742 results about "Structural similarity" patented technology

The invention discloses a personalized commodity recommending method which integrates attributes and structural similarity. In the method, users and commodities are used as nodes with characteristic information to be mapped to a network by integrating the attribute information and structural similarity information, and an information network chart is established according to the purchasing relation between customers and the commodities; and interests and preference among user node pairs are measured by the integrated attributes and structural similarity in the information network chart, and the nearest neighbor is selected by the interests and the preference to improve the accuracy of recommending. On the basis of the recommending method, the invention also discloses a personalized commodity recommending method which integrates the measurement of the attributes and the structural similarity. In the system, the interests and the preference of the users are measured accurately by a computing method of integrating the similarity of the attributes and the similarity of node structure backgrounds in the information network chart, and the generation efficiency of the nearest neighbor is improved by utilizing clustering technology. The method and the system can be applied to electronic commerce, and provide personalized commodity recommending for the users.

The present invention provides peptides and peptidomimetics corresponding to part or to the entirety of the region encompassed by residues 360-386 of human p53, said peptides and peptidomimetics characterized by the ability to activate DNA binding of wild-type p53 and to select tumor-derived p53 mutants. Pharmaceutical compositions of the compounds of the invention and methods of using these compositions therapeutically are also provided.

A novel method and system for 3d-aided-2D face recognition under large pose and illumination variations is disclosed. The method and system includes enrolling a face of a subject into a gallery database using raw 3D data. The method also includes verifying and / or identifying a target face form data produced by a 2D imagining or scanning device. A statistically derived annotated face model is fitted using a subdivision-based deformable model framework to the raw 3D data. The annotated face model is capable of being smoothly deformed into any face so it acts as a universal facial template. During authentication or identification, only a single 2D image is required. The subject specific fitted annotated face model from the gallery is used to lift a texture of a face from a 2D probe image, and a bidirectional relighting algorithm is employed to change the illumination of the gallery texture to match that of the probe. Then, the relit texture is compared to the gallery texture using a view-dependent complex wavelet structural similarity index metric.

The invention discloses a no-reference structural sharpness image quality evaluation method, which comprises the following steps of: acquiring an original image input in a computer; preprocessing the original image, removing influence of isolated noise points on the sharpness of the original image and acquiring an original image to be evaluated; constructing a reference image for the original image to be evaluated through a low pass filter; respectively performing gradient calculation on the original image to be evaluated and the reference image, and extracting sub-image vectors with rich texture information; calculating the structural similarity between corresponding sub-image vectors so as to obtain structural similarity results of the sub-image vectors; and calculating no-reference structural sharpness by using the obtained structural similarity results of the sub-image vectors so as to obtain quality evaluation index no-reference structural sharpness of the original image. The reference image is constructed through an imaging model, no-reference image quality evaluation is performed by a reference image quality evaluation method aiming at image blurring, and the method is applied to the fields of imaging quality detection and control of an imaging system, evaluation of an image processing algorithm, and the like.

The invention discloses an image quality evaluating method based on visual character and structure similarity and relates to image quality evaluating. The method comprises the steps of: reading the pixel information of a reference image and an image to be evaluated, storing the read information in a matrix form and setting into matrixes x and y; dividing the spaces of the images into blocks unevenly and recording each block (n) so that the layouts of the image to be evaluated and the reference image are same; carrying out structural similarity (SSIM) index arithmetic on each block (n) of the reference image and the image to be evaluated; extracting the weight factor w(n) of each block (n); comprehensively weighting an SSIM index corresponding to each block (n) to obtain comprehensive image quality WMSSIM so as to finish the image quality evaluating method based on visual character and structure similarity.

There is disclosed a system and method for video coding, and more particularly to video coding that uses structural similarity (SSIM) based rate-distortion optimization methods to improve the perceptual quality of decoded video without increasing data rate, or to reduce the data rate of compressed video stream without sacrificing perceived quality of the decoded video. In an embodiment, the video coding system and method may be a SSIM-based rate-distortion optimization approach that involves minimizing a joint cost function defined as the sum of a data rate term and a distortion functions. The distortion function may be defined to be monotonically increasing with the decrease of SSIM and a Lagrange parameter may be utilized to control the trade-off between rate and distortion. The optimal Lagrange parameter may be found by utilizing the ratio between a reduced-reference SSIM model with respect to quantization step, and a data rate model with respect to quantization step. In an embodiment, a group-of-picture (GOP) level quantization parameter (QP) adjustment method may be used in multi-pass encoding to reduce the bit-rate while keeping similar perceptual video quality. In another embodiment, a frame level QP adjustment method may be used in single-pass encoding to achieve constant SSIM quality. In accordance with an embodiment, the present invention may be implemented entirely at the encoder side and may or may not require any change at the decoder, and may be made compatible with existing video coding standards.

The present invention discloses a parallelized human body behavior identification method. According to the method, skeleton data of Kinect is used as input; a distributed behavior identification algorithm is implemented based on a Spark computing framework; and a complete parallel identifying process is formed. Acquisition of the skeleton data of a human body is based on scene depth acquisition capacity of Kinect and the data is preprocessed to ensure invariability of displacement and scale of characteristics; and a human body structural vector, joint included angle information and skeleton weight bias are respectively selected for static behavior characteristics and a dynamic behavior searching algorithm for a structural similarity is provided. On the identification algorithm, a neural network algorithm is parallelized on Spark; a quasi-newton method L-BFGS is adopted to optimize a network weight updating process; and the training speed is obviously increased. According to an identification platform, a Hadoop distributed file system HDFS is used as a behavior data storage layer; Spark is applied to a universal resource manager YARN; the parallel neural network algorithm is used as an upper application; and the integral system architecture has excellent extendibility.

A novel method and system for 3d-aided-2D face recognition under large pose and illumination variations is disclosed. The method and system includes enrolling a face of a subject into a gallery database using raw 3D data. The method also includes verifying and / or identifying a target face form data produced by a 2D imagining or scanning device. A statistically derived annotated face model is fitted using a subdivision-based deformable model framework to the raw 3D data. The annotated face model is capable of being smoothly deformed into any face so it acts as a universal facial template. During authentication or identification, only a single 2D image is required. The subject specific fitted annotated face model from the gallery is used to lift a texture of a face from a 2D probe image, and a bidirectional relighting algorithm is employed to change the illumination of the gallery texture to match that of the probe. Then, the relit texture is compared to the gallery texture using a view-dependent complex wavelet structural similarity index metric.

The invention relates to image quality evaluation. To show the fidelity and third dimension of a generated three-dimensional image, the degree of damages of a compression algorithm to the three-dimensional image, the degree of interference of noises introduced by a transmission process on the quality of the three-dimensional image, the display naturalness of the three-dimensional image, and the like, the technical scheme adopted by the invention is that: a human-visual-system (HVS)-based structural similarity (SSIM) and characteristic matching three-dimensional image quality evaluation methodcomprises the following steps of: (1) comparing the luminance, contrast and structural similarity of left and right views of an original image with those of the left and right views of a test image by using a structure distortion method; (2) extracting luminance and contrast indexes; (3) simulating a human eye band-pass property principle according to wavelet decomposition to obtain a human visual signal to noise ratio evaluation index; (4) reflecting the third dimension of the three-dimensional image by using the ratio of number of left and right view matching points of the test image to thenumber of the left and right view matching points of the original image; and (5) rationally weighting all the indexes to obtain an overall evaluation index. The method is mainly applied to the image quality evaluation.

A system and method for matching one or more source schemas with one or more target schemas is provided. The matching between source and target schemas is performed by gathering inputs pertaining to the source and target schemas, wherein the inputs comprises a set of details in a predefined format. Thereafter, the gathered inputs are processed by comparing the source schemas with the target schemas. The processing is performed to identify a set of matches between the source and target schemas based on the linguistic similarity, structural similarity and functional similarity and relationship between the source and target schemas. Subsequently, the identified matches are stored.

The invention relates to a comprehensive body similarity detection method, which comprises the steps of constructing tree structures of bodies, calculating semantic similarity, pragmatic similarity, structural similarity and attribute similarity of a source node and a target node, and obtaining an integral similarity by weighted summation. The attribute characteristics and structural characteristics of the bodies are considered, semantic information contained in the bodies is taken as an important index for balancing the similarity, and weight assignments and network search results are added for dynamic update aiming at the characteristics of different bodies, so the accuracy of body similarity detection is improved by fully using the characteristics of the bodies to calculate the similarity of the bodies without obviously increasing the calculation complexity.

The invention discloses a method for partial reference evaluation of wireless videos based on space-time domain feature extraction, which relates to a method for evaluating video quality. On the basis of performing profound understanding and detailed analysis on the existing video objective quality evaluation model, by combining visual characteristics of human eyes, the invention provides the method for the partial reference evaluation of the wireless videos based on the space-time domain feature extraction to improve the conventional SSIM model. The method takes the fluency of the time domain and the structural similarity and the definition of the space domain of the videos as main evaluation indexes, and under the condition of ensuring the evaluation accuracy, the method extracts characteristic parameters of ST domains (the space domain and the time domain), establishes a new evaluation model, reduces the reference data needed by the evaluation and lowers the computational complexity to ensure that the evaluation model is suitable for evaluating the quality of wireless transmission videos in real time.

The invention discloses an image super-resolution reconstruction method based on dictionary learning and structure similarity, mainly solving the problem that a reconstructed image based on the prior art has a fuzzy surface and a serious marginal sawtooth phenomenon. The image super-resolution reconstruction method comprises the following implementation steps of: (1) acquiring a training sample pair; (2) learning a pair of high / low-resolution dictionaries by using structural similarity (SSIM) and K-SVD (K-Singular Value Decomposition) methods; (3) working out a sparse expression coefficient of an input low-resolution image block; (4) reestablishing a high-resolution image block Xi by using the high-resolution dictionaries and the sparse coefficient; (5) fusing the high-resolution image block Xi to obtain a high-resolution image X'I subjected to information fusion; (6) obtaining a high-resolution image X according to the high-resolution image X'I; and (7) carrying out high-frequency information enhancement on the high-resolution image X through error compensation to obtain a high-resolution image subjected to high-frequency information enhancement. A simulation experiment shows that the image super-resolution reconstruction method has the advantages of clear image surface and sharpened margin and can be used for image identification and target classification.

Method and system for low complexity assessment of quality of an image are presented. By performing multiresolution decomposition of images using, for example, a discrete wavelet transform, and determining a metric based on a structural similarity index or a structural similarity map, a structural similarity score, characterizing similarity between images with a high degree of accuracy, is produced. The processing time is much smaller in comparison to that required by other methods producing image quality metrics of comparable accuracy.

The invention discloses an image quality evaluating method based on multi-scale structure similarity weighted aggregate. The traditional method based on structure similarity has defects in many aspects, in the method disclosed by the invention, the visual attention characteristics and multilayer visual characteristics of a human visual system are fully considered to realize the weighted aggregatefor the structure similarity in intra-scale and inter-scale manners, and the objective evaluation to a full reference image is carried out. The image quality evaluating method mainly comprises the steps of: in the scales, generating a weight coefficient of a corresponding image block based on visual saliency, and performing weighted aggregate on the structural similarity in the intra-scale manner; and among the scales, performing the weighted aggregate on the structure similarity in the inter-scale manner by using the weighted coefficient obtained through training or from experience.

The invention discloses a deep learning image denoising method integrating multiple scales and an attention mechanism. A peak signal-to-noise ratio and the structural similarity of Gaussian denoisingoutput of a deep learning model to an image are improved. The method mainly comprises the following steps: selecting an appropriate high-definition image training set, and making a corresponding noiseimage; building a deep learning network model and combining a multi-scale mechanism and an attention mechanism; training by using the selected training set and the built deep learning network model and taking the minimized loss function as a target until the loss function converges; and inputting a to-be-denoised image in the test set into the trained denoising network to obtain a denoised image.Compared with a traditional denoising method and an existing deep learning denoising method, the multi-scale and attention mechanism integrated deep learning denoising scheme provided by the invention has the advantage that the peak signal to noise ratio (PSNR) index is obviously improved.

The invention relates to an integrated design and manufacture method of a full resin airplane low-velocity flutter wind tunnel model based on photocuring rapid prototyping. The method first conducts the integrated design of the flutter model according to the actual structure of an airplane, the requirement of a wind tunnel experiment and the parameters of photocuring resin material and based on the photocuring resin material, and makes the full resin flutter model in an integrated way on the basis of the optimization of the photocuring rapid process. The method proposes a new design and manufacture concept of the flutter model of low modulus material, gets rid of unnecessary assembly links by the use of the advantages of accuracy, quickness and low cost of the photocuring rapid prototyping technology, the uniformity of the model material, the low modulus of the resin material and isotropy characteristic, and designs and manufactures the full resin flutter wind tunnel model meeting the full dynamic similarity. The method overcomes the defects of traditional technologies, improves the manufacture precision of the wind tunnel model, reduces cost, shortens the period and realizes structural similarity, thus boosting the development speed of an airplane.

In a direct sequence spread spectrum data communication system an information bit is mixed with a pseudorandom noise or spreading code to produce modulated codeword for transmission. A method of bandwidth efficient M-ary phase shift key modulation encoding at least 16 bits of data to a single codeword is disclosed for extending the data rate of a spread spectrum system. Interoperability with legacy devices is maximized by maintaining structural similarity between the modulated waveforms of the extended data rate and legacy systems.

The invention provides a method and a device for confirming web structure similarity. The method includes steps of confirming template feature vectors of webs according to DOM trees of the webs, calculating web structure similarity of the template feather vectors, and then finding or matching. Through the above processes, the method for confirming web structure similarity overcomes shortages that the method in the prior art can not calculate web structure similarity, and when operators find a cheat website, the operators can find cheat websites with identical web structures through finding home pages with similar template feature vectors. In addition, aggregate of the cheat websites can be automatically and fast found through matching and finding template feature vectors of all home page templates.

The embodiment of the invention provides a category label matching and mapping method and device. The method includes the steps that label information of source category labels and label information of target category labels are obtained; according to a label character string, literal similarity of all the source category labels and literal similarity of all the target category labels are determined; label vectorization information is obtained according to the label information and combined with label path information to determine semantic similarity of all the source category labels and semantic similarity of all the target category labels; according to the label path information, the structural similarity of all the source category labels and structural similarity of all the target category labels are determined; according to at least one of the literal similarity, the semantic similarity and the structural similarity of all the source category labels and all the target category labels, the source category label and the target category label with the similarity meeting set conditions are selected out, and a mapping relation is set up. Similarity matching and mapping of the labels can be achieved fast and accurately, the matching and mapping efficiency is high, manual participation is not needed, and manpower, material resources and financial resources are saved.

The invention relates to a photovoltaic module unsupervised defect detection method based on a GAN improved algorithm. The method comprises the following steps: step 1, training a generative adversarial network module according to an SSIM-GAN algorithm model; 2, training an encoder network module according to the SSIM-GAN algorithm model; 3, constructing a defect discrimination module; step 4, carrying out image detection. The method provided by the invention has the beneficial effects that the method can effectively detect tiny and diverse defects of the photovoltaic module, and can solve theproblem of unbalanced samples; an SSIM-GAN model is constructed, and the difference between the images is described by using structural similarity; a normal image is generated through a generative adversarial network; the images are mapped to the corresponding hidden spaces through the encoder network, whether the images to be detected have defects or not is judged through the defect detection module, rapid and accurate detection of unknown defects can be achieved under the condition that the number of the defect images is small, and the method has the advantages of being high in environmental adaptability and robustness.

An image interpolating method and apparatus, in which horizontal and vertical Differences of Absolute Inter-channel Differences (DAIDs) are calculated from a color filter array (CFA) image, and an unknown pixel is interpolated in horizontal and vertical directions estimated in consideration of the DAIDs of R, G, and B pixels.Therefore, the image interpolating method and apparatus provide a large Peak Signal and Noise Ratio (PSNR), a Structural Similarity (SSIM), and high visual quality images.

The invention discloses an image denoising method based on multi-scale parallel CNNs, comprising five steps: 1, building a multi-scale parallel convolution neural network model, wherein only that convolution layer and the activation lay are included, and residual learning is added at the same time; 2, setting training parameter of a multi-scale parallel convolution neural network model; 3, selecting a training set and cutting and flipping the selected training image to enhance the number of the training sets; 4, selecting the mean square error as a loss function and train a multi-scale parallel convolution neural network model with a minimization loss function to obtain an image denoising model; 5, inputting the noise image of arbitrary size to the image denoising model, and outputting thedenoised clean image. The invention can preserve the edge information and the detail information of the image as much as possible while denoising, can improve the structural similarity of the image,and can obtain a high-quality denoised image.

The invention belongs to the technical field of depth image inpainting, and particularly relates to a Kinect depth image inpainting method based on improved trilateral filtering for kinect depth images. The method comprises the steps that depth images and color images are synchronously acquired by utilizing Kinect; the color images and the depth images are aligned; edge information of the depth images is extracted; edge information of the color images is extracted; non-boundary texture information in the color images is removed; pixel points of which the depth values are incorrect are found in the depth images by using a region growing method and the incorrect depth values of the points are removed; and filling inpainting is performed on the hole areas of the depth images by using the improved trilateral filtering method based on aberration and structural similarity coefficient. The method has great hole filling effect for the kinect depth images so that the edge information of the depth images can be greatly maintained.

The invention discloses a de-noising method of filtering images in size adaptive block matching transform domains. Less false signals are introduced as two-dimension transformation of each image block in the block matching 3D (BM3D) in a basic estimation stage is abandoned by the method; image details can be well preserved as the block number in blocking matching groups of the method is less than the block number in the BM3D method. The image de-noising performance of the method is further improved as the method adaptively selects the block size based on form components during block matching. The current general objective evaluation of image de-nosing includes peak signal noise ratio (PSNR) and mean structural similarity (MSSIM), and according to the method, the de-noising calculation results of a plurality of standard images provided on BM3D networks are higher than the results of the BM3D method on the basis of the two objective evaluations and under all noise intensities.

The invention discloses a non-convex compressed sensing image reconstruction method based on a redundant dictionary and structure sparsity. A reconstruction process of the method includes: observing original image blocks; using a mutual neighboring technology for clustering observation vectors; using a genetic algorithm for finding optimal atom combinations in a dictionary direction for each class of observation vectors, and preserving species; after species expansion operation is executed on each image block, using a clonal selection algorithm for finding an optimal atom combination on scale and displacement in a determined direction for each image block; reconstructing each image block by the optimal atom combination; and piecing all the constructed image blocks in sequence to form an entire constructed image. Image structure sparsity prior and redundant dictionary direction features are fully utilized, the genetic algorithm is combined with the clonal selection algorithm, and the method is used as a nonlinear optimization reconstruction method to realize image reconstruction. The reconstructed image is good in visual effect, high in peak signal noise ratio and structural similarity, and the method can be used for non-convex compressed sensing reconstruction of image signals.

The invention relates to an ultrahigh definition video image quality objective evaluation method based on the visual perception characteristic. The method includes the steps of conducting 16*16 partitioning on each frame of an input original ultrahigh definition video sequence and each frame of a damaged ultrahigh definition video sequence so as to obtain macro blocks, obtaining the structural similarity value SSIMij of each block, calculating the weight wij of each macro block in an ultrahigh definition video image, conducting weighting on the SSIMij value of each macro block of the current frame through the corresponding wij so as to obtain the ultrahigh definition image quality of the single frame, and conducting weighting on the image quality of each frame of the whole video sequence so as to obtain an image quality objective evaluation result of the whole video sequence. According to the method, on the basis of an existing SSIM algorithm, luminance cover factors, texture complexity and movement information are taken into consideration, high definition and human eye vision characteristics of an ultrahigh definition video are taken into consideration as well, and weighting is conducted on spatial position information. The experiments show that compared with the traditional SSIM algorithm, the method has the advantage that consistency with the subjective evaluation result is greatly improved.

The invention belongs to the field of image processing. According to the invention, the consistence of an objective evaluation result and subjective evaluation is higher; and moreover, the development of a 3DTechnology is promoted to a certain extent. According to the technical scheme provided by the invention, a three-dimensional image quality objective evaluation method based on graph-based visual saliency comprises following steps of 1), by using a structural similarity SSIM algorithm, calculating comparison functions of the brightness, contrast, and structures of a reference right image and a right image; 2), through adoption of a GBVS (Graph-based Visual Saliency) graph saliency calculation model provided by the improvement of a characteristic graph technical method, calculating the saliency characteristics of a distorted image; and 3), carrying out weighted calculation on the image quality weights obtained in the step 1) and the saliency graph of the distorted image obtained in the step 2). The method is mainly applied to image processing.

The invention provides an image registration method based on improved structural similarity. According to the invention, the improved structural similarity serves as the objective function of the image registration for the first time; four parameters of the two-dimensional image rigid body transformation are obtained through translation, rotation and consistent scaling along the X-axis and Y-axis; and the single-modal and multimodal images are analyzed in detail based on the registration algorithm and performance of the structural similarity and are compared with that based on a normalized mutual information registration algorithm. The result shows that when an absolute value is extracted during defining the structural similarity, the structural similarity has favorable features of a convex function; for either the single-modal image registration or the multimodal image registration, the structural similarity serving as the measure function can achieve the sub-pixel registration with registration precision and robustness better than that based on the classic normalized mutual information registration algorithm; and if K1 is less than or equal to 0.000001, and K2 is less than or equal to 0.000003, the two-value image can achieve the pixel registration.