65 results about "Reference free" patented technology

The invention discloses a convolutional-neural-network-based reference-free three-dimensional image quality evaluation method. The method comprises the following steps: carrying out pretreatment on a 2D image; to be specific, inputting an image block obtained by pretreatment into a deep convolutional neural network, carrying out convolutional pooling processing to obtain an advanced feature of the image block, and then carrying out BP training by using the neural network based on a mass fraction of an original image so as to obtain a parameter of a base model; obtaining a corresponding basic model according to the parameter of the base model, carrying out centering on a three-dimensional image and carrying out pretreatment identical with that of the 2D image on the left image and the right image, and inputting the image blocks at the same position into the basic module simultaneously to obtain a corresponding advanced feature vector; and carrying out testing under a LIVE 3D database. On the basis of the reference-free evaluation algorithm, a good result better that the existing quality evaluation result can be obtained.

The invention relates to an ORB (object request broker) operator-based reference-free video smoothness evaluation method. The method comprises the following steps: taking continuous n frames of images of a video, and extracting ORB feature points from the n frames of images; matching the ORB feature points in every two adjacent frames of images; screening and removing the mismatched ORB feature points of two adjacent frames of images; generating an affine transformation matrix between every two adjacent frames of images, namely a homography matrix between every two adjacent frames of images, according to a motion affine transformation model, and gradually performing iterative solution on the homography matrix A; calculating motion parameters between every two adjacent frames of images, wherein the motion parameters comprise translation and rotation angels of the images; generating a translational motion trajectory and a rotary motion trajectory of a video sequence; performing filtering processing on the translational motion trajectory and the rotary motion trajectory by utilizing a Gauss filter to obtain a filtered translational motion trajectory and a filtered rotary motion trajectory; calculating a transitional jitter number and a rotary jitter number, calculating a horizontal smoothness value and a rotary smoothness value, and judging the smoothness of the video.

The invention discloses a reference-free type image quality evaluation method based on the shape consistency of a condition histogram. The reference-free type image quality evaluation method comprises the following steps: S1: carrying out nonlinear processing on a distorted image; S2: carrying out feature extraction on the image subjected to the nonlinear processing and extracting a combined histogram and a condition histogram curve histo (Y / Xi); solving a condition histogram average value; S3: utilizing the condition histogram curve histo (Y / Xi) and the condition histogram average value to solve a quality evaluation index D for judging the image quality. The quality evaluation index D obtained by using the method disclosed by the invention is simple and practical and the distortion degree of the distorted image can be effectively reflected; compared with a data training method, according to the method disclosed by invention, the obtained evaluation index has better objectivity and stability.

The invention discloses a reference-free three-dimensional picture quality objective evaluation method based on machine learning. The reference-free three-dimensional picture quality objective evaluation method comprises the steps that a vision dictionary list is structured in a training stage, sparse coefficient matrixes of all subblocks in a left viewpoint picture and all subblocks in a right viewpoint picture are calculated respectively for the left view point picture and the right view point picture of any distortion three-dimensional picture according to the structured vision dictionary list, the characteristic vector of the left viewpoint picture and the characteristic vector of the right viewpoint picture are obtained through the maximum pooling method, characteristic extraction is simple, and the computation complexity is low; a support vector regression training model of the left viewpoint picture and a support vector regression training model of the right viewpoint picture are structured, objective quality evaluation predictive values, corresponding to each characteristic vector in a test sample data set, of the left viewpoint picture and the right viewpoint picture respectively are obtained through prediction, weighing is conducted according to characteristic vector information, the objective quality evaluation prediction value of the three-dimensional picture is obtained, and the correlation between the objective evaluation result and subjective perception is high.

The invention discloses a steel coil storeroom position dynamic distribution method under a position-data-reference-free condition. The steel coil storeroom position dynamic distribution method includes the steps of dividing storeroom areas to form gridding structures, building a storeroom position distribution database in a management server of the storeroom areas, then determining a stacking rule of the storeroom areas, enabling each storeroom area to serve as a whole, carrying out stacking according to the same rule, carrying out stacking among the storeroom areas according to different demands and different user demand rules, dynamically modifying the user demand rule of the storeroom area to carry out stacking when the demands of the certain storeroom area are changed, and finally, after the steps are completed, carrying out management on steel coil storage, steel coil delivery, steel coil transferring and steel coil checking. According to the steel coil storeroom position dynamic distribution method, under the condition that a traveling positioning system is not provided, a dynamic storeroom position management mode is used for a steel coil storeroom, steel coils are reasonably and accurately stacked, the storeroom area use rate is improved, and the stack transferring quantity is reduced; meanwhile, the operation actual performance is collected, and therefore the position information of the steel coils inside the steel coil storeroom is accurate.

The invention discloses a reference-free image quality evaluation method based on a hierarchical feature fusion network, which mainly solves the problems of low precision and slow speed of the prior art. The implementation scheme is as follows: 1. The reference image is selected from MSCOCO data set and the polluted image database is established by adding noise; 2. Simultaneously de-averaging andprune that training set image and the t set image; 3. According to the hierarchical processing mechanism of human visual system from local features to global semantics, a hierarchical feature fusion network model is designed for end-to-end joint optimization. 4, train that hierarchical feature fusion network model by using a training set and a t set; 5, carry out de-averaging and cutting process on that images to be evaluated, and inputting the process images into a trained hierarchical feature fusion network model to obtain an image quality prediction score; The invention greatly improves theaccuracy and speed of no reference quality evaluation, and can be used for image screening, compression and video quality monitoring.

Disclosed in the invention is a natural-scene-based reference-free high-dynamic image quality evaluation algorithm. The algorithm is implemented as follows: step one, carrying out perceptually uniform(PU) coding on an HDR image to obtain a corresponding LDR image; step two, carrying out mean subtracted contrast normalization on the LDR image; step three, extracting an image feature of a salient region image block; and step four, carrying out image quality calculation, obtaining features of an original HDR image and a distorted HDR image, and carrying out fitting by using an MVG model to obtain a mean value and a variance matrix v- and sigma. Compared with the prior art, the natural-scene-based reference-free high-dynamic image quality evaluation algorithm has the following advantages: theconsistency with the human-eye-based objective high-dynamic image quality evaluation is high; no complicated conversion is needed during the calculation process; the complexity is low; the real-timehigh-dynamic image quality evaluation is realized; because of combination of the high-dynamic image with the reference-free image quality evaluation, the universality is high; and the novel idea is provided for the study on the high-dynamic image quality evaluation.

The invention discloses a reference-free image quality evaluation method based on image entropy. The method comprises the following steps of (1) extracting image features to be tested, and identifyingthe probability pi of each distortion type of the image to be tested by using a support vector classifier (SVC), wherein the image features include mutual information between different color channels, two-dimensional entropy of gray image and two-dimensional entropy and mutual information of filtered sub-band image; 2 respectively assuming that the images to be tested belong to a certain distortion type, calculating a score qi corresponding to the distortion type by the support vector regression (SVR), and obtaining a quality index of the image to be tested by weight sum. Experiments on LIVEand TID2013 databases show that the algorithm has good performance and consistency of subjective and objective evaluation.

Reference-free compensated imaging makes an estimation of the Fourier phase of a series of images of a target. The Fourier magnitude of the series of images is obtained by dividing the power spectral density of the series of images by an estimate of the power spectral density of atmospheric turbulence from a series of scene based wave front sensor (SBWFS) measurements of the target. A high-resolution image of the target is recovered from the Fourier phase and the Fourier magnitude.

Methods and apparatus to evaluate the semantic proximity between reference free-form text entry and a candidate free-form text request.

The invention discloses an image quality discrimination method based on remote sensing image phase correlation. The method comprises the following steps: pretreating a remote sensing image to obtain a periodic component frequency spectrum of the remote sensing image; adding N random phases in the periodic component frequency spectrum of the remote sensing image to form N remote sensing images added with the random phases; carrying out discrete inverse Fourier transform to obtain N time domain remote sensing images; calculating total variation values and phase related values of the N time domain remote sensing images peru1, peru2,..., peruN; and utilizing the image phase related values to carry out quality judgment on multiple remote sensing images. The method is a reference-free digital image quality judgment method without any reference image data and is more suitable for satellite remote sensing images. Compared with other reference-free quality judgment methods, the method provided by the invention is adaptive to various quality-reducing factors, and is not affected by ring, noise and other quality reducing factors.

The invention relates to a reference-free image quality evaluation method based on Walsh-Hadamard transformation. The method comprises steps that distortion images for training are selected; image transformation for each distortion image is carried out to acquire a local Walsh-Hadamard transformation image of the each distortion image; a rotation invariant uniform LBP operator is applied to zero sequency items and non-zero sequency items in three scales to carry out image characteristic extraction; for characteristic training, an SUR network is utilized to carry out characteristic training to acquire an image characteristic to subjective quality score mapping relationship model, the model is taken as an evaluation module, and image quality is evaluated.

The invention belongs to the field of image processing and provides a reference-free tone mapping image quality evaluation method based on color statistics and information entropy. According to the method, the technical proposal adopted by the invention is that an image quality evaluation method without reference tone mapping based on color statistics and information entropy is provided. The method comprises the following steps: first, data preparation; 2, extract color statistical features, mainly comprise that following three steps: (1) decomposing color channel; 2) carry out division normalization operation on that channels in (1) to obtain respective color normalization coefficient; (3) parameter fitting; 3, feature extraction of information entropy; Step 4, quality prediction. Featureextraction of the test set, input to the trained model, predict the quality of the test chart score. The invention is mainly applied to image processing occasions.

The invention provides a reference-free evaluation method for multi-distortion image quality. The method is an evaluation method based on bi-order structural distortion and non-local statistics. The method comprises the steps that first, downsampling is performed on a multi-distortion image to obtain multiple resolution images, and bi-order structural features of each resolution image are extracted and used for evaluating structural distortion in the image, wherein all the structural features form a first group of quality evaluation features; second, non-local similarity statistical features of each resolution image are extracted, and the features are used as a second group of quality evaluation features; and last, the two groups of features of the image are used as input, and a random forest is utilized to train a quality evaluation model of the multi-distortion image. The performance of the method is obviously superior to that of an existing reference-free image quality evaluation method, and the method has good cross-base performance and high extensibility.

A method and apparatus for identifying an inconsistency. A number of waves that propagate through a structure are generated. A response signal is generated in response to detecting at least a portion of the number of waves that propagate through the structure. A determination is made as to whether the response signal includes a reflected component. A presence of the inconsistency in the structure is indicated when the response signal includes the reflected component.

The invention discloses a general reference-free image quality evaluation method based on a local contrast mode. The method comprises acquiring histogram statistical characteristic vectors for the respective local binary mode characteristic image for 8 direction information images and 1 directionless information image for every distortionless image in the training stage, and making all the histogram statistical characteristic vectors to form a dictionary learning characteristic matrix; acquiring histogram statistical characteristic vectors for the respective local binary mode characteristic image for 8 direction information images and 1 directionless information image for a distortion image to be evaluated in the test stage, and making all the histogram statistical characteristic vectors to form a characteristic vector; and according to the dictionary learning characteristic matrix and the characteristic vector, utilizing a sparse algorithm to acquire a visual perception sparse characteristic vector, and then utilizing a support vector to realize regression, and obtaining an objective quality evaluation predicted value through prediction according to the visual perception sparse characteristic vector. The general reference-free image quality evaluation method based on a local contrast mode has the advantage of being effectively improve the correlation between an objective evaluation result and a subjective perception.

The invention discloses a reference-free image objective quality evaluation method based on gradient self-similarity. According to the process of the method, first, gradient filtering is performed on a to-be-evaluated distorted image to obtain an amplitude image of gradient information; second, information images in four directions are obtained according to the amplitude image of the gradient information, and a self-similarity image between the information image in each direction and the amplitude image is calculated; third, inter-pixel feature extraction method operation and intra-pixel feature extraction method operation are performed on the self-similarity images to obtain an inter-pixel feature graph and an intra-pixel feature graph; fourth, a histogram statistical method is adopted to perform statistical analysis on the inter-pixel feature graph and the intra-pixel feature graph; and last, support vectors are adopted to perform regression prediction on an objective quality evaluation predicted value of the to-be-evaluated distorted image according to histogram statistical feature vectors. The method has the advantages that influences of changes of image gradient self-similarity on visual quality can be fully considered, and therefore the correlation between an objective evaluation result and subjective perception can be effectively improved.

The invention discloses a reference-free stereo image quality objective evaluation method. At a training phase, a visual dictionary quality parallel table is obtained by obtaining a similarity image between a binocular competition response characteristic graph of each original undistorted stereo image and a binocular competition response characteristic graph of each distortion stereo image corresponding to each original undistorted stereo image, and a histogram characteristic vector of a local binary mode of the binocular competition response characteristic graph of each distortion stereo image corresponding to each original undistorted stereo image; and at a test phase, for any one distortion stereo image, a histogram characteristic vector corresponding to the distortion stereo image is obtained first of all, and then according to the constructed visual dictionary quality parallel table, an object quality evaluation prediction value of the distortion stereo image is obtained. The method has the following advantages: the calculation complexity is reduced, and since a stereo visual perception characteristic is taken into full consideration, correlation between an object evaluation result and subjective perception can be effectively improved.

The invention discloses a non-parametric miRNA data analysis method based on a miRBase database. The non-parametric miRNA data analysis method includes the following steps: a file preparation step; alogout data filtering step; a sRNA classified annotation step; a miRNA differential analysis step; a miRNA function and pathway analysis step; a miRNA sequence feature analysis step; and a result arrangement step. The non-parametric miRNA data analysis method based on a miRBase database has the advantages of performing analysis of miRNA sequencing data for reference-free miRNA sequences without the species; being comprehensive in the results including the miRNA analysis content involved and other measured small RNA information annotations; automatically arranging all the analysis results, andafter completing the analysis of each part, automatically counting the results, being visualized, and performing sorting and arrangement to enable the results to be arranged at a glance and used directly for report generation; and being visible for all the steps and being easy to query the errors.

The invention discloses a reference-free stereoscopic video quality objective evaluation method based on multi-view feature learning. The method comprises the following steps: performing curvelet transform on an image sequence, and extracting a coefficient to serve as a texture feature; comparing eight adjacent pixels with a central pixel; generating ten output modes; calculating the occurrence frequency of each mode, and averaging the occurrence frequencies to obtain an average value to serve as an airspace texture feature; performing dimension reduction to obtain a space domain feature; acquiring motion strength features of adjacent images, and calculating the average value to serve as a time domain feature; performing DCT (Discrete Cosine Transformation) on a tridimensional perception domain view, performing DCT coefficient modeling, extracting shape parameters, and calculating the average value to serve as a stereoscopic perception domain feature; performing SVM (Support Vector Machine) training; performing prediction by using an evaluation model to obtain an objective quality score; and weighting to obtain a finial quality score. The influences of a space domain, a time domainand a tridimensional perception feature on the stereoscopic video quality are combined to perform stereoscopic video quality evaluation, so that the accuracy of stereoscopic video objective quality accuracy is improved.

The invention discloses a reference-free spliced image quality evaluation method and system, and belongs to the technical field of image processing. The evaluation method comprises the following steps: firstly, calculating an adaptive threshold, and judging the detail complexity of a spliced image; then, determining the number of pixel points in the neighborhood of each pixel point according to the detail complexity of the spliced image, and acquiring a CLBP window gradient difference value of each pixel point through calculation; and then, acquiring the average CLBP window gradient differencevalue of the spliced image through calculation, so that the quality of the spliced image can be evaluated. According to the spliced image quality evaluation method provided by the invention, the quality of the spliced image is objectively evaluated by utilizing the average CLBP window gradient difference value (MCLBP _ M value) of the spliced image, the operation is simple, and an evaluation effect consistent with a subjective evaluation result can be achieved without reference images.

The invention discloses a grinding method based on a margin constraint condition. The method comprises following steps: step one, acquiring three-dimensional measurement data of a part, and reverselyreconstructing a reconstruction model of the part according to the three-dimensional measurement data; step two, performing initial matching to obtain an initial transformation matrix from the reconstruction model to a theoretical model; step three, performing accurate matching, completing accurate matching of the reconstruction model and the theoretical model through iterative operation, and obtaining machining reference and machining allowance of the part; step four, setting grinding parameters according to the machining reference and machining allowance which are obtained in step three, andgrinding the part. According to the method, the machining reference and the machining allowance of the part can be effectively determined, and the problem of difficulty in a numerical control abrasive belt self-adaptive grinding technology of reference-free blade parts is effectively solved.

The invention discloses a reference-free contrast distortion image quality evaluation method based on contrast enhancement. The method comprises the following steps of firstly, calculating a structural similarity index mean value and a variance between a distortion image and a contrast enhancement image as contrast enhancement characteristics; dividing the contrast distortion image into a plurality of superpixels, and calculating the mean value and the variance of the superpixels as superpixel characteristics; calculating the deviation of the contrast distortion image in the 0-degree direction, the 45-degree direction, the 90-degree direction and the 135-degree direction at each pixel point to form a deviation matrix, obtaining the deviation matrix characteristic values, and then obtainingthe deviation characteristics through calculation; combining the features to obtain a final feature vector; and sending into a support vector machine for training and testing to obtain an objective image quality evaluation result. The method fully considers the histogram of the image, the superpixel segmentation, the gray scale local deviation and the contrast distortion, and improves the qualityevaluation precision of the contrast distortion image.

The present invention presents a real-time synchronization system for power converters interconnected with the electrical network, whose operation is based on a structurally stable limit cycle oscillator and which develops pure sinusoidal trajectories, creating references free of harmonics and disturbances in network. The proposed invention has the advantage that it has a high degree of immunity and robustness within highly contaminated networks, either due to the presence of harmonics or other types of contamination that may exist in the network, with a better performance than the systems previously reported. Another advantage of the present invention is that regardless of the initial conditions that are established, the system always synchronizes with the signal of the network, guaranteeing a smooth transient from any initial condition to the limit cycle, so it does not require prior tuning. In addition, the proposed scheme does not require Phase-Locked Loop (PLL) or trigonometric functions for synchronization, thus reducing computational time and resources.