameter (LCC) and a Spearson sorting sequence related parameter (SROCC);

Determining whether the value of the Pearson linear correlation parameter (LCC) is greater than or equal to a first threshold value, and whether the value of the Spearson Sorting Sequence Related Parameter (SROCC) is greater than or equal to a second threshold value; if yes, Then, the image feature extractor and the predictor are trained; if not, the image feature extractor and the predictor are not trained, and the image feature extractor and the predictor are continuously trained.

The beneficial effects of the invention:

The system and method for measuring image sharpness value provided by the invention can perform fast convolution and downsampling processing on the image to be measured by the image feature extractor to obtain a single column feature vector, and use a predictor to perform arithmetic processing on a single column feature vector. To get the sharpness value of the image. The system for measuring the image sharpness value of the invention can quickly measure the sharpness value of the image after the training is finished, the training difficulty is low, the used parameters are few, the measured sharpness value is accurate and high, and the real-time property is strong. Can be widely used in optical imaging systems and medical imaging systems.

DRAWINGS

The above and other aspects and features of embodiments of the present invention are described by the following description in conjunction with the drawings And the advantages will become clearer, in the drawing:

1 is a block diagram of a preferred embodiment of a system for measuring image sharpness values in accordance with an embodiment of the present invention;

2 is a schematic diagram of a system for measuring image sharpness values in an operating state according to an embodiment of the present invention;

3 is a flow chart of a method for measuring image sharpness values according to an embodiment of the present invention;

4 is a flowchart of a method for training an image feature extractor according to an embodiment of the present invention;

FIG. 5 is a flowchart of a method for training a predictor according to an embodiment of the present invention; FIG.

6 is a flow chart of a method for verifying whether a measured sharpness value is accurate according to an embodiment of the present invention.

detailed description

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the invention may be embodied in many different forms and the invention should not be construed as being limited to the specific embodiments set forth herein. Rather, these embodiments are provided to explain the principles of the invention and its application, and the various embodiments of the invention can be understood by those skilled in the art. The same reference numerals are used throughout the specification and drawings to refer to the same.

The current methods for measuring image sharpness values are mainly divided into reference (the optimal image quality considered by the senses as a comparison), semi-reference (partial information of the optimal image with sensory perception as a comparison) and no reference ( There are no direct or indirect information to evaluate the image. Embodiments of the present invention are based on the principle of no reference image sharpness measurement to achieve measurement of image sharpness values.

In addition, the present invention also implements measurement of image sharpness values based on the principle of deep learning. Deep learning transforms the feature representation of the sample in the original space into a new feature space by transforming the feature image of the sample image layer by layer. It automatically learns the hierarchical features, reduces manual parameter selection and feature selection, and is more conducive to classification or feature. Visualization, at the same time, can well avoid the limitations caused by manually setting features, greatly improving the accuracy and efficiency of image sharpness measurement.

1 is a block diagram of a preferred embodiment of a system for measuring image sharpness values in accordance with an embodiment of the present invention. 2 is a schematic diagram of a system for measuring image sharpness values in an operating state according to an embodiment of the present invention.

1 and 2, a system for measuring image sharpness values according to an embodiment of the present invention includes an image feature extractor 10, a predictor 20, a trainer 30, and a verifier 40.

The image feature extractor 10 includes an image receiving module 11, a convolution module 12, a downsampling module 13, and a transform processing module 14. The image receiving module 10 is configured to receive an image. The convolution module 12 is configured to extract a first feature image in a local portion of the image; the downsampling module 13 is configured to perform a downsampling process on the first feature image obtained by the convolution process to obtain a resolution a lower second feature image; the transform processing module 14 is configured to transform the second feature image processed by the downsampling module 13 into a single column feature vector. In this embodiment, the single column feature vector is specifically a 200-dimensional vector. However, the invention is not limited thereto.

In the present embodiment, the image feature extractor 10 is preferably formed by a convolutional neural network configuration, and the convolutional neural network is simply referred to as CNN. The image feature extractor 10 may be specifically configured as an FPGA circuit or a chip, but the present invention is not limited thereto.

The predictor 20 includes an arithmetic processing module 21. The operation processing module 21 is configured to perform a calculation score on the single column feature vector to obtain a sharpness value of the image.

The operation processing module 21 specifically includes a summation layer 211 and an output layer 212. Specifically, the predictor 20 further includes an input layer 22, a mode layer 23 configured to pass a single column feature vector obtained by the image feature extractor 10 to the mode layer 22; the input layer 22 includes a plurality of first neurons, The number of first neurons is equal to the dimension of the single column feature vector extracted by the image feature extractor 10 from the image. The mode layer 23 is configured to correspond one-to-one to each sample data in the single-column feature vector, and the mode layer 23 also includes a plurality of second neurons, the number of the second neurons being equal to the number of the first neural units. The search layer 211 includes only two third neurons, the summation layer 211 is fully connected to the mode layer 23, and the operation between the summation layer 211 and the mode layer 23 (as shown in the following formula), and the output layer 212 is calculated. And the two output quotients of layer 211, the sharpness value of the final image is obtained. The formula for the predictor 20 to calculate the sharpness value of the image is:

Where X _i , Y are sample observations, σ is the smoothing factor, and n is the number of samples.

In order to reduce the difficulty of training, increase the speed of the calculation, and quickly measure the sharpness value of the image, the predictor 20 is preferably formed by a generalized regression neural network configuration. The predictor 20 may be specifically configured as an FPGA circuit or a chip, but the present invention is not limited thereto. The generalized regression neural network is abbreviated as GRNN, and the English is called the General regression neural network. Generalized regression neural network Neural network) is a variant of artificial neural networks with strong nonlinear mapping and generalization capabilities for small sample data. However, the present invention is not limited thereto, and for example, as another embodiment of the present invention, the predictor 20 may also be a support vector regression. Support vector regression is abbreviated as SVR, and English is called Support vector regression.

The trainer 30 is configured to train the image feature extractor 10 and the predictor 20 to enable the image feature extractor 10 and the predictor 20 to automatically learn hierarchical features, thereby achieving depth-based reference-free image clarity. The measurement of the degree value obtains an accurate sharpness value of the image to be tested. Specifically, the trainer is configured to train the image feature extractor to enable the image feature extractor to perform convolution and downsampling processing on the image to obtain a single column feature vector. The trainer is further configured to train the predictor to enable the predictor to perform an arithmetic process on the single column feature vector to obtain a sharpness value of the image. The trainer 30 may be specifically configured as an FPGA circuit or a chip, but the present invention is not limited thereto.

The verifier 40 is configured to verify the sharpness value obtained by the image feature extractor 10 in conjunction with the predictor measurement 20. More specifically, the verifier 40 is configured to verify whether the sharpness value obtained by the image feature extractor 10 in conjunction with the predictor measurement 20 is accurate or accurate. The verifier 40 may be specifically configured as an FPGA circuit or a chip, but the present invention is not limited thereto.

The system for measuring image sharpness values of embodiments of the present invention may be integrated into a machine system to score the acquired images to determine imaging capabilities of the machine system, including but not limited to optical imaging systems, and may also include medical imaging systems.

Specifically, as another embodiment of the present invention, the system for measuring image sharpness values can be applied to an image pickup apparatus. In this embodiment, the image capturing apparatus is capable of continuously taking a plurality of photographs, and the system for measuring the image sharpness value respectively measures the sharpness values of the plurality of photographs of the continuous shooting, and the image capturing apparatus is configured to compare the plurality of sharpness values. The size, which in turn outputs the photo corresponding to the maximum sharpness value (that is, the highest quality photo). It can be seen that the system for measuring the image sharpness value is applied to the image pickup device, and the photograph of the photograph with higher quality can be output for the user.

Still further, as still another embodiment of the present invention, the system for measuring image sharpness values can also be applied to a device for judging image quality. In this embodiment, the system for measuring the image sharpness value measures the sharpness value of the image to be tested. Set a reference threshold. The means for judging image quality is configured to compare a sharpness value of the image to be tested with a reference threshold, and when the sharpness value is greater than the reference threshold, determine that the sharpness of the image is clear; The sharpness value is small At the reference threshold, it is determined that the sharpness of the image is unclear.

The present invention also provides a method of the system for measuring image sharpness values. The method for measuring the image sharpness value of the system of the embodiment of the invention can be integrated into some image enhancement algorithms, and the parameters of the algorithm are optimized.

3 is a flow chart of a method of measuring image sharpness values in accordance with an embodiment of the present invention. Specifically, referring to FIG. 1 , FIG. 2 and FIG. 3 , in combination with the above system for measuring image sharpness value, the method for measuring image sharpness value specifically includes:

In operation 210, the image feature extractor 10 is trained to enable the image feature extractor 10 to sequentially perform convolution and downsampling processing on the image, thereby obtaining a single column feature vector. Here, the image feature extractor 10 is trained by the trainer 30. It should be noted that in the system framework of this embodiment, there is one and only one feature layer.

4 is a flow chart of a method of training an image feature extractor in accordance with an embodiment of the present invention. Specifically, referring to FIG. 4, the method for training the image feature extractor 10 specifically includes the following operations:

In operation 211, initialization is performed and a training set is input. Specifically, all convolution kernel weights and offset tops are initialized while the training set sample image is input to the image feature extractor 10. Here, the training set includes sample images with precise sharpness values.

In operation 212, the average squared error of image feature extractor 10 is calculated. Specifically, the sample image is obtained by calculating the output value O, and then calculating the output value O and the sample label y to obtain the model error value E. Whether the image feature extractor 10 model converges is judged by the error value, and if it converges, the training ends; if it does not converge, the residual of the output layer is continuously calculated. The specific formula for calculating the average squared error and residual of the image feature extractor 10 model is:

Where m is the number of samples per batch, y is the sample label, nl is the output layer, y is the sample label, a is the output value, f is the activation function, and z is the upper layer neuron of the output layer.

In operation 213, the residuals are reversed layer by layer to obtain residual values for each layer. The residual value of each layer indicates that the node has a corresponding effect on the residual of the final output value. The formula for calculating the residual value of each layer is:

δ ^(l) = ((W ^(l) ) ^T δ ^(l+1) )·f'(z ^(l) ),

Where W ^(l) is the weight of the first layer.

In operation 214, the parameter values of the weights and offsets are updated according to each layer residual calculation formula. The calculation formula of the parameter value of the update weight and offset term is:

among them,

Is the bias term of the first layer, and α is the learning rate.

In operation 220, the predictor 20 is trained to enable the predictor 20 to perform an arithmetic process on the single column feature vector to obtain a sharpness value of the image. Here, the predictor 20 is trained using the trainer 30.

FIG. 5 is a flow chart of a method for training a predictor according to an embodiment of the present invention. Specifically, referring to FIG. 5, the method for training the predictor 20 includes the following operations:

In operation 221, the training set is input to the trained image feature extractor 10 to obtain a single column feature vector of the training set. Specifically, the single column feature vector is a 200-dimensional vector.

In operation 222, a regression value of the dependent variable to the independent variable is calculated according to the single column feature vector and the label of the training set.

In operation 230, after training the image feature extractor 10 and the predictor 20, it is further included to verify whether the sharpness value measured by the image feature extractor 10 in conjunction with the predictor 20 is accurate. Here, the verifier 40 is used to verify whether the sharpness value measured by the image feature extractor 10 in conjunction with the predictor 20 is accurate.

6 is a flow chart of a method for verifying whether a measured sharpness value is accurate according to an embodiment of the present invention. Specifically, referring to FIG. 6, the method for verifying whether the image feature extractor 10 cooperates with the predictor 20 to determine whether the sharpness value is accurate includes the following operations:

In operation 231, the reference image is input to the trained image feature extractor 10, which performs feature extraction on the reference image and obtains a single column reference feature vector.

In operation 232, the trained predictor 20 inputs the single column reference feature vector and performs an operation to obtain a sharpness reference value of the reference image.

In operation 233, a Pearson linear correlation parameter (LCC) and a spearson ordering correlation parameter (SROCC) are calculated based on the calculated sharpness reference value and the subjective sharpness value of the reference image; the Pearson linearity The relevant parameters (LCC) and the Spearson Sorting Related Parameters (SROCC) are calculated as:

Where n is the number of samples,

Are _{{x 1, x 2, ...} , x n} and _{{y 1, y 2, ...} , y n} is the mean, σ _x, σ _y, respectively, the difference to their standard, r _xi, r _yi are x The sorting position of _i and y _i in their respective data sequences.

It should be noted that the Pearson linear correlation coefficient (LCC) is used to measure the accuracy of the prediction results. The Pearson rank-order correlation coefficient (SROCC) is used to measure the monotonicity of the prediction results.

In operation 234, it is determined whether the value of the Pearson linear correlation parameter (LCC) is greater than or equal to a first threshold value, and whether the value of the Spearson Sorting Sequence Related Parameter (SROCC) is greater than or equal to a second gate The limit value; if so, the image feature extractor and the predictor are trained to obtain an accurate sharpness value; if not, the image feature extractor and the predictor are not trained, and the image feature extractor and the predictor are continuously trained.

The first threshold value may be 0.8, 0.9, 0.91, 0.92. Preferably, in the embodiment, the first threshold value is preferably 0.9. The second threshold value may also be 0.8, 0.9, 0.91, 0.92. Preferably, in the embodiment, the second threshold value is preferably 0.9. Of course, the present invention is not limited thereto, and the first threshold value and the second threshold value may be appropriately changed according to actual conditions.

It should be noted that the above-mentioned "training the image feature extractor 10", "training the predictor 20", and "verifying whether the image feature extractor 10 matches the sharpness value measured by the predictor 20" is accurate. The method operation is an operation that needs to be performed when constructing a system for measuring image sharpness values, and it is not necessary to perform the above operations each time the image sharpness value is measured. When the system for measuring the image sharpness value is trained and verified, it is equivalent to completing the training and learning process of the system. Therefore, after the test When the image sharpness value is measured, the sharpness value measurement of the non-reference image can be realized, and the measurement speed and accuracy can be greatly improved. The operation of measuring the image sharpness value is as follows:

With continued reference to Figures 1, 2 and 3, in operation 240, the image is subjected to convolution processing using image feature extractor 10 to obtain a first feature image at a localized extraction of the image. Specifically, the image to be tested is received by the image receiving module 11, and the image is convoluted by the convolution module 12. Here, the image receiving module 11 directly receives the image to be tested, and does not require excessive preprocessing of the image to be measured, thereby improving work efficiency. Specifically, the image is convoluted using a plurality of convolution kernels k, and the calculation formula is as follows:

Where X _i is the received image to be tested, l represents the number of layers, k is the convolution kernel, M _j is the receptive field of the input layer, B is the bias term, and f is the activation function. Here, the number of the convolution cores is preferably eight, but the present invention is not limited thereto.

In operation 250, the local feature image obtained by the convolution process is downsampled by the image feature extractor 10 to obtain a second feature image. Specifically, the downsampling module 13 performs downsampling processing on the local first feature image obtained by the convolution process. The downsampling process is used to reduce the spatial resolution of the model and eliminate offset and image distortion. The calculation formula for downsampling is:

W _j =f(β _j p(y _j )),

Where p is the sampling function and β is the weighting factor.

In operation 260, the downsampled second feature image is transformed by the image feature extractor 10 to obtain a single column feature vector. Here, after multiple convolution and downsampling operations, several feature images (feature vectors) can be obtained, and all feature vectors are transformed into a single column of feature vectors. Specifically, the second feature image after the downsampling process is transformed by the transform processing module 14.

In operation 270, the single column feature vector is input using the predictor 20, and the single column feature vector is calculated to obtain a sharpness value of the image. Here, the calculation of the image sharpness value is performed on the single-column feature vector by the arithmetic processing module 21. Specifically, a single column feature vector is input to the input layer 22, and the input layer 22 passes the single column feature vector obtained by the image feature extractor 10 to the mode layer 22, and the mode layer 23 and each sample data in the single column feature vector are a correspondence, and layer 211 and mode The layer 23 is fully connected, and an operation is performed between the summing layer 211 and the mode layer 23 (as shown in the following "The formula of the predictor 20 for calculating the sharpness value of the image"), and the output layer 212 calculates the summing layer 211. The two output quotients give the final image clarity value. The formula for the predictor 20 to calculate the sharpness value of the image is:

Where X _i , Y are sample observations, σ is the smoothing factor, and n is the number of samples.

Preferably, in the embodiment of the present invention, the parameters of the system and method for measuring the image sharpness value are: (1) the number of image blocks to be tested is 200; (2) the size of the image block to be tested is [16 16]; (3) the size of the convolution kernel is [7 7]; (4) the number of convolution kernels is 8; (5) the number of iterations is 120; (6) generalization of generalized regression neural networks The parameter is 0.01; (6) the verification parameter is 1.8, and the verification parameter is used for selecting the advantages and disadvantages of the network learning. Of course, the invention is not limited thereto.

The Pearson linear correlation parameter (LCC) and the Spearson sorting correlation parameter (SROCC) range from 0 to 1, and the Pearson linear correlation parameter (LCC) and the Spearson ordering related parameter (SROCC) The larger the value, the higher the accuracy and performance of the system for measuring image sharpness values.

The Pearson linear correlation parameter LCC comparison results are shown in Table 1. Referring to Table 1, the image feature extractor 10 proposed in this embodiment is a convolutional neural network (CNN) and the predictor 20 is a generalized regression neural network (GRNN) on the LIVE, CSIQ library, or TID2008 and TID2013 libraries. The system (CNN-GRNN) is able to effectively predict the sharpness of the image. Similarly, the image feature extractor 10 proposed by another embodiment of the present invention is a convolutional neural network (CNN), and the predictor 20 is a support vector regression (SVR) system (CNN-SVR) can achieve the same technical effect. . Especially in the CSIQ, TID2008 and TID2013 libraries, the system consisting of a system of generalized regression neural networks (CNN-GRNN) and a system of support vector regression (CNN-SVR) is more accurate than the system composed of the other three algorithms. Reliable (approximately 0.05 to 0.16), more efficient and accurate.

The comparison results of Spilson for Spilson sorting successively are shown in Table 2. Please refer to Table 2, whether on the LIVE, CSIQ library, or TID2008 and TID2013 libraries, the image feature extractor 10 is a convolutional neural network (CNN), and the predictor 20 is a generalized regression neural network (GRNN) system (CNN). -GRNN) and image feature extractor 10 is a convolutional neural network (CNN), predictor 20 solutions for support vector regression (SVR) are superior to other solutions. Furthermore, the system consisting of a generalized regression neural network (CNN-GRNN) and a support vector regression (CNN-SVR) is more accurate and effective on the TID2008 and TID2013 libraries.

Table 1 Pearson linear correlation parameters LCC test results

Table 2 Spelson Sorting Related Parameters SROCC Test Results

In summary, according to the embodiment of the present invention, the method for measuring the image sharpness value can perform fast convolution and downsampling processing on the image to be measured by the feature extractor to obtain a single-column feature vector, and use the predictor to single-column feature vector. Perform a quick calculation to get the sharpness value of the image. The system for measuring the image sharpness value of the invention can quickly measure the sharpness value of the image after the training is finished, the training difficulty is low, the used parameters are few, the measured sharpness value is accurate and high, and the real-time property is strong. Can be widely used in optical imaging systems and medical imaging systems.

Although the present invention has been shown and described with respect to the specific embodiments of the present invention, Various changes in form and detail can be made here.

Claims (19)

1. A method of measuring image sharpness values, including:

   The image feature extractor is used to perform convolution processing on the image to obtain a first feature image in the local extraction of the image;

   Performing down-sampling processing on the first feature image obtained by the convolution process by using the image feature extractor to obtain a second feature image with lower resolution;

   Performing column transformation on the downsampled second feature image by using an image feature extractor to obtain a single column feature vector;

   The single column feature vector is used to calculate a sharpness value using a predictor to obtain a sharpness value of the image.
2. The method of measuring an image sharpness value according to claim 1, wherein the image is subjected to convolution processing using a plurality of convolution kernels, and the calculation formula is as follows:

   

   Where X _i is the received image, i is the number of layers, k is the convolution kernel, M _j is the receptive field of the input layer, B is the bias term, and f is the activation function.
3. The method of measuring image sharpness values according to claim 1, wherein said downsampling processing is for reducing spatial resolution of the model and eliminating offset and image distortion, and the calculation formula for downsampling processing is:

   W _j =f(β _j p(y _j )),

   Where p is the sampling function and β is the weighting factor.
4. The method of measuring an image sharpness value according to claim 1, wherein the predictor calculates a sharpness value for the image as:

   

   Where X _i , Y are sample observations, σ is the smoothing factor, and n is the number of samples.
5. A method of measuring an image sharpness value according to claim 1, wherein the image is utilized Before the feature extractor convolves the image, it also includes:

   The image feature extractor is trained to enable the image feature extractor to perform convolution and downsampling processing on the image to obtain a single column feature vector;

   The predictor is trained to enable the predictor to perform an arithmetic process on the single-column feature vector to obtain a sharpness value of the image.
6. The method of measuring an image sharpness value according to claim 5, wherein after training the image feature extractor and the predictor, further comprising verifying a sharpness value measured by the image feature extractor in conjunction with the predictor And the method for verifying that the image feature extractor matches the sharpness value measured by the predictor includes:

   Inputting a reference image into the trained image feature extractor, the image feature extractor extracting features of the reference image and obtaining a single column reference feature vector;

   The trained predictor inputs the single-column reference feature vector and performs an operation to obtain a sharpness reference value of the reference image;

   Calculating a Pearson linear correlation parameter (LCC) and a Spearson sorting sequence related parameter (SROCC) according to the calculated sharpness reference value and the subjective sharpness value of the reference image;

   Determining whether the value of the Pearson linear correlation parameter (LCC) is greater than or equal to a first threshold value, and whether the value of the Spearson Sorting Sequence Related Parameter (SROCC) is greater than or equal to a second threshold value; if yes, Then, the image feature extractor and the predictor are trained; if not, the image feature extractor and the predictor are not trained, and the image feature extractor and the predictor are continuously trained.
7. The method of measuring an image sharpness value according to claim 6, wherein the formula of the Pearson linear correlation parameter (LCC) and the Spearson Sorting Sequence Related Parameter (SROCC) is:

   

   

   Where n is the number of samples,

   

   Respectively _{{x1, x 2, ...,} x n} and _{{y 1, y 2, ...} , y n} is the mean, σ _x, σ _y, respectively, the difference to their standard, r _xi, r _yi are x _i And the position of y _i in their respective data sequences.
8. The method of measuring an image sharpness value according to claim 5, wherein the method of training the image feature extractor comprises:

   Initialize, enter the training set;

   Calculating the average squared error of the image feature extractor;

   Determining whether the average squared error converges; if the average squared error converges, the training ends; if not, the residual is calculated;

   Passing the residuals layer by layer in reverse to obtain the residual value of each layer;

   Update the parameter values for weights and offsets.
9. The method of measuring an image sharpness value according to claim 8, wherein the formula for calculating an average square error and a residual of the image feature extractor model is:

   

   

   Where m is the number of samples per batch, y is the sample label, nl is the output layer, y is the sample label, a is the output value, f is the activation function, and z is the upper layer neuron of the output layer.
10. A method of measuring an image sharpness value according to claim 8, wherein the formula for calculating the residual value of each layer is:

    δ ^(l) = ((W ^(l) ) ^T δ ^(l+1) )·f'(z ^(l) ),

    Where W ^(l) is the weight of the first layer.
11. The method of measuring an image sharpness value according to claim 8, wherein the calculation formula of the "update weight and parameter value of the offset term" is:

    

    

    among them,

    

    Is the bias term of the first layer, and α is the learning rate.
12. The method of measuring an image sharpness value according to claim 5, wherein the method of training the predictor comprises:

    Inputting the training set into the trained image feature extractor to obtain a part of the training set Single column feature vector;

    According to the single column feature vector and label of the training set, the regression value of the dependent variable to the independent variable is obtained.
13. A system for measuring image sharpness values, wherein the system comprises:

    The image feature extractor is configured to: receive an image; extract a first feature image from the local image; and perform blur processing on the extracted first feature image to obtain a second feature image with a lower resolution; The processed second feature image is transformed into a single column feature vector;

    The predictor is configured to perform a scoring calculation on the single-column feature vector to obtain a sharpness value of the image.
14. A system for measuring image sharpness values according to claim 13 wherein said system further comprises a trainer configured to train the image feature extractor to enable the image feature extractor to The image is convoluted and downsampled to obtain a single column feature vector.
15. A system for measuring image sharpness values according to claim 14, wherein the trainer is configured to:

    Initialize, input the training set to the image feature extractor;

    Calculating an average square error of the image feature extractor; determining whether the average squared error converges;

    If the average squared error converges, the training ends; if not, the residual is calculated; the residual is inversely transmitted layer by layer to obtain the residual value of each layer; and the parameter values of the weight and the offset term are updated.
16. The system for measuring image sharpness values according to claim 14, wherein the trainer is further configured to train a predictor to enable the predictor to perform arithmetic processing on the single-column feature vector, Thereby the sharpness value of the image is obtained.
17. A system for measuring image sharpness values according to claim 16, wherein the trainer is configured to:

    Inputting the training set into the trained image feature extractor to obtain a local single-column feature vector of the training set;

    According to the single column feature vector and label of the training set, the regression value of the dependent variable to the independent variable is obtained.
18. A system for measuring image sharpness values according to claim 13 wherein said system further comprises a validator configured to verify said image feature extractor to cooperate with said pre- The sharpness value measured by the detector.
19. A system for measuring image sharpness values according to claim 18, wherein said verifier is configured to:

    Inputting the reference image into the trained image feature extractor, the image feature extractor performs feature extraction on the reference image and obtains a single column reference feature vector, and the trained predictor inputs the single column reference feature vector, and performs an operation to Obtaining a sharpness reference value of the reference image;

    Calculating a sharpness reference value and a subjective sharpness value of the reference image, and calculating a Pearson linear correlation parameter (LCC) and a Spearson sorting sequence related parameter (SROCC);

    Determining whether the value of the Pearson linear correlation parameter (LCC) is greater than or equal to a first threshold value, and whether the value of the Spearson Sorting Sequence Related Parameter (SROCC) is greater than or equal to a second threshold value; if yes, Then, the image feature extractor and the predictor are trained; if not, the image feature extractor and the predictor are not trained, and the image feature extractor and the predictor are continuously trained.

Images